mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-20 12:54:11 +08:00
Add NVTX annotations around training phases and buffer computations RFC/discussion: https://dev-discuss.pytorch.org/t/rfc-performance-profiling-at-scale-with-details-nvtx-annotations/2224 <img width="2160" alt="Screenshot 2024-07-10 at 11 48 04" src="https://github.com/pytorch/pytorch/assets/1175576/9ade139c-d393-473f-9b68-6c25da367dc4"> Pull Request resolved: https://github.com/pytorch/pytorch/pull/130429 Approved by: https://github.com/aorenste, https://github.com/eellison, https://github.com/albanD Co-authored-by: Cedric GESTES <cedric.gestes@flex.ai>
10 lines
380 B
Python
10 lines
380 B
Python
# mypy: allow-untyped-defs
|
|
# Defined in torch/csrc/cuda/shared/nvtx.cpp
|
|
def rangePushA(message: str) -> int: ...
|
|
def rangePop() -> int: ...
|
|
def rangeStartA(message: str) -> int: ...
|
|
def rangeEnd(int) -> None: ...
|
|
def markA(message: str) -> None: ...
|
|
def deviceRangeStart(message: str, stream: int) -> object: ...
|
|
def deviceRangeEnd(range_handle: object, stream: int) -> None: ...
|