[BugFix][PD]Fix metadata_buffer_index leak when aborted in PD#17483
Merged
ShangmingCai merged 4 commits intosgl-project:mainfrom Feb 9, 2026
Merged
[BugFix][PD]Fix metadata_buffer_index leak when aborted in PD#17483ShangmingCai merged 4 commits intosgl-project:mainfrom
ShangmingCai merged 4 commits intosgl-project:mainfrom
Conversation
ZhengWG
requested review from
Ying1123,
hnyls2002,
merrymercy and
xiezhq-hermann
as code owners
Collaborator
Author
|
@ShangmingCai Could you take a look at this PR? |
ZhengWG
force-pushed
the
fix-pd-meta-leak
branch
from
42aa39f to
9a4194c
Compare
Collaborator
|
/tag-and-rerun-ci |
Collaborator
Author
|
/rerun-failed-ci |
1 similar comment
Collaborator
Author
|
/rerun-failed-ci |
Collaborator
Author
|
/rerun-failed-ci |
2 similar comments
Collaborator
Author
|
/rerun-failed-ci |
Collaborator
Author
|
/rerun-failed-ci |
Collaborator
Author
|
/rerun-failed-ci |
2 similar comments
Collaborator
Author
|
/rerun-failed-ci |
Collaborator
Author
|
/rerun-failed-ci |
Johnsonms
pushed a commit
to Johnsonms/sglang
that referenced
this pull request
Feb 14, 2026
1StepForever
pushed a commit
to 1StepForever/sglang
that referenced
this pull request
Feb 26, 2026
* www/pr/ks: (265 commits) [BugFix][PD]Fix metadata_buffer_index leak when aborted in PD (sgl-project#17483) Refactoring Mooncake TE as a shared distributed component (sgl-project#17810) [ModelOPT] Support Qwen 3 Next Coder NVFP4 (sgl-project#18224) Update author information in pyproject.toml (sgl-project#18453) [Kimi-K2.5] Fix missing `quant_config` in `KimiK25` (sgl-project#18440) Add tensor parallelism support to LFM2 ShortConv layers (sgl-project#17777) [diffusion] chore: revise process title (sgl-project#18446) Fix TRT-LLM MLA backend applying k_scale to BF16 KV cache in BMM1 (sgl-project#18396) [diffusion] refactor: group component loaders under the component_loaders/ directory (sgl-project#18438) [ModelOpt] Fix broken Qwen3-235B-A22B-Instruct-2507-NVFP4 launch (sgl-project#18189) [diffusion] feat: support efficient sequence shard (sgl-project#18161) [CI] fix: notebook ci may not working (sgl-project#18417) fix: sync server_args.kv_cache_dtype when detecting FP8 KV cache (sgl-project#18394) [Fix] Fix backend selection after flashinfer version update (sgl-project#18364) [diffusion] platform: support WAN/FLUX/Qwen-Image/Qwen-Image-edit on Ascend (sgl-project#13662) fix: fix NVFP4 Kimi-K2.5 weight mapping and exclude list (sgl-project#18370) [diffusion] feat: support saving videos directly on the server to avoid the overhead of tensor transfer (sgl-project#18253) [diffusion] fix: respect dist_timeout option (sgl-project#18386) [Doc] Fix outdated `--fp4-gemm-backend` documentation (sgl-project#18350) [diffusion] fix: remove unnecessary norm_type argument from GLM-Image dits (sgl-project#18382) ...
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.
Motivation
In PD mode, when requests are aborted via
abort_request(), themetadata_buffer_indexallocated inpop_bootstrapped()is not freed, causing a memory leak. This happens when requests in thewaiting_queuehave already been allocated ametadata_buffer_indexbut are aborted before entering theinflight_queue, where the index would normally be freed.Modifications
Added cleanup logic in
abort_request()to freemetadata_buffer_indexwhen aborting requests inwaiting_queuefor PD mode.Accuracy Tests
Benchmarking and Profiling
Checklist
Review Process
/tag-run-ci-label,/rerun-failed-ci,/tag-and-rerun-ci