skip HPU graphs for long prefills#1033
Merged
Merged
Conversation
Signed-off-by: Youlei Yang <youlei.yang@intel.com>
yangulei
requested review from
Wei-Lin-Intel,
czhu15,
mgawarkiewicz-intel,
piotrbocian,
taotod and
wpyszka
as code owners
Contributor
There was a problem hiding this comment.
Pull request overview
This PR re-applies the “skip HPU graphs for long prefills” behavior to reduce HPU OOM risk by avoiding HPU graph capture for large prompt (prefill) workloads, especially when long context is involved (e.g., chunked prefill / prefix caching scenarios).
Changes:
- Introduces
max_graph_capture_tokens, defaulting tomax_num_batched_tokenswhenmax_cudagraph_capture_sizeis unset. - Updates the HPU-graph enable/disable heuristic to account for context size when deciding whether to bypass HPU graphs for prefills.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Signed-off-by: Youlei Yang <youlei.yang@intel.com>
czhu15
pushed a commit
that referenced
this pull request
Feb 27, 2026
Re-apply #780 to avoid OOM error caused by too many unnecessary HPU graphs captured for long prefills. --------- Signed-off-by: Youlei Yang <youlei.yang@intel.com>
tvoas
pushed a commit
to tvoas/vllm-gaudi
that referenced
this pull request
Mar 11, 2026
Re-apply vllm-project#780 to avoid OOM error caused by too many unnecessary HPU graphs captured for long prefills. --------- Signed-off-by: Youlei Yang <youlei.yang@intel.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Re-apply #780 to avoid OOM error caused by too many unnecessary HPU graphs captured for long prefills.