Skip to content

Instantly share code, notes, and snippets.

@ScottTodd
Last active October 31, 2024 23:15
Show Gist options
  • Save ScottTodd/4cd0c343a92375e7fbdaaf37c38bfc06 to your computer and use it in GitHub Desktop.
Save ScottTodd/4cd0c343a92375e7fbdaaf37c38bfc06 to your computer and use it in GitHub Desktop.
nod@Shark16:~/dev/scratch/shark-platform $ python3.11 -m venv 3.11.venv
nod@Shark16:~/dev/scratch/shark-platform $ source 3.11.venv/bin/activate
(3.11.venv) nod@Shark16:~/dev/scratch/shark-platform $ python -m pip install ~/Downloads/sharktank-3.0.0rc20241031-py3-none-any.whl
Processing /home/nod/Downloads/sharktank-3.0.0rc20241031-py3-none-any.whl
Collecting iree-turbine (from sharktank==3.0.0rc20241031)
Using cached iree_turbine-2.4.1-py3-none-any.whl.metadata (5.4 kB)
Collecting numpy>=1.26.3 (from iree-turbine->sharktank==3.0.0rc20241031)
Using cached numpy-2.1.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (60 kB)
Collecting iree-compiler (from iree-turbine->sharktank==3.0.0rc20241031)
Using cached iree_compiler-20240828.999-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (592 bytes)
Collecting iree-runtime (from iree-turbine->sharktank==3.0.0rc20241031)
Using cached iree_runtime-20240828.999-cp311-cp311-manylinux_2_28_x86_64.whl.metadata (775 bytes)
Collecting torch>=2.3.0 (from iree-turbine->sharktank==3.0.0rc20241031)
Using cached torch-2.5.1-cp311-cp311-manylinux1_x86_64.whl.metadata (28 kB)
Collecting Jinja2>=3.1.3 (from iree-turbine->sharktank==3.0.0rc20241031)
Using cached jinja2-3.1.4-py3-none-any.whl.metadata (2.6 kB)
Collecting MarkupSafe>=2.0 (from Jinja2>=3.1.3->iree-turbine->sharktank==3.0.0rc20241031)
Using cached MarkupSafe-3.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.0 kB)
Collecting filelock (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached filelock-3.16.1-py3-none-any.whl.metadata (2.9 kB)
Collecting typing-extensions>=4.8.0 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached typing_extensions-4.12.2-py3-none-any.whl.metadata (3.0 kB)
Collecting networkx (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached networkx-3.4.2-py3-none-any.whl.metadata (6.3 kB)
Collecting fsspec (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached fsspec-2024.10.0-py3-none-any.whl.metadata (11 kB)
Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)
Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)
Collecting nvidia-cublas-cu12==12.4.5.8 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cufft-cu12==11.2.1.3 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-curand-cu12==10.3.5.147 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)
Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)
Collecting nvidia-nccl-cu12==2.21.5 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_nccl_cu12-2.21.5-py3-none-manylinux2014_x86_64.whl.metadata (1.8 kB)
Collecting nvidia-nvtx-cu12==12.4.127 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.7 kB)
Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting triton==3.1.0 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached triton-3.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.3 kB)
Collecting sympy==1.13.1 (from torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached sympy-1.13.1-py3-none-any.whl.metadata (12 kB)
Collecting mpmath<1.4,>=1.1.0 (from sympy==1.13.1->torch>=2.3.0->iree-turbine->sharktank==3.0.0rc20241031)
Using cached mpmath-1.3.0-py3-none-any.whl.metadata (8.6 kB)
Using cached iree_turbine-2.4.1-py3-none-any.whl (223 kB)
Using cached jinja2-3.1.4-py3-none-any.whl (133 kB)
Using cached numpy-2.1.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (16.3 MB)
Using cached torch-2.5.1-cp311-cp311-manylinux1_x86_64.whl (906.5 MB)
Using cached nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)
Using cached nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (13.8 MB)
Using cached nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (24.6 MB)
Using cached nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (883 kB)
Using cached nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)
Using cached nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)
Using cached nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)
Using cached nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)
Using cached nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)
Using cached nvidia_nccl_cu12-2.21.5-py3-none-manylinux2014_x86_64.whl (188.7 MB)
Using cached nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)
Using cached nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (99 kB)
Using cached sympy-1.13.1-py3-none-any.whl (6.2 MB)
Using cached triton-3.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (209.5 MB)
Using cached iree_compiler-20240828.999-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (68.3 MB)
Using cached iree_runtime-20240828.999-cp311-cp311-manylinux_2_28_x86_64.whl (8.0 MB)
Using cached MarkupSafe-3.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (23 kB)
Using cached typing_extensions-4.12.2-py3-none-any.whl (37 kB)
Using cached filelock-3.16.1-py3-none-any.whl (16 kB)
Using cached fsspec-2024.10.0-py3-none-any.whl (179 kB)
Using cached networkx-3.4.2-py3-none-any.whl (1.7 MB)
Using cached mpmath-1.3.0-py3-none-any.whl (536 kB)
Installing collected packages: mpmath, typing-extensions, sympy, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, numpy, networkx, MarkupSafe, fsspec, filelock, triton, nvidia-cusparse-cu12, nvidia-cudnn-cu12, Jinja2, iree-runtime, iree-compiler, nvidia-cusolver-cu12, torch, iree-turbine, sharktank
Successfully installed Jinja2-3.1.4 MarkupSafe-3.0.2 filelock-3.16.1 fsspec-2024.10.0 iree-compiler-20240828.999 iree-runtime-20240828.999 iree-turbine-2.4.1 mpmath-1.3.0 networkx-3.4.2 numpy-2.1.2 nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupti-cu12-12.4.127 nvidia-cuda-nvrtc-cu12-12.4.127 nvidia-cuda-runtime-cu12-12.4.127 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nccl-cu12-2.21.5 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.4.127 sharktank-3.0.0rc20241031 sympy-1.13.1 torch-2.5.1 triton-3.1.0 typing-extensions-4.12.2
[notice] A new release of pip is available: 24.0 -> 24.3.1
[notice] To update, run: pip install --upgrade pip
(3.11.venv) nod@Shark16:~/dev/scratch/shark-platform $ python
Python 3.11.10 (main, Sep 7 2024, 18:35:41) [GCC 11.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from sharktank import ops
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/sharktank/ops/__init__.py", line 19, in <module>
from . import _registry
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/sharktank/ops/_registry.py", line 17, in <module>
from ..types import PrimitiveTensor, QuantizedTensor
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/sharktank/types/__init__.py", line 7, in <module>
from .layouts import *
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/sharktank/types/layouts.py", line 21, in <module>
from .tensors import (
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/sharktank/types/tensors.py", line 31, in <module>
from iree.turbine.aot import (
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/iree/turbine/__init__.py", line 18, in <module>
from shark_turbine import aot
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/shark_turbine/aot/__init__.py", line 11, in <module>
from .builtins import *
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/shark_turbine/aot/builtins/__init__.py", line 7, in <module>
from .globals import *
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/shark_turbine/aot/builtins/globals.py", line 12, in <module>
from ..support.procedural import (
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/shark_turbine/aot/support/procedural/__init__.py", line 13, in <module>
from .base import *
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/shark_turbine/aot/support/procedural/base.py", line 260, in <module>
from .primitives import (
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/shark_turbine/aot/support/procedural/primitives.py", line 23, in <module>
from torch.export import (
ImportError: cannot import name 'dynamic_dim' from 'torch.export' (/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/torch/export/__init__.py)
>>>
(3.11.venv) nod@Shark16:~/dev/scratch/shark-platform $ pip install -f https://iree.dev/pip-release-links.html --src deps \
-e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine"
Looking in links: https://iree.dev/pip-release-links.html
Obtaining iree-turbine from git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine
Cloning https://github.com/iree-org/iree-turbine.git to ./deps/iree-turbine
Running command git clone --filter=blob:none --quiet https://github.com/iree-org/iree-turbine.git /home/nod/dev/scratch/shark-platform/deps/iree-turbine
Resolved https://github.com/iree-org/iree-turbine.git to commit 8febe6afcf98dfd17a387b351a9e0014f6a910a7
Installing build dependencies ... done
Checking if build backend supports build_editable ... done
Getting requirements to build editable ... done
Preparing editable metadata (pyproject.toml) ... done
Requirement already satisfied: numpy>=1.26.3 in ./3.11.venv/lib/python3.11/site-packages (from iree-turbine) (2.1.2)
Requirement already satisfied: iree-compiler in ./3.11.venv/lib/python3.11/site-packages (from iree-turbine) (20240828.999)
Requirement already satisfied: iree-runtime in ./3.11.venv/lib/python3.11/site-packages (from iree-turbine) (20240828.999)
Requirement already satisfied: torch>=2.3.0 in ./3.11.venv/lib/python3.11/site-packages (from iree-turbine) (2.5.1)
Requirement already satisfied: Jinja2>=3.1.3 in ./3.11.venv/lib/python3.11/site-packages (from iree-turbine) (3.1.4)
Requirement already satisfied: MarkupSafe>=2.0 in ./3.11.venv/lib/python3.11/site-packages (from Jinja2>=3.1.3->iree-turbine) (3.0.2)
Requirement already satisfied: filelock in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (3.16.1)
Requirement already satisfied: typing-extensions>=4.8.0 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (4.12.2)
Requirement already satisfied: networkx in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (3.4.2)
Requirement already satisfied: fsspec in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (2024.10.0)
Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (12.4.127)
Requirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (12.4.127)
Requirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (12.4.127)
Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (9.1.0.70)
Requirement already satisfied: nvidia-cublas-cu12==12.4.5.8 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (12.4.5.8)
Requirement already satisfied: nvidia-cufft-cu12==11.2.1.3 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (11.2.1.3)
Requirement already satisfied: nvidia-curand-cu12==10.3.5.147 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (10.3.5.147)
Requirement already satisfied: nvidia-cusolver-cu12==11.6.1.9 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (11.6.1.9)
Requirement already satisfied: nvidia-cusparse-cu12==12.3.1.170 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (12.3.1.170)
Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (2.21.5)
Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (12.4.127)
Requirement already satisfied: nvidia-nvjitlink-cu12==12.4.127 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (12.4.127)
Requirement already satisfied: triton==3.1.0 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (3.1.0)
Requirement already satisfied: sympy==1.13.1 in ./3.11.venv/lib/python3.11/site-packages (from torch>=2.3.0->iree-turbine) (1.13.1)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in ./3.11.venv/lib/python3.11/site-packages (from sympy==1.13.1->torch>=2.3.0->iree-turbine) (1.3.0)
Building wheels for collected packages: iree-turbine
Building editable for iree-turbine (pyproject.toml) ... done
Created wheel for iree-turbine: filename=iree_turbine-2.3.0rc20240621-0.editable-py3-none-any.whl size=10360 sha256=d06b26233842c49075b3af9f91968b96db01aa6509c806156bc0d48ecdb8b261
Stored in directory: /tmp/pip-ephem-wheel-cache-gnc9h2_0/wheels/c0/80/10/7dfb706f2840d355b7922682cb8daa9a0a3d945044ea22935f
Successfully built iree-turbine
Installing collected packages: iree-turbine
Attempting uninstall: iree-turbine
Found existing installation: iree-turbine 2.4.1
Uninstalling iree-turbine-2.4.1:
Successfully uninstalled iree-turbine-2.4.1
Successfully installed iree-turbine-2.3.0rc20240621
[notice] A new release of pip is available: 24.0 -> 24.3.1
[notice] To update, run: pip install --upgrade pip
(3.11.venv) nod@Shark16:~/dev/scratch/shark-platform $ python
Python 3.11.10 (main, Sep 7 2024, 18:35:41) [GCC 11.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from sharktank import ops
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/sharktank/ops/__init__.py", line 19, in <module>
from . import _registry
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/sharktank/ops/_registry.py", line 17, in <module>
from ..types import PrimitiveTensor, QuantizedTensor
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/sharktank/types/__init__.py", line 12, in <module>
from . import gguf_interop
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/sharktank/types/gguf_interop/__init__.py", line 7, in <module>
from .base import load_file
File "/home/nod/dev/scratch/shark-platform/3.11.venv/lib/python3.11/site-packages/sharktank/types/gguf_interop/base.py", line 14, in <module>
from gguf import GGUFReader, GGUFValueType
ModuleNotFoundError: No module named 'gguf'
>>> quit()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment