Last active
October 27, 2021 10:10
-
-
Save mur6/f79c89699aa151b2cf4c2da62701aaad to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| {"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"microsoft_ Mesh_Transformers.ipynb","provenance":[],"mount_file_id":"1viLALOavIu5Jb3ihbNFa1N-aUPSmGdmE","authorship_tag":"ABX9TyP4+fiLxcFabYggGdsDmhO1"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"KR3WhnEG7ZCt","executionInfo":{"status":"ok","timestamp":1635240495471,"user_tz":-540,"elapsed":292,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"8ec37563-ca8b-40c0-a5da-ec9e29524018"},"source":["%cd /content"],"execution_count":11,"outputs":[{"output_type":"stream","name":"stdout","text":["/content\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"EcmJJt9drU0W","executionInfo":{"status":"ok","timestamp":1635240498882,"user_tz":-540,"elapsed":1396,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"6e522a37-fa14-4ce5-e7b0-121857b7c3df"},"source":["!git clone -l -s https://github.com/microsoft/MeshTransformer MeshTransformer"],"execution_count":12,"outputs":[{"output_type":"stream","name":"stdout","text":["Cloning into 'MeshTransformer'...\n","warning: --local is ignored\n","remote: Enumerating objects: 199, done.\u001b[K\n","remote: Counting objects: 100% (199/199), done.\u001b[K\n","remote: Compressing objects: 100% (165/165), done.\u001b[K\n","remote: Total 199 (delta 72), reused 132 (delta 29), pack-reused 0\u001b[K\n","Receiving objects: 100% (199/199), 6.45 MiB | 16.86 MiB/s, done.\n","Resolving deltas: 100% (72/72), done.\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"_gRPfiLEGdnu","executionInfo":{"status":"ok","timestamp":1635240501299,"user_tz":-540,"elapsed":557,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"815a1870-8c1f-4b70-ab51-7a5208258458"},"source":["%cd MeshTransformer"],"execution_count":13,"outputs":[{"output_type":"stream","name":"stdout","text":["/content/MeshTransformer\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"kYtIEpp37--m","executionInfo":{"status":"ok","timestamp":1635240673390,"user_tz":-540,"elapsed":11494,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"85f89026-4a3d-437d-e219-69c08be3d53c"},"source":["!git submodule update --init --recursive"],"execution_count":18,"outputs":[{"output_type":"stream","name":"stdout","text":["Submodule 'manopth' (https://github.com/hassony2/manopth) registered for path 'manopth'\n","Submodule 'transformers' (https://github.com/huggingface/transformers) registered for path 'transformers'\n","Cloning into '/content/MeshTransformer/manopth'...\n","Cloning into '/content/MeshTransformer/transformers'...\n","Submodule path 'manopth': checked out '4f1dcad1201ff1bfca6e065a85f0e3456e1aa32b'\n","Submodule path 'transformers': checked out '067923d3267325f525f4e46f357360c191ba562e'\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"QM0k0_O-7yhO","executionInfo":{"status":"ok","timestamp":1635240678030,"user_tz":-540,"elapsed":825,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"6656e915-41f4-46da-a5ef-9fc8730fc17a"},"source":["!python setup.py build develop"],"execution_count":19,"outputs":[{"output_type":"stream","name":"stdout","text":["running build\n","running build_py\n","copying metro/modeling/bert/modeling_bert.py -> build/lib/metro/modeling/bert\n","copying metro/modeling/bert/modeling_utils.py -> build/lib/metro/modeling/bert\n","copying metro/modeling/bert/file_utils.py -> build/lib/metro/modeling/bert\n","copying metro/modeling/bert/modeling_metro.py -> build/lib/metro/modeling/bert\n","running develop\n","running egg_info\n","creating metro.egg-info\n","writing metro.egg-info/PKG-INFO\n","writing dependency_links to metro.egg-info/dependency_links.txt\n","writing top-level names to metro.egg-info/top_level.txt\n","writing manifest file 'metro.egg-info/SOURCES.txt'\n","adding license file 'LICENSE'\n","adding license file 'NOTICE.md'\n","writing manifest file 'metro.egg-info/SOURCES.txt'\n","running build_ext\n","Creating /usr/local/lib/python3.7/dist-packages/metro.egg-link (link to .)\n","Adding metro 0.1.0 to easy-install.pth file\n","\n","Installed /content/MeshTransformer\n","Processing dependencies for metro==0.1.0\n","Finished processing dependencies for metro==0.1.0\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":926},"id":"wAp_-1p88Mjk","executionInfo":{"status":"ok","timestamp":1635240724484,"user_tz":-540,"elapsed":10461,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"1650a969-4728-41f3-e8f2-7ed4405f842d"},"source":["!pip install -r requirements.txt"],"execution_count":21,"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting yacs\n"," Downloading yacs-0.1.8-py3-none-any.whl (14 kB)\n","Requirement already satisfied: cython in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 2)) (0.29.24)\n","Requirement already satisfied: opencv-python in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 3)) (4.1.2.30)\n","Requirement already satisfied: tqdm in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 4)) (4.62.3)\n","Requirement already satisfied: nltk in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 5)) (3.2.5)\n","Requirement already satisfied: numpy in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 6)) (1.19.5)\n","Requirement already satisfied: scipy==1.4.1 in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 7)) (1.4.1)\n","Collecting chumpy\n"," Downloading chumpy-0.70.tar.gz (50 kB)\n","\u001b[K |████████████████████████████████| 50 kB 3.9 MB/s \n","\u001b[?25hCollecting boto3\n"," Downloading boto3-1.19.3-py3-none-any.whl (131 kB)\n","\u001b[K |████████████████████████████████| 131 kB 16.2 MB/s \n","\u001b[?25hRequirement already satisfied: requests in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 10)) (2.23.0)\n","Requirement already satisfied: PyYAML in /usr/local/lib/python3.7/dist-packages (from yacs->-r requirements.txt (line 1)) (3.13)\n","Requirement already satisfied: six in /usr/local/lib/python3.7/dist-packages (from nltk->-r requirements.txt (line 5)) (1.15.0)\n","Collecting jmespath<1.0.0,>=0.7.1\n"," Downloading jmespath-0.10.0-py2.py3-none-any.whl (24 kB)\n","Collecting s3transfer<0.6.0,>=0.5.0\n"," Downloading s3transfer-0.5.0-py3-none-any.whl (79 kB)\n","\u001b[K |████████████████████████████████| 79 kB 7.3 MB/s \n","\u001b[?25hCollecting botocore<1.23.0,>=1.22.3\n"," Downloading botocore-1.22.3-py3-none-any.whl (8.0 MB)\n","\u001b[K |████████████████████████████████| 8.0 MB 55.3 MB/s \n","\u001b[?25hRequirement already satisfied: python-dateutil<3.0.0,>=2.1 in /usr/local/lib/python3.7/dist-packages (from botocore<1.23.0,>=1.22.3->boto3->-r requirements.txt (line 9)) (2.8.2)\n","Collecting urllib3<1.27,>=1.25.4\n"," Downloading urllib3-1.26.7-py2.py3-none-any.whl (138 kB)\n","\u001b[K |████████████████████████████████| 138 kB 46.4 MB/s \n","\u001b[?25hRequirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests->-r requirements.txt (line 10)) (2.10)\n","Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests->-r requirements.txt (line 10)) (3.0.4)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests->-r requirements.txt (line 10)) (2021.5.30)\n"," Downloading urllib3-1.25.11-py2.py3-none-any.whl (127 kB)\n","\u001b[K |████████████████████████████████| 127 kB 50.6 MB/s \n","\u001b[?25hBuilding wheels for collected packages: chumpy\n"," Building wheel for chumpy (setup.py) ... \u001b[?25l\u001b[?25hdone\n"," Created wheel for chumpy: filename=chumpy-0.70-py3-none-any.whl size=58285 sha256=15ea83b4f23e0d8070d6828a7ab70bbc43de0a8721f30804cf80e7187da93540\n"," Stored in directory: /root/.cache/pip/wheels/59/68/de/5e0c5d77e573e8c150e69e07a25035e6b6a04952d6e1814dbc\n","Successfully built chumpy\n","Installing collected packages: urllib3, jmespath, botocore, s3transfer, yacs, chumpy, boto3\n"," Attempting uninstall: urllib3\n"," Found existing installation: urllib3 1.24.3\n"," Uninstalling urllib3-1.24.3:\n"," Successfully uninstalled urllib3-1.24.3\n","\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n","datascience 0.10.6 requires folium==0.2.1, but you have folium 0.8.3 which is incompatible.\u001b[0m\n","Successfully installed boto3-1.19.3 botocore-1.22.3 chumpy-0.70 jmespath-0.10.0 s3transfer-0.5.0 urllib3-1.25.11 yacs-0.1.8\n"]},{"output_type":"display_data","data":{"application/vnd.colab-display-data+json":{"pip_warning":{"packages":["urllib3"]}}},"metadata":{}}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"KobmbWnY8aVT","executionInfo":{"status":"ok","timestamp":1635240761952,"user_tz":-540,"elapsed":3442,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"5ec5cfd7-a3e7-4b15-dcbf-ec0be76db713"},"source":["!pip install matplotlib"],"execution_count":23,"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: matplotlib in /usr/local/lib/python3.7/dist-packages (3.2.2)\n","Requirement already satisfied: numpy>=1.11 in /usr/local/lib/python3.7/dist-packages (from matplotlib) (1.19.5)\n","Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.7/dist-packages (from matplotlib) (0.10.0)\n","Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib) (1.3.2)\n","Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib) (2.4.7)\n","Requirement already satisfied: python-dateutil>=2.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib) (2.8.2)\n","Requirement already satisfied: six in /usr/local/lib/python3.7/dist-packages (from cycler>=0.10->matplotlib) (1.15.0)\n"]}]},{"cell_type":"code","metadata":{"id":"1gyW4Y-s90gZ","executionInfo":{"status":"ok","timestamp":1635244522571,"user_tz":-540,"elapsed":518,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}}},"source":["!opendr==0.78"],"execution_count":28,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Hr7_RcCD8d55","executionInfo":{"status":"ok","timestamp":1635241159570,"user_tz":-540,"elapsed":26780,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"c178190f-7e0a-414d-83fb-af07516c983f"},"source":["!pip install opendr"],"execution_count":27,"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting opendr\n"," Using cached opendr-0.78.tar.gz (581 kB)\n"," Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n","Requirement already satisfied: Cython in /usr/local/lib/python3.7/dist-packages (from opendr) (0.29.24)\n","Requirement already satisfied: chumpy>=0.58 in /usr/local/lib/python3.7/dist-packages (from opendr) (0.70)\n","Requirement already satisfied: matplotlib in /usr/local/lib/python3.7/dist-packages (from opendr) (3.2.2)\n","Requirement already satisfied: scipy>=0.13.0 in /usr/local/lib/python3.7/dist-packages (from chumpy>=0.58->opendr) (1.4.1)\n","Requirement already satisfied: six>=1.11.0 in /usr/local/lib/python3.7/dist-packages (from chumpy>=0.58->opendr) (1.15.0)\n","Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib->opendr) (1.3.2)\n","Requirement already satisfied: python-dateutil>=2.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib->opendr) (2.8.2)\n","Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.7/dist-packages (from matplotlib->opendr) (0.10.0)\n","Requirement already satisfied: numpy>=1.11 in /usr/local/lib/python3.7/dist-packages (from matplotlib->opendr) (1.19.5)\n","Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib->opendr) (2.4.7)\n","Building wheels for collected packages: opendr\n"," Building wheel for opendr (setup.py) ... \u001b[?25lerror\n","\u001b[31m ERROR: Failed building wheel for opendr\u001b[0m\n","\u001b[?25h Running setup.py clean for opendr\n","Failed to build opendr\n","Installing collected packages: opendr\n"," Running setup.py install for opendr ... \u001b[?25l\u001b[?25herror\n","\u001b[31mERROR: Command errored out with exit status 1: /usr/bin/python3 -u -c 'import io, os, sys, setuptools, tokenize; sys.argv[0] = '\"'\"'/tmp/pip-install-w7x6oej_/opendr_22ab300b85ae4fbb85d57859b0b2b1e0/setup.py'\"'\"'; __file__='\"'\"'/tmp/pip-install-w7x6oej_/opendr_22ab300b85ae4fbb85d57859b0b2b1e0/setup.py'\"'\"';f = getattr(tokenize, '\"'\"'open'\"'\"', open)(__file__) if os.path.exists(__file__) else io.StringIO('\"'\"'from setuptools import setup; setup()'\"'\"');code = f.read().replace('\"'\"'\\r\\n'\"'\"', '\"'\"'\\n'\"'\"');f.close();exec(compile(code, __file__, '\"'\"'exec'\"'\"'))' install --record /tmp/pip-record-kugxry_d/install-record.txt --single-version-externally-managed --compile --install-headers /usr/local/include/python3.7/opendr Check the logs for full command output.\u001b[0m\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"3akRQ_-q7gB6","executionInfo":{"status":"ok","timestamp":1635240849962,"user_tz":-540,"elapsed":1799,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"c3987995-22a8-444b-e4d4-ed85df01e7b8"},"source":["!python ./metro/tools/end2end_inference_bodymesh.py --resume_checkpoint ./models/metro_release/metro_3dpw_state_dict.bin --image_file_or_path ./samples/human-body"],"execution_count":25,"outputs":[{"output_type":"stream","name":"stdout","text":["Traceback (most recent call last):\n"," File \"./metro/tools/end2end_inference_bodymesh.py\", line 28, in <module>\n"," from metro.utils.renderer import Renderer, visualize_reconstruction, visualize_reconstruction_test, visualize_reconstruction_no_text, visualize_reconstruction_and_att_local\n"," File \"/content/MeshTransformer/metro/utils/renderer.py\", line 14, in <module>\n"," from opendr.camera import ProjectPoints\n","ModuleNotFoundError: No module named 'opendr'\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"6ztg-TXJrUep","executionInfo":{"status":"ok","timestamp":1635236561420,"user_tz":-540,"elapsed":80550,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"4bdaa4b3-7d8f-417f-e88d-bc86e2af22de"},"source":["!pip install torch==1.4.0 torchvision==0.5.0"],"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting torch==1.4.0\n"," Using cached torch-1.4.0-cp37-cp37m-manylinux1_x86_64.whl (753.4 MB)\n","Collecting torchvision==0.5.0\n"," Using cached torchvision-0.5.0-cp37-cp37m-manylinux1_x86_64.whl (4.0 MB)\n","Requirement already satisfied: six in /usr/local/lib/python3.7/dist-packages (from torchvision==0.5.0) (1.15.0)\n","Requirement already satisfied: numpy in /usr/local/lib/python3.7/dist-packages (from torchvision==0.5.0) (1.19.5)\n","Requirement already satisfied: pillow>=4.1.1 in /usr/local/lib/python3.7/dist-packages (from torchvision==0.5.0) (7.1.2)\n","Installing collected packages: torch, torchvision\n"," Attempting uninstall: torch\n"," Found existing installation: torch 1.9.0+cu111\n"," Uninstalling torch-1.9.0+cu111:\n"," Successfully uninstalled torch-1.9.0+cu111\n","\u001b[31mERROR: Operation cancelled by user\u001b[0m\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"w6mvLzJWsJ7b","executionInfo":{"status":"ok","timestamp":1635237088691,"user_tz":-540,"elapsed":412,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"aa21cb11-3ef1-4f11-ed6f-ea0e9bb61fc7"},"source":["!nvcc --version"],"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["nvcc: NVIDIA (R) Cuda compiler driver\n","Copyright (c) 2005-2020 NVIDIA Corporation\n","Built on Mon_Oct_12_20:09:46_PDT_2020\n","Cuda compilation tools, release 11.1, V11.1.105\n","Build cuda_11.1.TC455_06.29190527_0\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"rjUqAmMzumcS","executionInfo":{"status":"ok","timestamp":1635237134906,"user_tz":-540,"elapsed":5,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"5ca99305-a6e5-4c9f-c42d-cfd5fcabcc3a"},"source":["%cd .."],"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["/\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"yp_ZCh3ouo3Z","executionInfo":{"status":"ok","timestamp":1635237190723,"user_tz":-540,"elapsed":2236,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"96ad2d54-dcb3-4cac-ef50-8548e901aade"},"source":["!git clone -l -s https://github.com/NVIDIA/apex.git"],"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Cloning into 'apex'...\n","warning: --local is ignored\n","remote: Enumerating objects: 8466, done.\u001b[K\n","remote: Counting objects: 100% (553/553), done.\u001b[K\n","remote: Compressing objects: 100% (347/347), done.\u001b[K\n","remote: Total 8466 (delta 316), reused 353 (delta 194), pack-reused 7913\u001b[K\n","Receiving objects: 100% (8466/8466), 14.38 MiB | 22.79 MiB/s, done.\n","Resolving deltas: 100% (5715/5715), done.\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"899fchf7u58i","executionInfo":{"status":"ok","timestamp":1635237213759,"user_tz":-540,"elapsed":279,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"cc9b9741-a23e-455e-d20c-833530ef37b3"},"source":["%cd apex"],"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["/apex\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"YpLNwCt0u715","executionInfo":{"status":"ok","timestamp":1635238865523,"user_tz":-540,"elapsed":1636982,"user":{"displayName":"Taichi Muraki","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GiB5e_ohaBJFC9uV-Z-KaibIQGS8XX9tb36VRniGQ=s64","userId":"04137847541288404485"}},"outputId":"bb8f144a-5926-466f-d5a5-0123da33d836"},"source":["!python setup.py install --cuda_ext --cpp_ext"],"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda'\n","\n","Warning: Torch did not find available GPUs on this system.\n"," If your intention is to cross-compile, this is not an error.\n","By default, Apex will cross-compile for Pascal (compute capabilities 6.0, 6.1, 6.2),\n","Volta (compute capability 7.0), Turing (compute capability 7.5),\n","and, if the CUDA version is >= 11.0, Ampere (compute capability 8.0).\n","If you wish to cross-compile for a single specific architecture,\n","export TORCH_CUDA_ARCH_LIST=\"compute capability\" before running setup.py.\n","\n","\n","\n","torch.__version__ = 1.9.0+cu111\n","\n","\n","setup.py:67: UserWarning: Option --pyprof not specified. Not installing PyProf dependencies!\n"," warnings.warn(\"Option --pyprof not specified. Not installing PyProf dependencies!\")\n","\n","Compiling cuda extensions with\n","nvcc: NVIDIA (R) Cuda compiler driver\n","Copyright (c) 2005-2020 NVIDIA Corporation\n","Built on Mon_Oct_12_20:09:46_PDT_2020\n","Cuda compilation tools, release 11.1, V11.1.105\n","Build cuda_11.1.TC455_06.29190527_0\n","from /usr/local/cuda/bin\n","\n","running install\n","running bdist_egg\n","running egg_info\n","creating apex.egg-info\n","writing apex.egg-info/PKG-INFO\n","writing dependency_links to apex.egg-info/dependency_links.txt\n","writing top-level names to apex.egg-info/top_level.txt\n","writing manifest file 'apex.egg-info/SOURCES.txt'\n","/usr/local/lib/python3.7/dist-packages/torch/utils/cpp_extension.py:370: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils backend.\n"," warnings.warn(msg.format('we could not find ninja.'))\n","adding license file 'LICENSE'\n","writing manifest file 'apex.egg-info/SOURCES.txt'\n","installing library code to build/bdist.linux-x86_64/egg\n","running install_lib\n","running build_py\n","creating build\n","creating build/lib.linux-x86_64-3.7\n","creating build/lib.linux-x86_64-3.7/apex\n","copying apex/__init__.py -> build/lib.linux-x86_64-3.7/apex\n","copying apex/_autocast_utils.py -> build/lib.linux-x86_64-3.7/apex\n","creating build/lib.linux-x86_64-3.7/apex/pyprof\n","copying apex/pyprof/__init__.py -> build/lib.linux-x86_64-3.7/apex/pyprof\n","creating build/lib.linux-x86_64-3.7/apex/contrib\n","copying apex/contrib/__init__.py -> build/lib.linux-x86_64-3.7/apex/contrib\n","creating build/lib.linux-x86_64-3.7/apex/transformer\n","copying apex/transformer/__init__.py -> build/lib.linux-x86_64-3.7/apex/transformer\n","copying apex/transformer/parallel_state.py -> build/lib.linux-x86_64-3.7/apex/transformer\n","copying apex/transformer/enums.py -> build/lib.linux-x86_64-3.7/apex/transformer\n","creating build/lib.linux-x86_64-3.7/apex/mlp\n","copying apex/mlp/__init__.py -> build/lib.linux-x86_64-3.7/apex/mlp\n","copying apex/mlp/mlp.py -> build/lib.linux-x86_64-3.7/apex/mlp\n","creating build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/__version__.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/rnn_compat.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/__init__.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/wrap.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/_initialize.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/frontend.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/_amp_state.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/handle.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/opt.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/amp.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/compat.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/utils.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/_process_optimizer.py -> build/lib.linux-x86_64-3.7/apex/amp\n","copying apex/amp/scaler.py -> build/lib.linux-x86_64-3.7/apex/amp\n","creating build/lib.linux-x86_64-3.7/apex/normalization\n","copying apex/normalization/__init__.py -> build/lib.linux-x86_64-3.7/apex/normalization\n","copying apex/normalization/fused_layer_norm.py -> build/lib.linux-x86_64-3.7/apex/normalization\n","creating build/lib.linux-x86_64-3.7/apex/multi_tensor_apply\n","copying apex/multi_tensor_apply/__init__.py -> build/lib.linux-x86_64-3.7/apex/multi_tensor_apply\n","copying apex/multi_tensor_apply/multi_tensor_apply.py -> build/lib.linux-x86_64-3.7/apex/multi_tensor_apply\n","creating build/lib.linux-x86_64-3.7/apex/parallel\n","copying apex/parallel/__init__.py -> build/lib.linux-x86_64-3.7/apex/parallel\n","copying apex/parallel/LARC.py -> build/lib.linux-x86_64-3.7/apex/parallel\n","copying apex/parallel/distributed.py -> build/lib.linux-x86_64-3.7/apex/parallel\n","copying apex/parallel/sync_batchnorm_kernel.py -> build/lib.linux-x86_64-3.7/apex/parallel\n","copying apex/parallel/optimized_sync_batchnorm_kernel.py -> build/lib.linux-x86_64-3.7/apex/parallel\n","copying apex/parallel/sync_batchnorm.py -> build/lib.linux-x86_64-3.7/apex/parallel\n","copying apex/parallel/multiproc.py -> build/lib.linux-x86_64-3.7/apex/parallel\n","copying apex/parallel/optimized_sync_batchnorm.py -> build/lib.linux-x86_64-3.7/apex/parallel\n","creating build/lib.linux-x86_64-3.7/apex/RNN\n","copying apex/RNN/__init__.py -> build/lib.linux-x86_64-3.7/apex/RNN\n","copying apex/RNN/cells.py -> build/lib.linux-x86_64-3.7/apex/RNN\n","copying apex/RNN/RNNBackend.py -> build/lib.linux-x86_64-3.7/apex/RNN\n","copying apex/RNN/models.py -> build/lib.linux-x86_64-3.7/apex/RNN\n","creating build/lib.linux-x86_64-3.7/apex/fused_dense\n","copying apex/fused_dense/__init__.py -> build/lib.linux-x86_64-3.7/apex/fused_dense\n","copying apex/fused_dense/fused_dense.py -> build/lib.linux-x86_64-3.7/apex/fused_dense\n","creating build/lib.linux-x86_64-3.7/apex/optimizers\n","copying apex/optimizers/__init__.py -> build/lib.linux-x86_64-3.7/apex/optimizers\n","copying apex/optimizers/fused_adam.py -> build/lib.linux-x86_64-3.7/apex/optimizers\n","copying apex/optimizers/fused_novograd.py -> build/lib.linux-x86_64-3.7/apex/optimizers\n","copying apex/optimizers/fused_adagrad.py -> build/lib.linux-x86_64-3.7/apex/optimizers\n","copying apex/optimizers/fused_lamb.py -> build/lib.linux-x86_64-3.7/apex/optimizers\n","copying apex/optimizers/fused_sgd.py -> build/lib.linux-x86_64-3.7/apex/optimizers\n","creating build/lib.linux-x86_64-3.7/apex/reparameterization\n","copying apex/reparameterization/__init__.py -> build/lib.linux-x86_64-3.7/apex/reparameterization\n","copying apex/reparameterization/reparameterization.py -> build/lib.linux-x86_64-3.7/apex/reparameterization\n","copying apex/reparameterization/weight_norm.py -> build/lib.linux-x86_64-3.7/apex/reparameterization\n","creating build/lib.linux-x86_64-3.7/apex/fp16_utils\n","copying apex/fp16_utils/fp16_optimizer.py -> build/lib.linux-x86_64-3.7/apex/fp16_utils\n","copying apex/fp16_utils/__init__.py -> build/lib.linux-x86_64-3.7/apex/fp16_utils\n","copying apex/fp16_utils/fp16util.py -> build/lib.linux-x86_64-3.7/apex/fp16_utils\n","copying apex/fp16_utils/loss_scaler.py -> build/lib.linux-x86_64-3.7/apex/fp16_utils\n","creating build/lib.linux-x86_64-3.7/apex/pyprof/nvtx\n","copying apex/pyprof/nvtx/__init__.py -> build/lib.linux-x86_64-3.7/apex/pyprof/nvtx\n","copying apex/pyprof/nvtx/nvmarker.py -> build/lib.linux-x86_64-3.7/apex/pyprof/nvtx\n","creating build/lib.linux-x86_64-3.7/apex/pyprof/parse\n","copying apex/pyprof/parse/__init__.py -> build/lib.linux-x86_64-3.7/apex/pyprof/parse\n","copying apex/pyprof/parse/__main__.py -> build/lib.linux-x86_64-3.7/apex/pyprof/parse\n","copying apex/pyprof/parse/kernel.py -> build/lib.linux-x86_64-3.7/apex/pyprof/parse\n","copying apex/pyprof/parse/nvvp.py -> build/lib.linux-x86_64-3.7/apex/pyprof/parse\n","copying apex/pyprof/parse/db.py -> build/lib.linux-x86_64-3.7/apex/pyprof/parse\n","copying apex/pyprof/parse/parse.py -> build/lib.linux-x86_64-3.7/apex/pyprof/parse\n","creating build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/linear.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/normalization.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/__init__.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/base.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/loss.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/index_slice_join_mutate.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/__main__.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/dropout.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/optim.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/usage.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/activation.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/softmax.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/data.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/randomSample.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/utility.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/misc.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/embedding.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/convert.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/pooling.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/conv.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/recurrentCell.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/blas.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/output.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/pointwise.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/reduction.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","copying apex/pyprof/prof/prof.py -> build/lib.linux-x86_64-3.7/apex/pyprof/prof\n","creating build/lib.linux-x86_64-3.7/apex/contrib/layer_norm\n","copying apex/contrib/layer_norm/__init__.py -> build/lib.linux-x86_64-3.7/apex/contrib/layer_norm\n","copying apex/contrib/layer_norm/layer_norm.py -> build/lib.linux-x86_64-3.7/apex/contrib/layer_norm\n","creating build/lib.linux-x86_64-3.7/apex/contrib/groupbn\n","copying apex/contrib/groupbn/__init__.py -> build/lib.linux-x86_64-3.7/apex/contrib/groupbn\n","copying apex/contrib/groupbn/batch_norm.py -> build/lib.linux-x86_64-3.7/apex/contrib/groupbn\n","creating build/lib.linux-x86_64-3.7/apex/contrib/fmha\n","copying apex/contrib/fmha/__init__.py -> build/lib.linux-x86_64-3.7/apex/contrib/fmha\n","copying apex/contrib/fmha/fmha.py -> build/lib.linux-x86_64-3.7/apex/contrib/fmha\n","creating build/lib.linux-x86_64-3.7/apex/contrib/sparsity\n","copying apex/contrib/sparsity/sparse_masklib.py -> build/lib.linux-x86_64-3.7/apex/contrib/sparsity\n","copying apex/contrib/sparsity/__init__.py -> build/lib.linux-x86_64-3.7/apex/contrib/sparsity\n","copying apex/contrib/sparsity/asp.py -> build/lib.linux-x86_64-3.7/apex/contrib/sparsity\n","creating build/lib.linux-x86_64-3.7/apex/contrib/xentropy\n","copying apex/contrib/xentropy/__init__.py -> build/lib.linux-x86_64-3.7/apex/contrib/xentropy\n","copying apex/contrib/xentropy/softmax_xentropy.py -> build/lib.linux-x86_64-3.7/apex/contrib/xentropy\n","creating build/lib.linux-x86_64-3.7/apex/contrib/optimizers\n","copying apex/contrib/optimizers/fp16_optimizer.py -> build/lib.linux-x86_64-3.7/apex/contrib/optimizers\n","copying apex/contrib/optimizers/__init__.py -> build/lib.linux-x86_64-3.7/apex/contrib/optimizers\n","copying apex/contrib/optimizers/fused_adam.py -> build/lib.linux-x86_64-3.7/apex/contrib/optimizers\n","copying apex/contrib/optimizers/distributed_fused_lamb.py -> build/lib.linux-x86_64-3.7/apex/contrib/optimizers\n","copying apex/contrib/optimizers/distributed_fused_adam_v3.py -> build/lib.linux-x86_64-3.7/apex/contrib/optimizers\n","copying apex/contrib/optimizers/distributed_fused_adam.py -> build/lib.linux-x86_64-3.7/apex/contrib/optimizers\n","copying apex/contrib/optimizers/distributed_fused_adam_v2.py -> build/lib.linux-x86_64-3.7/apex/contrib/optimizers\n","copying apex/contrib/optimizers/fused_lamb.py -> build/lib.linux-x86_64-3.7/apex/contrib/optimizers\n","copying apex/contrib/optimizers/fused_sgd.py -> build/lib.linux-x86_64-3.7/apex/contrib/optimizers\n","creating build/lib.linux-x86_64-3.7/apex/contrib/bottleneck\n","copying apex/contrib/bottleneck/bottleneck_module_test.py -> build/lib.linux-x86_64-3.7/apex/contrib/bottleneck\n","copying apex/contrib/bottleneck/__init__.py -> build/lib.linux-x86_64-3.7/apex/contrib/bottleneck\n","copying apex/contrib/bottleneck/test.py -> build/lib.linux-x86_64-3.7/apex/contrib/bottleneck\n","copying apex/contrib/bottleneck/bottleneck.py -> build/lib.linux-x86_64-3.7/apex/contrib/bottleneck\n","creating build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn\n","copying apex/contrib/multihead_attn/fast_self_multihead_attn_norm_add_func.py -> build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn\n","copying apex/contrib/multihead_attn/self_multihead_attn.py -> build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn\n","copying apex/contrib/multihead_attn/__init__.py -> build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn\n","copying apex/contrib/multihead_attn/encdec_multihead_attn_func.py -> build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn\n","copying apex/contrib/multihead_attn/self_multihead_attn_func.py -> build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn\n","copying apex/contrib/multihead_attn/fast_encdec_multihead_attn_norm_add_func.py -> build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn\n","copying apex/contrib/multihead_attn/mask_softmax_dropout_func.py -> build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn\n","copying apex/contrib/multihead_attn/fast_encdec_multihead_attn_func.py -> build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn\n","copying apex/contrib/multihead_attn/fast_self_multihead_attn_func.py -> build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn\n","copying apex/contrib/multihead_attn/encdec_multihead_attn.py -> build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn\n","creating build/lib.linux-x86_64-3.7/apex/contrib/transducer\n","copying apex/contrib/transducer/__init__.py -> build/lib.linux-x86_64-3.7/apex/contrib/transducer\n","copying apex/contrib/transducer/transducer.py -> build/lib.linux-x86_64-3.7/apex/contrib/transducer\n","creating build/lib.linux-x86_64-3.7/apex/transformer/functional\n","copying apex/transformer/functional/__init__.py -> build/lib.linux-x86_64-3.7/apex/transformer/functional\n","copying apex/transformer/functional/fused_softmax.py -> build/lib.linux-x86_64-3.7/apex/transformer/functional\n","creating build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel\n","copying apex/transformer/tensor_parallel/__init__.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel\n","copying apex/transformer/tensor_parallel/memory.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel\n","copying apex/transformer/tensor_parallel/random.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel\n","copying apex/transformer/tensor_parallel/layers.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel\n","copying apex/transformer/tensor_parallel/data.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel\n","copying apex/transformer/tensor_parallel/mappings.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel\n","copying apex/transformer/tensor_parallel/microbatches.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel\n","copying apex/transformer/tensor_parallel/utils.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel\n","copying apex/transformer/tensor_parallel/cross_entropy.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel\n","creating build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/tests\n","copying apex/transformer/tensor_parallel/tests/__init__.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/tests\n","copying apex/transformer/tensor_parallel/tests/global_vars.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/tests\n","copying apex/transformer/tensor_parallel/tests/commons.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/tests\n","copying apex/transformer/tensor_parallel/tests/arguments.py -> build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/tests\n","creating build/lib.linux-x86_64-3.7/apex/amp/lists\n","copying apex/amp/lists/__init__.py -> build/lib.linux-x86_64-3.7/apex/amp/lists\n","copying apex/amp/lists/functional_overrides.py -> build/lib.linux-x86_64-3.7/apex/amp/lists\n","copying apex/amp/lists/torch_overrides.py -> build/lib.linux-x86_64-3.7/apex/amp/lists\n","copying apex/amp/lists/tensor_overrides.py -> build/lib.linux-x86_64-3.7/apex/amp/lists\n","running build_ext\n","building 'apex_C' extension\n","creating build/temp.linux-x86_64-3.7\n","creating build/temp.linux-x86_64-3.7/csrc\n","x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/include/python3.7m -c csrc/flatten_unflatten.cpp -o build/temp.linux-x86_64-3.7/csrc/flatten_unflatten.o -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=apex_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Parallel.h:140:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/utils.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:13\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/flatten_unflatten.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ParallelOpenMP.h:87:0:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kignoring #pragma omp parallel [\u001b[01;35m\u001b[K-Wunknown-pragmas\u001b[m\u001b[K]\n"," #pragma omp parallel for if ((end - begin) >= grain_size)\n"," \n","x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -Wl,-Bsymbolic-functions -Wl,-z,relro -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.7/csrc/flatten_unflatten.o -L/usr/local/lib/python3.7/dist-packages/torch/lib -lc10 -ltorch -ltorch_cpu -ltorch_python -o build/lib.linux-x86_64-3.7/apex_C.cpython-37m-x86_64-linux-gnu.so\n","building 'amp_C' extension\n","x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/amp_C_frontend.cpp -o build/temp.linux-x86_64-3.7/csrc/amp_C_frontend.o -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Parallel.h:140:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/utils.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:13\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/amp_C_frontend.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ParallelOpenMP.h:87:0:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kignoring #pragma omp parallel [\u001b[01;35m\u001b[K-Wunknown-pragmas\u001b[m\u001b[K]\n"," #pragma omp parallel for if ((end - begin) >= grain_size)\n"," \n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/multi_tensor_sgd_kernel.cu -o build/temp.linux-x86_64-3.7/csrc/multi_tensor_sgd_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -lineinfo -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/multi_tensor_scale_kernel.cu -o build/temp.linux-x86_64-3.7/csrc/multi_tensor_scale_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -lineinfo -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/multi_tensor_axpby_kernel.cu -o build/temp.linux-x86_64-3.7/csrc/multi_tensor_axpby_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -lineinfo -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/multi_tensor_l2norm_kernel.cu -o build/temp.linux-x86_64-3.7/csrc/multi_tensor_l2norm_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -lineinfo -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/multi_tensor_l2norm_scale_kernel.cu -o build/temp.linux-x86_64-3.7/csrc/multi_tensor_l2norm_scale_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -lineinfo -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/multi_tensor_lamb_stage_1.cu -o build/temp.linux-x86_64-3.7/csrc/multi_tensor_lamb_stage_1.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -lineinfo -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/multi_tensor_lamb_stage_2.cu -o build/temp.linux-x86_64-3.7/csrc/multi_tensor_lamb_stage_2.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -lineinfo -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/multi_tensor_adam.cu -o build/temp.linux-x86_64-3.7/csrc/multi_tensor_adam.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -lineinfo -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/multi_tensor_adagrad.cu -o build/temp.linux-x86_64-3.7/csrc/multi_tensor_adagrad.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -lineinfo -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/multi_tensor_novograd.cu -o build/temp.linux-x86_64-3.7/csrc/multi_tensor_novograd.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -lineinfo -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/multi_tensor_lamb.cu -o build/temp.linux-x86_64-3.7/csrc/multi_tensor_lamb.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -lineinfo -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=amp_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -Wl,-Bsymbolic-functions -Wl,-z,relro -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.7/csrc/amp_C_frontend.o build/temp.linux-x86_64-3.7/csrc/multi_tensor_sgd_kernel.o build/temp.linux-x86_64-3.7/csrc/multi_tensor_scale_kernel.o build/temp.linux-x86_64-3.7/csrc/multi_tensor_axpby_kernel.o build/temp.linux-x86_64-3.7/csrc/multi_tensor_l2norm_kernel.o build/temp.linux-x86_64-3.7/csrc/multi_tensor_l2norm_scale_kernel.o build/temp.linux-x86_64-3.7/csrc/multi_tensor_lamb_stage_1.o build/temp.linux-x86_64-3.7/csrc/multi_tensor_lamb_stage_2.o build/temp.linux-x86_64-3.7/csrc/multi_tensor_adam.o build/temp.linux-x86_64-3.7/csrc/multi_tensor_adagrad.o build/temp.linux-x86_64-3.7/csrc/multi_tensor_novograd.o build/temp.linux-x86_64-3.7/csrc/multi_tensor_lamb.o -L/usr/local/lib/python3.7/dist-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda_cu -ltorch_cuda_cpp -o build/lib.linux-x86_64-3.7/amp_C.cpython-37m-x86_64-linux-gnu.so\n","building 'syncbn' extension\n","x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/syncbn.cpp -o build/temp.linux-x86_64-3.7/csrc/syncbn.o -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=syncbn -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Parallel.h:140:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/utils.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:13\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/syncbn.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ParallelOpenMP.h:87:0:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kignoring #pragma omp parallel [\u001b[01;35m\u001b[K-Wunknown-pragmas\u001b[m\u001b[K]\n"," #pragma omp parallel for if ((end - begin) >= grain_size)\n"," \n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/welford.cu -o build/temp.linux-x86_64-3.7/csrc/welford.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=syncbn -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -Wl,-Bsymbolic-functions -Wl,-z,relro -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.7/csrc/syncbn.o build/temp.linux-x86_64-3.7/csrc/welford.o -L/usr/local/lib/python3.7/dist-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda_cu -ltorch_cuda_cpp -o build/lib.linux-x86_64-3.7/syncbn.cpython-37m-x86_64-linux-gnu.so\n","building 'fused_layer_norm_cuda' extension\n","x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/layer_norm_cuda.cpp -o build/temp.linux-x86_64-3.7/csrc/layer_norm_cuda.o -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=fused_layer_norm_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Parallel.h:140:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/utils.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:13\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ParallelOpenMP.h:87:0:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kignoring #pragma omp parallel [\u001b[01;35m\u001b[K-Wunknown-pragmas\u001b[m\u001b[K]\n"," #pragma omp parallel for if ((end - begin) >= grain_size)\n"," \n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kstd::vector<at::Tensor> layer_norm(at::Tensor, c10::IntArrayRef, double)\u001b[m\u001b[K’:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:129:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(input);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kstd::vector<at::Tensor> layer_norm_affine(at::Tensor, c10::IntArrayRef, at::Tensor, at::Tensor, double)\u001b[m\u001b[K’:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:150:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(input);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:151:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(gamma);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:152:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(beta);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kstd::vector<at::Tensor> layer_norm_affine_mixed_dtypes(at::Tensor, c10::IntArrayRef, at::Tensor, at::Tensor, double)\u001b[m\u001b[K’:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:174:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(input);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kat::Tensor layer_norm_gradient(at::Tensor, at::Tensor, at::Tensor, at::Tensor, c10::IntArrayRef, double)\u001b[m\u001b[K’:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:216:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(dout);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:217:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(mean);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:218:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(invvar);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:219:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(input);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kstd::vector<at::Tensor> layer_norm_gradient_affine(at::Tensor, at::Tensor, at::Tensor, at::Tensor, c10::IntArrayRef, at::Tensor, at::Tensor, double)\u001b[m\u001b[K’:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:242:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(dout);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:243:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(mean);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:244:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(invvar);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:245:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(input);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:246:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(gamma);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/DeviceType.h:8:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Device.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/core/Allocator.h:6\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:7\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:42:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," #define CHECK_CUDA(x) TORCH_CHECK(x.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K.is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/macros/Macros.h:195:64:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KC10_UNLIKELY\u001b[m\u001b[K’\n"," #define C10_UNLIKELY(expr) (__builtin_expect(static_cast<bool>(\u001b[01;36m\u001b[Kexpr\u001b[m\u001b[K), 0))\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/c10/util/Exception.h:430:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K’\n"," if (\u001b[01;36m\u001b[KC10_UNLIKELY_OR_CONST\u001b[m\u001b[K(!(cond))) { \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:117:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KTORCH_CHECK\u001b[m\u001b[K’\n"," #define CHECK_CUDA(x) \u001b[01;36m\u001b[KTORCH_CHECK\u001b[m\u001b[K(x.type().is_cuda(), #x \" must be a CUDA tensor\")\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:119:24:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_CUDA\u001b[m\u001b[K’\n"," #define CHECK_INPUT(x) \u001b[01;36m\u001b[KCHECK_CUDA\u001b[m\u001b[K(x); CHECK_CONTIGUOUS(x)\n"," \u001b[01;36m\u001b[K^~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:247:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KCHECK_INPUT\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KC\u001b[m\u001b[KHECK_INPUT(beta);\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/layer_norm_cuda.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/layer_norm_cuda_kernel.cu -o build/temp.linux-x86_64-3.7/csrc/layer_norm_cuda_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -maxrregcount=50 -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=fused_layer_norm_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -Wl,-Bsymbolic-functions -Wl,-z,relro -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.7/csrc/layer_norm_cuda.o build/temp.linux-x86_64-3.7/csrc/layer_norm_cuda_kernel.o -L/usr/local/lib/python3.7/dist-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda_cu -ltorch_cuda_cpp -o build/lib.linux-x86_64-3.7/fused_layer_norm_cuda.cpython-37m-x86_64-linux-gnu.so\n","building 'mlp_cuda' extension\n","x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/mlp.cpp -o build/temp.linux-x86_64-3.7/csrc/mlp.o -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=mlp_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Parallel.h:140:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/utils.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:13\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ParallelOpenMP.h:87:0:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kignoring #pragma omp parallel [\u001b[01;35m\u001b[K-Wunknown-pragmas\u001b[m\u001b[K]\n"," #pragma omp parallel for if ((end - begin) >= grain_size)\n"," \n","\u001b[01m\u001b[Kcsrc/mlp.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kstd::vector<at::Tensor> mlp_forward(int, int, std::vector<at::Tensor>)\u001b[m\u001b[K’:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:57:21:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < num_layers\u001b[m\u001b[K; i++) {\n"," \u001b[01;35m\u001b[K~~^~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:64:77:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto out = at::empty({batch_size, output_features.back()}, inputs[0].type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:65:67:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto reserved_space = at::empty({reserved_size}, inputs[0].type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:65:68:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Knarrowing conversion of ‘\u001b[01m\u001b[Kreserved_size\u001b[m\u001b[K’ from ‘\u001b[01m\u001b[Klong unsigned int\u001b[m\u001b[K’ to ‘\u001b[01m\u001b[Klong int\u001b[m\u001b[K’ inside { } [\u001b[01;35m\u001b[K-Wnarrowing\u001b[m\u001b[K]\n"," auto reserved_space = at::empty({reserved_size}, inputs[0].type()\u001b[01;35m\u001b[K)\u001b[m\u001b[K;\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:65:68:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Knarrowing conversion of ‘\u001b[01m\u001b[Kreserved_size\u001b[m\u001b[K’ from ‘\u001b[01m\u001b[Klong unsigned int\u001b[m\u001b[K’ to ‘\u001b[01m\u001b[Klong int\u001b[m\u001b[K’ inside { } [\u001b[01;35m\u001b[K-Wnarrowing\u001b[m\u001b[K]\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:67:59:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto lt_workspace = at::empty({1 << 22}, inputs[0].type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:69:54:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," AT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K, \"mlp_forward\", [&] {\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:221:28:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," const auto& the_type = \u001b[01;36m\u001b[KTYPE\u001b[m\u001b[K; \\\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:223:56:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," at::ScalarType _st = ::detail::scalar_type(the_type\u001b[01;35m\u001b[K)\u001b[m\u001b[K; \\\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:69:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:121:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," inline at::ScalarType \u001b[01;36m\u001b[Kscalar_type\u001b[m\u001b[K(const at::DeprecatedTypeProperties& t) {\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:72:23:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < n\u001b[m\u001b[Kum_layers; i++) {\n"," \u001b[01;35m\u001b[K~~^~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:69:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:78:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = mlp_fp<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:69:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:72:23:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < n\u001b[m\u001b[Kum_layers; i++) {\n"," \u001b[01;35m\u001b[K~~^~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:69:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:78:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = mlp_fp<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:69:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:72:23:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < n\u001b[m\u001b[Kum_layers; i++) {\n"," \u001b[01;35m\u001b[K~~^~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:69:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:78:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = mlp_fp<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:69:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kstd::vector<at::Tensor> mlp_backward(int, int, at::Tensor, std::vector<at::Tensor>, std::vector<at::Tensor>)\u001b[m\u001b[K’:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:115:21:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < num_layers\u001b[m\u001b[K; i++) {\n"," \u001b[01;35m\u001b[K~~^~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:120:21:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < inputs.size()\u001b[m\u001b[K; i++) {\n"," \u001b[01;35m\u001b[K~~^~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:121:67:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," outputs.push_back(at::empty(inputs[i].sizes(), inputs[i].type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K)); // clone for testing now\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:54:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," AT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K, \"mlp_backward\", [&] {\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:221:28:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," const auto& the_type = \u001b[01;36m\u001b[KTYPE\u001b[m\u001b[K; \\\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:223:56:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," at::ScalarType _st = ::detail::scalar_type(the_type\u001b[01;35m\u001b[K)\u001b[m\u001b[K; \\\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:121:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," inline at::ScalarType \u001b[01;36m\u001b[Kscalar_type\u001b[m\u001b[K(const at::DeprecatedTypeProperties& t) {\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:126:23:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < n\u001b[m\u001b[Kum_layers; i++) {\n"," \u001b[01;35m\u001b[K~~^~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:130:23:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < inputs.size()\u001b[m\u001b[K; i++) {\n"," \u001b[01;35m\u001b[K~~^~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:138:80:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto work_space = at::empty({work_size / sizeof(scalar_t)}, inputs[0].type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:138:44:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Knarrowing conversion of ‘\u001b[01m\u001b[K(work_size / sizeof (scalar_t))\u001b[m\u001b[K’ from ‘\u001b[01m\u001b[Klong unsigned int\u001b[m\u001b[K’ to ‘\u001b[01m\u001b[Klong int\u001b[m\u001b[K’ inside { } [\u001b[01;35m\u001b[K-Wnarrowing\u001b[m\u001b[K]\n"," auto work_space = at::empty({\u001b[01;35m\u001b[Kwork_size / sizeof(\u001b[m\u001b[Kscalar_t)}, inputs[0].type());\n"," \u001b[01;35m\u001b[K~~~~~~~~~~^~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:138:44:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Knarrowing conversion of ‘\u001b[01m\u001b[K(work_size / sizeof (scalar_t))\u001b[m\u001b[K’ from ‘\u001b[01m\u001b[Klong unsigned int\u001b[m\u001b[K’ to ‘\u001b[01m\u001b[Klong int\u001b[m\u001b[K’ inside { } [\u001b[01;35m\u001b[K-Wnarrowing\u001b[m\u001b[K]\n"," auto work_space = at::empty({\u001b[01;35m\u001b[Kwork_size / sizeof(\u001b[m\u001b[Kscalar_t)}, inputs[0].type());\n"," \u001b[01;35m\u001b[K~~~~~~~~~~^~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:140:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = mlp_bp<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:126:23:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < n\u001b[m\u001b[Kum_layers; i++) {\n"," \u001b[01;35m\u001b[K~~^~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:130:23:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < inputs.size()\u001b[m\u001b[K; i++) {\n"," \u001b[01;35m\u001b[K~~^~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:138:80:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto work_space = at::empty({work_size / sizeof(scalar_t)}, inputs[0].type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:138:44:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Knarrowing conversion of ‘\u001b[01m\u001b[K(work_size / sizeof (scalar_t))\u001b[m\u001b[K’ from ‘\u001b[01m\u001b[Klong unsigned int\u001b[m\u001b[K’ to ‘\u001b[01m\u001b[Klong int\u001b[m\u001b[K’ inside { } [\u001b[01;35m\u001b[K-Wnarrowing\u001b[m\u001b[K]\n"," auto work_space = at::empty({\u001b[01;35m\u001b[Kwork_size / sizeof(\u001b[m\u001b[Kscalar_t)}, inputs[0].type());\n"," \u001b[01;35m\u001b[K~~~~~~~~~~^~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:138:44:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Knarrowing conversion of ‘\u001b[01m\u001b[K(work_size / sizeof (scalar_t))\u001b[m\u001b[K’ from ‘\u001b[01m\u001b[Klong unsigned int\u001b[m\u001b[K’ to ‘\u001b[01m\u001b[Klong int\u001b[m\u001b[K’ inside { } [\u001b[01;35m\u001b[K-Wnarrowing\u001b[m\u001b[K]\n"," auto work_space = at::empty({\u001b[01;35m\u001b[Kwork_size / sizeof(\u001b[m\u001b[Kscalar_t)}, inputs[0].type());\n"," \u001b[01;35m\u001b[K~~~~~~~~~~^~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:140:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = mlp_bp<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:126:23:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < n\u001b[m\u001b[Kum_layers; i++) {\n"," \u001b[01;35m\u001b[K~~^~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:130:23:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kcomparison between signed and unsigned integer expressions [\u001b[01;35m\u001b[K-Wsign-compare\u001b[m\u001b[K]\n"," for (int i = 0; \u001b[01;35m\u001b[Ki < inputs.size()\u001b[m\u001b[K; i++) {\n"," \u001b[01;35m\u001b[K~~^~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:138:80:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto work_space = at::empty({work_size / sizeof(scalar_t)}, inputs[0].type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/mlp.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:138:44:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Knarrowing conversion of ‘\u001b[01m\u001b[K(work_size / sizeof (scalar_t))\u001b[m\u001b[K’ from ‘\u001b[01m\u001b[Klong unsigned int\u001b[m\u001b[K’ to ‘\u001b[01m\u001b[Klong int\u001b[m\u001b[K’ inside { } [\u001b[01;35m\u001b[K-Wnarrowing\u001b[m\u001b[K]\n"," auto work_space = at::empty({\u001b[01;35m\u001b[Kwork_size / sizeof(\u001b[m\u001b[Kscalar_t)}, inputs[0].type());\n"," \u001b[01;35m\u001b[K~~~~~~~~~~^~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:138:44:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Knarrowing conversion of ‘\u001b[01m\u001b[K(work_size / sizeof (scalar_t))\u001b[m\u001b[K’ from ‘\u001b[01m\u001b[Klong unsigned int\u001b[m\u001b[K’ to ‘\u001b[01m\u001b[Klong int\u001b[m\u001b[K’ inside { } [\u001b[01;35m\u001b[K-Wnarrowing\u001b[m\u001b[K]\n"," auto work_space = at::empty({\u001b[01;35m\u001b[Kwork_size / sizeof(\u001b[m\u001b[Kscalar_t)}, inputs[0].type());\n"," \u001b[01;35m\u001b[K~~~~~~~~~~^~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:140:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = mlp_bp<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/mlp.cpp:124:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(inputs[0].type(), \"mlp_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/mlp_cuda.cu -o build/temp.linux-x86_64-3.7/csrc/mlp_cuda.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=mlp_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -Wl,-Bsymbolic-functions -Wl,-z,relro -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.7/csrc/mlp.o build/temp.linux-x86_64-3.7/csrc/mlp_cuda.o -L/usr/local/lib/python3.7/dist-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda_cu -ltorch_cuda_cpp -o build/lib.linux-x86_64-3.7/mlp_cuda.cpython-37m-x86_64-linux-gnu.so\n","building 'fused_dense_cuda' extension\n","x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/fused_dense.cpp -o build/temp.linux-x86_64-3.7/csrc/fused_dense.o -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=fused_dense_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Parallel.h:140:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/utils.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:13\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ParallelOpenMP.h:87:0:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kignoring #pragma omp parallel [\u001b[01;35m\u001b[K-Wunknown-pragmas\u001b[m\u001b[K]\n"," #pragma omp parallel for if ((end - begin) >= grain_size)\n"," \n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kat::Tensor linear_bias_forward(at::Tensor, at::Tensor, at::Tensor)\u001b[m\u001b[K’:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:30:63:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto out = at::empty({batch_size, out_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:33:55:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto lt_workspace = at::empty({1 << 22}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:35:50:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," AT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K, \"linear_bias_forward\", [&] {\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:221:28:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," const auto& the_type = \u001b[01;36m\u001b[KTYPE\u001b[m\u001b[K; \\\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:223:56:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," at::ScalarType _st = ::detail::scalar_type(the_type\u001b[01;35m\u001b[K)\u001b[m\u001b[K; \\\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:35:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:121:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," inline at::ScalarType \u001b[01;36m\u001b[Kscalar_type\u001b[m\u001b[K(const at::DeprecatedTypeProperties& t) {\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:37:15:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kb_ptr\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," scalar_t* \u001b[01;35m\u001b[Kb\u001b[m\u001b[K_ptr = bias.data_ptr<scalar_t>();\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:35:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:38:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_bias_forward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:35:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:37:15:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kb_ptr\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," scalar_t* \u001b[01;35m\u001b[Kb\u001b[m\u001b[K_ptr = bias.data_ptr<scalar_t>();\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:35:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:38:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_bias_forward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:35:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:37:15:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kb_ptr\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," scalar_t* \u001b[01;35m\u001b[Kb\u001b[m\u001b[K_ptr = bias.data_ptr<scalar_t>();\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:35:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:38:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_bias_forward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:35:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kstd::vector<at::Tensor> linear_bias_backward(at::Tensor, at::Tensor, at::Tensor)\u001b[m\u001b[K’:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:64:69:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto d_weight = at::empty({out_features, in_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:68:54:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto d_bias = at::empty({out_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:70:66:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto d_input = at::empty({batch_size, in_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:73:55:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto lt_workspace = at::empty({1 << 22}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:75:50:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," AT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K, \"linear_bias_backward\", [&] {\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:221:28:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," const auto& the_type = \u001b[01;36m\u001b[KTYPE\u001b[m\u001b[K; \\\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:223:56:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," at::ScalarType _st = ::detail::scalar_type(the_type\u001b[01;35m\u001b[K)\u001b[m\u001b[K; \\\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:75:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:121:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," inline at::ScalarType \u001b[01;36m\u001b[Kscalar_type\u001b[m\u001b[K(const at::DeprecatedTypeProperties& t) {\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:77:15:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kd_b_ptr\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," scalar_t* \u001b[01;35m\u001b[Kd\u001b[m\u001b[K_b_ptr = d_bias.data_ptr<scalar_t>();\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:75:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:78:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_bias_backward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:75:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:77:15:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kd_b_ptr\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," scalar_t* \u001b[01;35m\u001b[Kd\u001b[m\u001b[K_b_ptr = d_bias.data_ptr<scalar_t>();\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:75:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:78:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_bias_backward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:75:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:77:15:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kd_b_ptr\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," scalar_t* \u001b[01;35m\u001b[Kd\u001b[m\u001b[K_b_ptr = d_bias.data_ptr<scalar_t>();\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:75:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:78:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_bias_backward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:75:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kstd::vector<at::Tensor> linear_gelu_linear_forward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor)\u001b[m\u001b[K’:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:106:70:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto output1 = at::empty({batch_size, hidden_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:107:70:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto gelu_in = at::empty({batch_size, hidden_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:108:67:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto output2 = at::empty({batch_size, out_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:111:55:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto lt_workspace = at::empty({1 << 22}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:113:50:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," AT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K, \"linear_gelu_linear_forward\", [&] {\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:221:28:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," const auto& the_type = \u001b[01;36m\u001b[KTYPE\u001b[m\u001b[K; \\\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:223:56:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," at::ScalarType _st = ::detail::scalar_type(the_type\u001b[01;35m\u001b[K)\u001b[m\u001b[K; \\\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:113:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_gelu_linear_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:121:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," inline at::ScalarType \u001b[01;36m\u001b[Kscalar_type\u001b[m\u001b[K(const at::DeprecatedTypeProperties& t) {\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:118:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_gelu_linear_forward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:113:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_gelu_linear_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:118:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_gelu_linear_forward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:113:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_gelu_linear_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:118:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_gelu_linear_forward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:113:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_gelu_linear_forward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[Kstd::vector<at::Tensor> linear_gelu_linear_backward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor)\u001b[m\u001b[K’:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:149:73:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto d_weight1 = at::empty({hidden_features, in_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:150:74:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto d_weight2 = at::empty({out_features, hidden_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:151:58:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto d_bias1 = at::empty({hidden_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:152:55:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto d_bias2 = at::empty({out_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:153:66:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto d_input = at::empty({batch_size, in_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:154:72:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto d_output1 = at::empty({batch_size, hidden_features}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:157:55:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," auto lt_workspace = at::empty({1 << 22}, input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K);\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:159:50:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," AT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(\u001b[01;35m\u001b[K)\u001b[m\u001b[K, \"linear_bias_backward\", [&] {\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:221:28:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," const auto& the_type = \u001b[01;36m\u001b[KTYPE\u001b[m\u001b[K; \\\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Tensor.h:3:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Context.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:9\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/core/TensorBody.h:338:30:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," DeprecatedTypeProperties & \u001b[01;36m\u001b[Ktype\u001b[m\u001b[K() const {\n"," \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ATen.h:13:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/types.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/data.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:8\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/fused_dense.cpp:1\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:223:56:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n"," at::ScalarType _st = ::detail::scalar_type(the_type\u001b[01;35m\u001b[K)\u001b[m\u001b[K; \\\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:159:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:121:23:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n"," inline at::ScalarType \u001b[01;36m\u001b[Kscalar_type\u001b[m\u001b[K(const at::DeprecatedTypeProperties& t) {\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:162:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_gelu_linear_backward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:226:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Double, double, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:159:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:162:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_gelu_linear_backward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:227:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Float, float, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:159:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:\u001b[m\u001b[K In lambda function:\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:162:10:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kunused variable ‘\u001b[01m\u001b[Kresult\u001b[m\u001b[K’ [\u001b[01;35m\u001b[K-Wunused-variable\u001b[m\u001b[K]\n"," auto \u001b[01;35m\u001b[Kr\u001b[m\u001b[Kesult = linear_gelu_linear_backward_cuda<scalar_t>(\n"," \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:66:12:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin definition of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE_USING_HINT\u001b[m\u001b[K’\n"," return \u001b[01;36m\u001b[K__VA_ARGS__\u001b[m\u001b[K(); \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Dispatch.h:228:7:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KAT_PRIVATE_CASE_TYPE\u001b[m\u001b[K(NAME, at::ScalarType::Half, at::Half, __VA_ARGS__) \\\n"," \u001b[01;36m\u001b[K^~~~~~~~~~~~~~~~~~~~\u001b[m\u001b[K\n","\u001b[01m\u001b[Kcsrc/fused_dense.cpp:159:3:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kin expansion of macro ‘\u001b[01m\u001b[KAT_DISPATCH_FLOATING_TYPES_AND_HALF\u001b[m\u001b[K’\n"," \u001b[01;36m\u001b[KA\u001b[m\u001b[KT_DISPATCH_FLOATING_TYPES_AND_HALF(input.type(), \"linear_bias_backward\", [&] {\n"," \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n","/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/fused_dense_cuda.cu -o build/temp.linux-x86_64-3.7/csrc/fused_dense_cuda.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=fused_dense_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","csrc/fused_dense_cuda.cu(1148): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1272): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1273): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1274): warning: variable \"status\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1329): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1330): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1148): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1272): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1273): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1274): warning: variable \"status\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1329): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1330): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1148): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1272): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1273): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1274): warning: variable \"status\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1329): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1330): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1148): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1272): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1273): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1274): warning: variable \"status\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1329): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1330): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1148): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1272): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1273): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1274): warning: variable \"status\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1329): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1330): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1148): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1272): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1273): warning: variable \"beta_zero\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1274): warning: variable \"status\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1329): warning: variable \"alpha\" was declared but never referenced\n","\n","csrc/fused_dense_cuda.cu(1330): warning: variable \"beta_zero\" was declared but never referenced\n","\n","x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -Wl,-Bsymbolic-functions -Wl,-z,relro -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.7/csrc/fused_dense.o build/temp.linux-x86_64-3.7/csrc/fused_dense_cuda.o -L/usr/local/lib/python3.7/dist-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda_cu -ltorch_cuda_cpp -o build/lib.linux-x86_64-3.7/fused_dense_cuda.cpython-37m-x86_64-linux-gnu.so\n","building 'scaled_upper_triang_masked_softmax_cuda' extension\n","creating build/temp.linux-x86_64-3.7/csrc/megatron\n","x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/apex/csrc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/megatron/scaled_upper_triang_masked_softmax.cpp -o build/temp.linux-x86_64-3.7/csrc/megatron/scaled_upper_triang_masked_softmax.o -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=scaled_upper_triang_masked_softmax_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Parallel.h:140:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/utils.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:13\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/megatron/scaled_upper_triang_masked_softmax.cpp:18\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ParallelOpenMP.h:87:0:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kignoring #pragma omp parallel [\u001b[01;35m\u001b[K-Wunknown-pragmas\u001b[m\u001b[K]\n"," #pragma omp parallel for if ((end - begin) >= grain_size)\n"," \n","/usr/local/cuda/bin/nvcc -I/apex/csrc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/megatron/scaled_upper_triang_masked_softmax_cuda.cu -o build/temp.linux-x86_64-3.7/csrc/megatron/scaled_upper_triang_masked_softmax_cuda.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -O3 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --expt-relaxed-constexpr --expt-extended-lambda -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=scaled_upper_triang_masked_softmax_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -Wl,-Bsymbolic-functions -Wl,-z,relro -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.7/csrc/megatron/scaled_upper_triang_masked_softmax.o build/temp.linux-x86_64-3.7/csrc/megatron/scaled_upper_triang_masked_softmax_cuda.o -L/usr/local/lib/python3.7/dist-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda_cu -ltorch_cuda_cpp -o build/lib.linux-x86_64-3.7/scaled_upper_triang_masked_softmax_cuda.cpython-37m-x86_64-linux-gnu.so\n","building 'scaled_masked_softmax_cuda' extension\n","x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/apex/csrc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/megatron/scaled_masked_softmax.cpp -o build/temp.linux-x86_64-3.7/csrc/megatron/scaled_masked_softmax.o -O3 -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=scaled_masked_softmax_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14\n","In file included from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/Parallel.h:140:0\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/utils.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/nn.h:3\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include/torch/all.h:13\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/torch/extension.h:4\u001b[m\u001b[K,\n"," from \u001b[01m\u001b[Kcsrc/megatron/scaled_masked_softmax.cpp:18\u001b[m\u001b[K:\n","\u001b[01m\u001b[K/usr/local/lib/python3.7/dist-packages/torch/include/ATen/ParallelOpenMP.h:87:0:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kignoring #pragma omp parallel [\u001b[01;35m\u001b[K-Wunknown-pragmas\u001b[m\u001b[K]\n"," #pragma omp parallel for if ((end - begin) >= grain_size)\n"," \n","/usr/local/cuda/bin/nvcc -I/apex/csrc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c csrc/megatron/scaled_masked_softmax_cuda.cu -o build/temp.linux-x86_64-3.7/csrc/megatron/scaled_masked_softmax_cuda.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -O3 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --expt-relaxed-constexpr --expt-extended-lambda -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=scaled_masked_softmax_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_61,code=sm_61 -gencode=arch=compute_62,code=sm_62 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -std=c++14\n","x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -Wl,-Bsymbolic-functions -Wl,-z,relro -g -fdebug-prefix-map=/build/python3.7-Y7dWVB/python3.7-3.7.12=. -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.7/csrc/megatron/scaled_masked_softmax.o build/temp.linux-x86_64-3.7/csrc/megatron/scaled_masked_softmax_cuda.o -L/usr/local/lib/python3.7/dist-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda_cu -ltorch_cuda_cpp -o build/lib.linux-x86_64-3.7/scaled_masked_softmax_cuda.cpython-37m-x86_64-linux-gnu.so\n","creating build/bdist.linux-x86_64\n","creating build/bdist.linux-x86_64/egg\n","copying build/lib.linux-x86_64-3.7/syncbn.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg\n","copying build/lib.linux-x86_64-3.7/amp_C.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg\n","copying build/lib.linux-x86_64-3.7/fused_layer_norm_cuda.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg\n","copying build/lib.linux-x86_64-3.7/scaled_upper_triang_masked_softmax_cuda.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg\n","copying build/lib.linux-x86_64-3.7/mlp_cuda.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg\n","copying build/lib.linux-x86_64-3.7/apex_C.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg\n","copying build/lib.linux-x86_64-3.7/fused_dense_cuda.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg\n","creating build/bdist.linux-x86_64/egg/apex\n","creating build/bdist.linux-x86_64/egg/apex/pyprof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/__init__.py -> build/bdist.linux-x86_64/egg/apex/pyprof\n","creating build/bdist.linux-x86_64/egg/apex/pyprof/nvtx\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/nvtx/__init__.py -> build/bdist.linux-x86_64/egg/apex/pyprof/nvtx\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/nvtx/nvmarker.py -> build/bdist.linux-x86_64/egg/apex/pyprof/nvtx\n","creating build/bdist.linux-x86_64/egg/apex/pyprof/parse\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/parse/__init__.py -> build/bdist.linux-x86_64/egg/apex/pyprof/parse\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/parse/__main__.py -> build/bdist.linux-x86_64/egg/apex/pyprof/parse\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/parse/kernel.py -> build/bdist.linux-x86_64/egg/apex/pyprof/parse\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/parse/nvvp.py -> build/bdist.linux-x86_64/egg/apex/pyprof/parse\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/parse/db.py -> build/bdist.linux-x86_64/egg/apex/pyprof/parse\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/parse/parse.py -> build/bdist.linux-x86_64/egg/apex/pyprof/parse\n","creating build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/linear.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/normalization.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/__init__.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/base.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/loss.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/index_slice_join_mutate.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/__main__.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/dropout.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/optim.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/usage.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/activation.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/softmax.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/data.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/randomSample.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/utility.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/misc.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/embedding.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/convert.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/pooling.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/conv.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/recurrentCell.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/blas.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/output.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/pointwise.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/reduction.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","copying build/lib.linux-x86_64-3.7/apex/pyprof/prof/prof.py -> build/bdist.linux-x86_64/egg/apex/pyprof/prof\n","creating build/bdist.linux-x86_64/egg/apex/contrib\n","copying build/lib.linux-x86_64-3.7/apex/contrib/__init__.py -> build/bdist.linux-x86_64/egg/apex/contrib\n","creating build/bdist.linux-x86_64/egg/apex/contrib/layer_norm\n","copying build/lib.linux-x86_64-3.7/apex/contrib/layer_norm/__init__.py -> build/bdist.linux-x86_64/egg/apex/contrib/layer_norm\n","copying build/lib.linux-x86_64-3.7/apex/contrib/layer_norm/layer_norm.py -> build/bdist.linux-x86_64/egg/apex/contrib/layer_norm\n","creating build/bdist.linux-x86_64/egg/apex/contrib/groupbn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/groupbn/__init__.py -> build/bdist.linux-x86_64/egg/apex/contrib/groupbn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/groupbn/batch_norm.py -> build/bdist.linux-x86_64/egg/apex/contrib/groupbn\n","creating build/bdist.linux-x86_64/egg/apex/contrib/fmha\n","copying build/lib.linux-x86_64-3.7/apex/contrib/fmha/__init__.py -> build/bdist.linux-x86_64/egg/apex/contrib/fmha\n","copying build/lib.linux-x86_64-3.7/apex/contrib/fmha/fmha.py -> build/bdist.linux-x86_64/egg/apex/contrib/fmha\n","creating build/bdist.linux-x86_64/egg/apex/contrib/sparsity\n","copying build/lib.linux-x86_64-3.7/apex/contrib/sparsity/sparse_masklib.py -> build/bdist.linux-x86_64/egg/apex/contrib/sparsity\n","copying build/lib.linux-x86_64-3.7/apex/contrib/sparsity/__init__.py -> build/bdist.linux-x86_64/egg/apex/contrib/sparsity\n","copying build/lib.linux-x86_64-3.7/apex/contrib/sparsity/asp.py -> build/bdist.linux-x86_64/egg/apex/contrib/sparsity\n","creating build/bdist.linux-x86_64/egg/apex/contrib/xentropy\n","copying build/lib.linux-x86_64-3.7/apex/contrib/xentropy/__init__.py -> build/bdist.linux-x86_64/egg/apex/contrib/xentropy\n","copying build/lib.linux-x86_64-3.7/apex/contrib/xentropy/softmax_xentropy.py -> build/bdist.linux-x86_64/egg/apex/contrib/xentropy\n","creating build/bdist.linux-x86_64/egg/apex/contrib/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/contrib/optimizers/fp16_optimizer.py -> build/bdist.linux-x86_64/egg/apex/contrib/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/contrib/optimizers/__init__.py -> build/bdist.linux-x86_64/egg/apex/contrib/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/contrib/optimizers/fused_adam.py -> build/bdist.linux-x86_64/egg/apex/contrib/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/contrib/optimizers/distributed_fused_lamb.py -> build/bdist.linux-x86_64/egg/apex/contrib/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/contrib/optimizers/distributed_fused_adam_v3.py -> build/bdist.linux-x86_64/egg/apex/contrib/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/contrib/optimizers/distributed_fused_adam.py -> build/bdist.linux-x86_64/egg/apex/contrib/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/contrib/optimizers/distributed_fused_adam_v2.py -> build/bdist.linux-x86_64/egg/apex/contrib/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/contrib/optimizers/fused_lamb.py -> build/bdist.linux-x86_64/egg/apex/contrib/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/contrib/optimizers/fused_sgd.py -> build/bdist.linux-x86_64/egg/apex/contrib/optimizers\n","creating build/bdist.linux-x86_64/egg/apex/contrib/bottleneck\n","copying build/lib.linux-x86_64-3.7/apex/contrib/bottleneck/bottleneck_module_test.py -> build/bdist.linux-x86_64/egg/apex/contrib/bottleneck\n","copying build/lib.linux-x86_64-3.7/apex/contrib/bottleneck/__init__.py -> build/bdist.linux-x86_64/egg/apex/contrib/bottleneck\n","copying build/lib.linux-x86_64-3.7/apex/contrib/bottleneck/test.py -> build/bdist.linux-x86_64/egg/apex/contrib/bottleneck\n","copying build/lib.linux-x86_64-3.7/apex/contrib/bottleneck/bottleneck.py -> build/bdist.linux-x86_64/egg/apex/contrib/bottleneck\n","creating build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn/fast_self_multihead_attn_norm_add_func.py -> build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn/self_multihead_attn.py -> build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn/__init__.py -> build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn/encdec_multihead_attn_func.py -> build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn/self_multihead_attn_func.py -> build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn/fast_encdec_multihead_attn_norm_add_func.py -> build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn/mask_softmax_dropout_func.py -> build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn/fast_encdec_multihead_attn_func.py -> build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn/fast_self_multihead_attn_func.py -> build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn\n","copying build/lib.linux-x86_64-3.7/apex/contrib/multihead_attn/encdec_multihead_attn.py -> build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn\n","creating build/bdist.linux-x86_64/egg/apex/contrib/transducer\n","copying build/lib.linux-x86_64-3.7/apex/contrib/transducer/__init__.py -> build/bdist.linux-x86_64/egg/apex/contrib/transducer\n","copying build/lib.linux-x86_64-3.7/apex/contrib/transducer/transducer.py -> build/bdist.linux-x86_64/egg/apex/contrib/transducer\n","copying build/lib.linux-x86_64-3.7/apex/__init__.py -> build/bdist.linux-x86_64/egg/apex\n","creating build/bdist.linux-x86_64/egg/apex/transformer\n","creating build/bdist.linux-x86_64/egg/apex/transformer/functional\n","copying build/lib.linux-x86_64-3.7/apex/transformer/functional/__init__.py -> build/bdist.linux-x86_64/egg/apex/transformer/functional\n","copying build/lib.linux-x86_64-3.7/apex/transformer/functional/fused_softmax.py -> build/bdist.linux-x86_64/egg/apex/transformer/functional\n","copying build/lib.linux-x86_64-3.7/apex/transformer/__init__.py -> build/bdist.linux-x86_64/egg/apex/transformer\n","copying build/lib.linux-x86_64-3.7/apex/transformer/parallel_state.py -> build/bdist.linux-x86_64/egg/apex/transformer\n","creating build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/__init__.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/memory.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/random.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/layers.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel\n","creating build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/tests\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/tests/__init__.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/tests\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/tests/global_vars.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/tests\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/tests/commons.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/tests\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/tests/arguments.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/tests\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/data.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/mappings.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/microbatches.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/utils.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel\n","copying build/lib.linux-x86_64-3.7/apex/transformer/tensor_parallel/cross_entropy.py -> build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel\n","copying build/lib.linux-x86_64-3.7/apex/transformer/enums.py -> build/bdist.linux-x86_64/egg/apex/transformer\n","creating build/bdist.linux-x86_64/egg/apex/mlp\n","copying build/lib.linux-x86_64-3.7/apex/mlp/__init__.py -> build/bdist.linux-x86_64/egg/apex/mlp\n","copying build/lib.linux-x86_64-3.7/apex/mlp/mlp.py -> build/bdist.linux-x86_64/egg/apex/mlp\n","creating build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/__version__.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/rnn_compat.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/__init__.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/wrap.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/_initialize.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/frontend.py -> build/bdist.linux-x86_64/egg/apex/amp\n","creating build/bdist.linux-x86_64/egg/apex/amp/lists\n","copying build/lib.linux-x86_64-3.7/apex/amp/lists/__init__.py -> build/bdist.linux-x86_64/egg/apex/amp/lists\n","copying build/lib.linux-x86_64-3.7/apex/amp/lists/functional_overrides.py -> build/bdist.linux-x86_64/egg/apex/amp/lists\n","copying build/lib.linux-x86_64-3.7/apex/amp/lists/torch_overrides.py -> build/bdist.linux-x86_64/egg/apex/amp/lists\n","copying build/lib.linux-x86_64-3.7/apex/amp/lists/tensor_overrides.py -> build/bdist.linux-x86_64/egg/apex/amp/lists\n","copying build/lib.linux-x86_64-3.7/apex/amp/_amp_state.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/handle.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/opt.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/amp.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/compat.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/utils.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/_process_optimizer.py -> build/bdist.linux-x86_64/egg/apex/amp\n","copying build/lib.linux-x86_64-3.7/apex/amp/scaler.py -> build/bdist.linux-x86_64/egg/apex/amp\n","creating build/bdist.linux-x86_64/egg/apex/normalization\n","copying build/lib.linux-x86_64-3.7/apex/normalization/__init__.py -> build/bdist.linux-x86_64/egg/apex/normalization\n","copying build/lib.linux-x86_64-3.7/apex/normalization/fused_layer_norm.py -> build/bdist.linux-x86_64/egg/apex/normalization\n","creating build/bdist.linux-x86_64/egg/apex/multi_tensor_apply\n","copying build/lib.linux-x86_64-3.7/apex/multi_tensor_apply/__init__.py -> build/bdist.linux-x86_64/egg/apex/multi_tensor_apply\n","copying build/lib.linux-x86_64-3.7/apex/multi_tensor_apply/multi_tensor_apply.py -> build/bdist.linux-x86_64/egg/apex/multi_tensor_apply\n","creating build/bdist.linux-x86_64/egg/apex/parallel\n","copying build/lib.linux-x86_64-3.7/apex/parallel/__init__.py -> build/bdist.linux-x86_64/egg/apex/parallel\n","copying build/lib.linux-x86_64-3.7/apex/parallel/LARC.py -> build/bdist.linux-x86_64/egg/apex/parallel\n","copying build/lib.linux-x86_64-3.7/apex/parallel/distributed.py -> build/bdist.linux-x86_64/egg/apex/parallel\n","copying build/lib.linux-x86_64-3.7/apex/parallel/sync_batchnorm_kernel.py -> build/bdist.linux-x86_64/egg/apex/parallel\n","copying build/lib.linux-x86_64-3.7/apex/parallel/optimized_sync_batchnorm_kernel.py -> build/bdist.linux-x86_64/egg/apex/parallel\n","copying build/lib.linux-x86_64-3.7/apex/parallel/sync_batchnorm.py -> build/bdist.linux-x86_64/egg/apex/parallel\n","copying build/lib.linux-x86_64-3.7/apex/parallel/multiproc.py -> build/bdist.linux-x86_64/egg/apex/parallel\n","copying build/lib.linux-x86_64-3.7/apex/parallel/optimized_sync_batchnorm.py -> build/bdist.linux-x86_64/egg/apex/parallel\n","creating build/bdist.linux-x86_64/egg/apex/RNN\n","copying build/lib.linux-x86_64-3.7/apex/RNN/__init__.py -> build/bdist.linux-x86_64/egg/apex/RNN\n","copying build/lib.linux-x86_64-3.7/apex/RNN/cells.py -> build/bdist.linux-x86_64/egg/apex/RNN\n","copying build/lib.linux-x86_64-3.7/apex/RNN/RNNBackend.py -> build/bdist.linux-x86_64/egg/apex/RNN\n","copying build/lib.linux-x86_64-3.7/apex/RNN/models.py -> build/bdist.linux-x86_64/egg/apex/RNN\n","creating build/bdist.linux-x86_64/egg/apex/fused_dense\n","copying build/lib.linux-x86_64-3.7/apex/fused_dense/__init__.py -> build/bdist.linux-x86_64/egg/apex/fused_dense\n","copying build/lib.linux-x86_64-3.7/apex/fused_dense/fused_dense.py -> build/bdist.linux-x86_64/egg/apex/fused_dense\n","creating build/bdist.linux-x86_64/egg/apex/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/optimizers/__init__.py -> build/bdist.linux-x86_64/egg/apex/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/optimizers/fused_adam.py -> build/bdist.linux-x86_64/egg/apex/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/optimizers/fused_novograd.py -> build/bdist.linux-x86_64/egg/apex/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/optimizers/fused_adagrad.py -> build/bdist.linux-x86_64/egg/apex/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/optimizers/fused_lamb.py -> build/bdist.linux-x86_64/egg/apex/optimizers\n","copying build/lib.linux-x86_64-3.7/apex/optimizers/fused_sgd.py -> build/bdist.linux-x86_64/egg/apex/optimizers\n","creating build/bdist.linux-x86_64/egg/apex/reparameterization\n","copying build/lib.linux-x86_64-3.7/apex/reparameterization/__init__.py -> build/bdist.linux-x86_64/egg/apex/reparameterization\n","copying build/lib.linux-x86_64-3.7/apex/reparameterization/reparameterization.py -> build/bdist.linux-x86_64/egg/apex/reparameterization\n","copying build/lib.linux-x86_64-3.7/apex/reparameterization/weight_norm.py -> build/bdist.linux-x86_64/egg/apex/reparameterization\n","copying build/lib.linux-x86_64-3.7/apex/_autocast_utils.py -> build/bdist.linux-x86_64/egg/apex\n","creating build/bdist.linux-x86_64/egg/apex/fp16_utils\n","copying build/lib.linux-x86_64-3.7/apex/fp16_utils/fp16_optimizer.py -> build/bdist.linux-x86_64/egg/apex/fp16_utils\n","copying build/lib.linux-x86_64-3.7/apex/fp16_utils/__init__.py -> build/bdist.linux-x86_64/egg/apex/fp16_utils\n","copying build/lib.linux-x86_64-3.7/apex/fp16_utils/fp16util.py -> build/bdist.linux-x86_64/egg/apex/fp16_utils\n","copying build/lib.linux-x86_64-3.7/apex/fp16_utils/loss_scaler.py -> build/bdist.linux-x86_64/egg/apex/fp16_utils\n","copying build/lib.linux-x86_64-3.7/scaled_masked_softmax_cuda.cpython-37m-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/nvtx/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/nvtx/nvmarker.py to nvmarker.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/parse/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/parse/__main__.py to __main__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/parse/kernel.py to kernel.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/parse/nvvp.py to nvvp.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/parse/db.py to db.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/parse/parse.py to parse.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/linear.py to linear.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/normalization.py to normalization.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/base.py to base.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/loss.py to loss.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/index_slice_join_mutate.py to index_slice_join_mutate.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/__main__.py to __main__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/dropout.py to dropout.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/optim.py to optim.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/usage.py to usage.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/activation.py to activation.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/softmax.py to softmax.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/data.py to data.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/randomSample.py to randomSample.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/utility.py to utility.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/misc.py to misc.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/embedding.py to embedding.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/convert.py to convert.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/pooling.py to pooling.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/conv.py to conv.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/recurrentCell.py to recurrentCell.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/blas.py to blas.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/output.py to output.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/pointwise.py to pointwise.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/reduction.py to reduction.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/pyprof/prof/prof.py to prof.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/layer_norm/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/layer_norm/layer_norm.py to layer_norm.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/groupbn/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/groupbn/batch_norm.py to batch_norm.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/fmha/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/fmha/fmha.py to fmha.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/sparsity/sparse_masklib.py to sparse_masklib.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/sparsity/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/sparsity/asp.py to asp.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/xentropy/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/xentropy/softmax_xentropy.py to softmax_xentropy.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/optimizers/fp16_optimizer.py to fp16_optimizer.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/optimizers/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/optimizers/fused_adam.py to fused_adam.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/optimizers/distributed_fused_lamb.py to distributed_fused_lamb.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/optimizers/distributed_fused_adam_v3.py to distributed_fused_adam_v3.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/optimizers/distributed_fused_adam.py to distributed_fused_adam.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/optimizers/distributed_fused_adam_v2.py to distributed_fused_adam_v2.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/optimizers/fused_lamb.py to fused_lamb.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/optimizers/fused_sgd.py to fused_sgd.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/bottleneck/bottleneck_module_test.py to bottleneck_module_test.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/bottleneck/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/bottleneck/test.py to test.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/bottleneck/bottleneck.py to bottleneck.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn/fast_self_multihead_attn_norm_add_func.py to fast_self_multihead_attn_norm_add_func.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn/self_multihead_attn.py to self_multihead_attn.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn/encdec_multihead_attn_func.py to encdec_multihead_attn_func.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn/self_multihead_attn_func.py to self_multihead_attn_func.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn/fast_encdec_multihead_attn_norm_add_func.py to fast_encdec_multihead_attn_norm_add_func.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn/mask_softmax_dropout_func.py to mask_softmax_dropout_func.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn/fast_encdec_multihead_attn_func.py to fast_encdec_multihead_attn_func.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn/fast_self_multihead_attn_func.py to fast_self_multihead_attn_func.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/multihead_attn/encdec_multihead_attn.py to encdec_multihead_attn.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/transducer/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/contrib/transducer/transducer.py to transducer.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/functional/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/functional/fused_softmax.py to fused_softmax.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/parallel_state.py to parallel_state.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/memory.py to memory.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/random.py to random.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/layers.py to layers.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/tests/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/tests/global_vars.py to global_vars.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/tests/commons.py to commons.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/tests/arguments.py to arguments.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/data.py to data.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/mappings.py to mappings.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/microbatches.py to microbatches.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/utils.py to utils.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/tensor_parallel/cross_entropy.py to cross_entropy.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/transformer/enums.py to enums.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/mlp/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/mlp/mlp.py to mlp.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/__version__.py to __version__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/rnn_compat.py to rnn_compat.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/wrap.py to wrap.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/_initialize.py to _initialize.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/frontend.py to frontend.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/lists/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/lists/functional_overrides.py to functional_overrides.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/lists/torch_overrides.py to torch_overrides.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/lists/tensor_overrides.py to tensor_overrides.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/_amp_state.py to _amp_state.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/handle.py to handle.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/opt.py to opt.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/amp.py to amp.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/compat.py to compat.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/utils.py to utils.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/_process_optimizer.py to _process_optimizer.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/amp/scaler.py to scaler.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/normalization/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/normalization/fused_layer_norm.py to fused_layer_norm.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/multi_tensor_apply/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/multi_tensor_apply/multi_tensor_apply.py to multi_tensor_apply.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/parallel/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/parallel/LARC.py to LARC.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/parallel/distributed.py to distributed.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/parallel/sync_batchnorm_kernel.py to sync_batchnorm_kernel.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/parallel/optimized_sync_batchnorm_kernel.py to optimized_sync_batchnorm_kernel.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/parallel/sync_batchnorm.py to sync_batchnorm.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/parallel/multiproc.py to multiproc.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/parallel/optimized_sync_batchnorm.py to optimized_sync_batchnorm.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/RNN/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/RNN/cells.py to cells.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/RNN/RNNBackend.py to RNNBackend.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/RNN/models.py to models.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/fused_dense/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/fused_dense/fused_dense.py to fused_dense.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/optimizers/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/optimizers/fused_adam.py to fused_adam.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/optimizers/fused_novograd.py to fused_novograd.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/optimizers/fused_adagrad.py to fused_adagrad.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/optimizers/fused_lamb.py to fused_lamb.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/optimizers/fused_sgd.py to fused_sgd.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/reparameterization/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/reparameterization/reparameterization.py to reparameterization.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/reparameterization/weight_norm.py to weight_norm.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/_autocast_utils.py to _autocast_utils.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/fp16_utils/fp16_optimizer.py to fp16_optimizer.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/fp16_utils/__init__.py to __init__.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/fp16_utils/fp16util.py to fp16util.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/apex/fp16_utils/loss_scaler.py to loss_scaler.cpython-37.pyc\n","creating stub loader for apex_C.cpython-37m-x86_64-linux-gnu.so\n","creating stub loader for amp_C.cpython-37m-x86_64-linux-gnu.so\n","creating stub loader for syncbn.cpython-37m-x86_64-linux-gnu.so\n","creating stub loader for fused_layer_norm_cuda.cpython-37m-x86_64-linux-gnu.so\n","creating stub loader for mlp_cuda.cpython-37m-x86_64-linux-gnu.so\n","creating stub loader for fused_dense_cuda.cpython-37m-x86_64-linux-gnu.so\n","creating stub loader for scaled_upper_triang_masked_softmax_cuda.cpython-37m-x86_64-linux-gnu.so\n","creating stub loader for scaled_masked_softmax_cuda.cpython-37m-x86_64-linux-gnu.so\n","byte-compiling build/bdist.linux-x86_64/egg/apex_C.py to apex_C.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/amp_C.py to amp_C.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/syncbn.py to syncbn.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/fused_layer_norm_cuda.py to fused_layer_norm_cuda.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/mlp_cuda.py to mlp_cuda.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/fused_dense_cuda.py to fused_dense_cuda.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/scaled_upper_triang_masked_softmax_cuda.py to scaled_upper_triang_masked_softmax_cuda.cpython-37.pyc\n","byte-compiling build/bdist.linux-x86_64/egg/scaled_masked_softmax_cuda.py to scaled_masked_softmax_cuda.cpython-37.pyc\n","creating build/bdist.linux-x86_64/egg/EGG-INFO\n","copying apex.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO\n","copying apex.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO\n","copying apex.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO\n","copying apex.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO\n","writing build/bdist.linux-x86_64/egg/EGG-INFO/native_libs.txt\n","zip_safe flag not set; analyzing archive contents...\n","__pycache__.amp_C.cpython-37: module references __file__\n","__pycache__.apex_C.cpython-37: module references __file__\n","__pycache__.fused_dense_cuda.cpython-37: module references __file__\n","__pycache__.fused_layer_norm_cuda.cpython-37: module references __file__\n","__pycache__.mlp_cuda.cpython-37: module references __file__\n","__pycache__.scaled_masked_softmax_cuda.cpython-37: module references __file__\n","__pycache__.scaled_upper_triang_masked_softmax_cuda.cpython-37: module references __file__\n","__pycache__.syncbn.cpython-37: module references __file__\n","apex.pyprof.nvtx.__pycache__.nvmarker.cpython-37: module references __file__\n","apex.pyprof.nvtx.__pycache__.nvmarker.cpython-37: module references __path__\n","creating dist\n","creating 'dist/apex-0.1-py3.7-linux-x86_64.egg' and adding 'build/bdist.linux-x86_64/egg' to it\n","removing 'build/bdist.linux-x86_64/egg' (and everything under it)\n","Processing apex-0.1-py3.7-linux-x86_64.egg\n","creating /usr/local/lib/python3.7/dist-packages/apex-0.1-py3.7-linux-x86_64.egg\n","Extracting apex-0.1-py3.7-linux-x86_64.egg to /usr/local/lib/python3.7/dist-packages\n","Adding apex 0.1 to easy-install.pth file\n","\n","Installed /usr/local/lib/python3.7/dist-packages/apex-0.1-py3.7-linux-x86_64.egg\n","Processing dependencies for apex==0.1\n","Finished processing dependencies for apex==0.1\n"]}]}]} |
View raw
(Sorry about that, but we can’t show files that are this big right now.)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment