Skip to content

[Refactor] profiler config optimze #6141

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
MengqingCao merged 1 commit into from
Jan 27, 2026
Merged

[Refactor] profiler config optimze #6141

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions vllm_ascend/worker/worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -561,7 +561,7 @@ def _init_profiler(self):
aic_metrics=torch_npu.profiler.AiCMetrics.AiCoreNone,
l2_cache=False,
Copy link
Copy Markdown
Collaborator

@whx-sjtu whx-sjtu Jan 26, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it's better to keep these default values in case user wants to enable one of these parameters but don't known concrete param name.

Copy link
Copy Markdown
Contributor Author

@mengchengTang mengchengTang Jan 26, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the suggestion. I agree that explicitly listing these parameters makes it easier for users to discover and enable them if needed. I have restored the parameters with their default values.

op_attr=False,
data_simplification=False,
data_simplification=True,
record_op_args=False,
gc_detect_threshold=None,
)
Expand All @@ -571,9 +571,11 @@ def _init_profiler(self):
torch_npu.profiler.ProfilerActivity.CPU,
torch_npu.profiler.ProfilerActivity.NPU,
],
with_stack=profiler_config.torch_profiler_with_stack,
with_stack=False,
profile_memory=profiler_config.torch_profiler_with_memory,
with_modules=False,
# NOTE: torch_npu.profiler.with_modules is equivalent to torch.profiler.with_stack.
# The with_stack option in torch_npu.profiler introduces significant time overhead.
with_modules=profiler_config.torch_profiler_with_stack,
experimental_config=experimental_config,
on_trace_ready=torch_npu.profiler.tensorboard_trace_handler(
torch_profiler_trace_dir))
Expand Down