*i\ddlZddlmZmZgdZgdZdZdZejdZ y) N) check_errorcudart)startstopprofile)gpustarttimestampgpuendtimestamp gridsize3dthreadblocksizestreamidzenableonstart 0conckerneltracecFttjy)zStarts cuda profiler data collection. .. warning:: Raises CudaError in case of it is unable to start the profiler. N)rrcudaProfilerStartU/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/torch/cuda/profiler.pyrrs **,-rcFttjy)zStops cuda profiler data collection. .. warning:: Raises CudaError in case of it is unable to stop the profiler. N)rrcudaProfilerStoprrrrrs ))+,rc#\K tdty#twxYww)a Enable profiling. Context Manager to enabling profile collection by the active profiling tool from CUDA backend. Example: >>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_CUDA) >>> import torch >>> model = torch.nn.Linear(20, 30).cuda() >>> inputs = torch.randn(128, 20).cuda() >>> with torch.cuda.profiler.profile() as prof: ... model(inputs) N)rrrrrrr&s   s, , ),) contextlibrr__all__ DEFAULT_FLAGSrrcontextmanagerrrrrrs=! ' .- r