Skip to content

add VLLM_ENGINE_PROFILER_SKIP_STEPS to the engine profiler #2143

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

Open
wants to merge 3 commits into
base: aice/v1.22.0
Choose a base branch
from
Open

add VLLM_ENGINE_PROFILER_SKIP_STEPS to the engine profiler #2143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8619c3f
add VLLM_ENGINE_PROFILER_SKIP_STEPS to the engine profiler
yangulei Nov 19, 2025
bb36473
fix typo
yangulei Nov 19, 2025
bb3dacb
update readme
yangulei Nov 19, 2025
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
7 changes: 4 additions & 3 deletions scripts/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -467,9 +467,10 @@ modID CPU Affinity NUMA Affinity
### Profile the LLM engine
The following 4 ENVs are used to control the device profiling:
* `VLLM_ENGINE_PROFILER_ENABLED`, set to `true` to enable device profiler.
* `VLLM_ENGINE_PROFILER_WARMUP_STEPS`, number of steps to ignore for profiling.
* `VLLM_ENGINE_PROFILER_STEPS`, number of steps to capture for profiling.
* `VLLM_ENGINE_PROFILER_REPEAT`, number of cycles for (warmup + profile).
* `VLLM_ENGINE_PROFILER_SKIP_STEPS`, number of steps to skip for profiling.
* `VLLM_ENGINE_PROFILER_WARMUP_STEPS`, number of steps to ignore for each repetition.
* `VLLM_ENGINE_PROFILER_STEPS`, number of steps to capture profile in each repetition.
* `VLLM_ENGINE_PROFILER_REPEAT`, number of repetition for (warmup_steps + profile_steps).

> Please refer to [torch.profiler.schedule](https://pytorch.org/docs/stable/profiler.html#torch.profiler.schedule) for more details about the profiler schedule arguments.

Expand Down
4 changes: 3 additions & 1 deletion vllm/entrypoints/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -264,10 +264,12 @@ def _setup_profiler(self):
"false").lower() in ["true", "1"]
if not enable_profile:
return None
skip_first = int(os.getenv("VLLM_ENGINE_PROFILER_SKIP_STEPS", "0"))
warmup = int(os.getenv("VLLM_ENGINE_PROFILER_WARMUP_STEPS", "0"))
steps = int(os.getenv("VLLM_ENGINE_PROFILER_STEPS", "1"))
repeat = int(os.getenv("VLLM_ENGINE_PROFILER_REPEAT", "1"))
schedule = torch.profiler.schedule(wait=0,
schedule = torch.profiler.schedule(skip_first=skip_first,
wait=0,
warmup=warmup,
active=steps,
repeat=repeat)
Expand Down