Enable DeepGemm fast warmup in CI to prevent cold-cache timeouts#18823
Merged
Conversation
When CI runners restart, the DeepGemm cache is lost, causing a full warmup that compiles up to 128K kernel variants (~30 min), which exceeds CI timeouts. Enable SGLANG_JIT_DEEPGEMM_FAST_WARMUP to reduce compilation to ~3K variants (<3 min warmup).
alisonshao
requested review from
Fridge003,
Kangyan-Zhou,
ispobock and
merrymercy
as code owners
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Collaborator
Author
|
/rerun-stage stage-c-test-deepep-4-gpu |
Contributor
|
✅ Triggered |
Contributor
Collaborator
Author
|
/tag-and-rerun-ci |
Collaborator
Author
|
/rerun-stage stage-c-test-4-gpu-b200 |
Contributor
|
✅ Triggered |
Contributor
magicYang1573
pushed a commit
to magicYang1573/sglang
that referenced
this pull request
Mar 9, 2026
Wangzheee
pushed a commit
to Wangzheee/sglang
that referenced
this pull request
Mar 21, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
SGLANG_JIT_DEEPGEMM_FAST_WARMUP=trueglobally in CI workflow to prevent DeepGemm compilation timeouts when runners restart and the JIT cache (~/.cache/deep_gemm) is lostContext
Previously
SGLANG_DG_CACHE_DIRwas set so CI workers shared a single DeepGemm cache directory. When runners are reprovisioned, this cache is lost. Setting the fast warmup flag through the workflow env ensures this is handled in code without requiring machine-level configuration.Test plan