Skip to content

Instantly share code, notes, and snippets.

File "/data/users/suo/fbsource/genai/frontier/verl/verl/single_controller/monarch/base.py", line 548, in func
File "/packages/verl_workspace/verl/verl/single_controller/base/decorator.py", line 594, in inner
return func(*args, **kwargs)
File "/packages/verl_workspace/verl/verl/utils/profiler/performance.py", line 96, in f
return self.log(decorated_function, *args, **kwargs)
File "/packages/verl_workspace/verl/verl/utils/profiler/performance.py", line 109, in log
output = func(*args, **kwargs)
File "/packages/verl_workspace/verl/verl/workers/megatron_workers.py", line 764, in compute_log_prob
output, entropys = self.actor.compute_log_prob(
File "/packages/verl_workspace/verl/verl/utils/profiler/performance.py", line 96, in f
This file has been truncated, but you can view the full file.
I! CuDNN (v90800 87) function cudnnCreate() called:
i! handle: location=host; addr=0x55ba34aedc70;
i! Time: 2025-07-16T17:36:49.965429 (0d+0h+0m+3s since start)
i! Process=1973364; Thread=1973364; GPU=NULL; Handle=NULL; StreamId=NULL.
I! CuDNN (v90800 87) function cudnnGraphLibraryConfigInit() called:
i! apiLog: type=cudnnLibConfig_t; val=FULL;
i! Time: 2025-07-16T17:36:49.965483 (0d+0h+0m+3s since start)
i! Process=1973364; Thread=1973364; GPU=NULL; Handle=NULL; StreamId=NULL.
import torch
import transformer_engine
import transformer_engine_torch as tex
obj = torch.load("te_fused_attn_fwd_inputs.pt", weights_only=False)
print(obj)
print(tex.fused_attn_fwd(*obj))
PyTorch version: 2.6.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A
OS: CentOS Stream 9 (x86_64)
GCC version: (conda-forge gcc 15.1.0-3) 15.1.0
Clang version: 20.1.3 (CentOS 20.1.3-1.el9)
CMake version: Could not collect
Libc version: glibc-2.34
No X1 transaction date X2 house age X3 distance to the nearest MRT station X4 number of convenience stores X5 latitude X6 longitude Y house price of unit area
1 2012.917 32 84.87882 10 24.98298 121.54024 37.9
2 2012.917 19.5 306.5947 9 24.98034 121.53951 42.2
3 2013.583 13.3 561.9845 5 24.98746 121.54391 47.3
4 2013.500 13.3 561.9845 5 24.98746 121.54391 54.8
5 2012.833 5 390.5684 5 24.97937 121.54245 43.1
6 2012.667 7.1 2175.03 3 24.96305 121.51254 32.1
7 2012.667 34.5 623.4731 7 24.97933 121.53642 40.3
8 2013.417 20.3 287.6025 6 24.98042 121.54228 46.7
9 2013.500 31.7 5512.038 1 24.95095 121.48458 18.8
@suo
suo / gist:21371d187e8d97c347610f9a57837630
Created September 18, 2023 21:36
OECD better life index
"LOCATION","Country","INDICATOR","Indicator","MEASURE","Measure","INEQUALITY","Inequality","Unit Code","Unit","PowerCode Code","PowerCode","Reference Period Code","Reference Period","Value","Flag Codes","Flags"
"AUS","Australia","JE_LMIS","Labour market insecurity","L","Value","TOT","Total","PC","Percentage","0","Units",,,3.1,,
"AUT","Austria","JE_LMIS","Labour market insecurity","L","Value","TOT","Total","PC","Percentage","0","Units",,,2.3,,
"BEL","Belgium","JE_LMIS","Labour market insecurity","L","Value","TOT","Total","PC","Percentage","0","Units",,,2.4,,
"CAN","Canada","JE_LMIS","Labour market insecurity","L","Value","TOT","Total","PC","Percentage","0","Units",,,3.8,,
"CZE","Czech Republic","JE_LMIS","Labour market insecurity","L","Value","TOT","Total","PC","Percentage","0","Units",,,2.3,,
"DNK","Denmark","JE_LMIS","Labour market insecurity","L","Value","TOT","Total","PC","Percentage","0","Units",,,4.5,,
"FIN","Finland","JE_LMIS","Labour market insecurity","L","Value","TOT","Total","PC","Percentage","0","U
File "/private/home/suo/scratch/test.py", line 11, in <module>
func(a, b)
File "/raid/suo/pytorch/torch/_dynamo/eval_frame.py", line 176, in _fn
return fn(*args, **kwargs)
File "/private/home/suo/scratch/test.py", line 5, in func
@torchdynamo.optimize("nvprims_nvfuser")
File "/raid/suo/pytorch/torch/_dynamo/eval_frame.py", line 176, in _fn
return fn(*args, **kwargs)
File "/raid/suo/pytorch/functorch/_src/aot_autograd.py", line 870, in forward
return compiled_f(
Traceback (most recent call last):
File "/raid/suo/pytorch/torch/_dynamo/convert_frame.py", line 380, in _compile
out_code = transform_code_object(code, transform)
File "/raid/suo/pytorch/torch/_dynamo/bytecode_transformation.py", line 341, in transform_code_object
transformations(instructions, code_options)
File "/raid/suo/pytorch/torch/_dynamo/convert_frame.py", line 357, in transform
tracer = InstructionTranslator(
File "/raid/suo/pytorch/torch/_dynamo/symbolic_convert.py", line 1399, in __init__
self.symbolic_locals = collections.OrderedDict(
File "/raid/suo/pytorch/torch/_dynamo/symbolic_convert.py", line 1400, in <genexpr>
This file has been truncated, but you can view the full file.
[{"name": "CMakeFiles/install.util", "cat": "targets", "ph": "X", "ts": 264686000, "dur": 1228000, "pid": 0, "tid": 0, "args": {}}, {"name": "lib/libnnapi_backend.so", "cat": "targets", "ph": "X", "ts": 264563000, "dur": 123000, "pid": 0, "tid": 0, "args": {}}, {"name": "lib/libtorch_python.so", "cat": "targets", "ph": "X", "ts": 264230000, "dur": 333000, "pid": 0, "tid": 0, "args": {}}, {"name": "bin/torch_shm_manager", "cat": "targets", "ph": "X", "ts": 264230000, "dur": 130000, "pid": 0, "tid": 1, "args": {}}, {"name": "lib/libtorch_cuda_linalg.so", "cat": "targets", "ph": "X", "ts": 263984000, "dur": 342000, "pid": 0, "tid": 2, "args": {}}, {"name": "lib/libshm.so", "cat": "targets", "ph": "X", "ts": 264108000, "dur": 122000, "pid": 0, "tid": 0, "args": {}}, {"name": "lib/libtorch.so", "cat": "targets", "ph": "X", "ts": 263984000, "dur": 124000, "pid": 0, "tid": 0, "args": {}}, {"name": "lib/libtorch_cuda.so", "cat": "targets", "ph": "X", "ts": 263110000, "dur": 873000, "pid": 0, "tid": 0, "args": {}}, {"
This file has been truncated, but you can view the full file.
[{"name": "CMakeFiles/install.util", "cat": "targets", "ph": "X", "ts": 294887000, "dur": 2602000, "pid": 0, "tid": 0, "args": {}}, {"name": "lib/libnnapi_backend.so", "cat": "targets", "ph": "X", "ts": 294568000, "dur": 319000, "pid": 0, "tid": 0, "args": {}}, {"name": "lib/libtorch_python.so", "cat": "targets", "ph": "X", "ts": 291494000, "dur": 3074000, "pid": 0, "tid": 0, "args": {}}, {"name": "bin/torch_shm_manager", "cat": "targets", "ph": "X", "ts": 291494000, "dur": 274000, "pid": 0, "tid": 1, "args": {}}, {"name": "lib/libshm.so", "cat": "targets", "ph": "X", "ts": 291225000, "dur": 269000, "pid": 0, "tid": 0, "args": {}}, {"name": "lib/libtorch_cuda_linalg.so", "cat": "targets", "ph": "X", "ts": 290957000, "dur": 533000, "pid": 0, "tid": 1, "args": {}}, {"name": "lib/libtorch.so", "cat": "targets", "ph": "X", "ts": 290957000, "dur": 268000, "pid": 0, "tid": 0, "args": {}}, {"name": "lib/libtorch_cuda.so", "cat": "targets", "ph": "X", "ts": 283423000, "dur": 7534000, "pid": 0, "tid": 0, "args": {}},