redefine tmp_workspace using full tensor in append_attn#6999
Open
lizhenyun01 wants to merge 8 commits intoPaddlePaddle:developfrom
Open
redefine tmp_workspace using full tensor in append_attn#6999lizhenyun01 wants to merge 8 commits intoPaddlePaddle:developfrom
lizhenyun01 wants to merge 8 commits intoPaddlePaddle:developfrom
Conversation
|
Thanks for your contribution! |
fastdeploy-bot
left a comment
fastdeploy-bot
left a comment
There was a problem hiding this comment.
AI CI Agent | skill:
pr_review_agent
Review completed (解析失败)
Jiang-Jia-Jun
added a commit
that referenced
this pull request
Mar 25, 2026
…end_attn(#6999) (#7002) * [Cherry-Pick][BugFix][APIServer] Enable control socket disable option in API server (#6551) (#6554) * Initial plan * [BugFix][APIServer] Add control_socket_disable to gunicorn options (cherry-pick of #6551) Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> * [Cherry-Pick][BugFix] Fix AttributeError in recycle_gpu_blocks when prefix_tree_status_signal not initialized(#6531) (#6559) * fix mtp acceptance rate decline * [BugFix] Fix AttributeError in recycle_gpu_blocks when prefix_tree_status_signal not initialized - Add hasattr check before accessing prefix_tree_status_signal - The signal is only initialized in launch_cache_messager, not in __init__ - Fixes CI test failure in test_prefix_cache_manager.py Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * [BugFix] Reset prefix cache when model weights are updating - Call self.reset() before setting status to NORMAL in UPDATING state - Ensure cache consistency when model weights change - Consistent with CLEARING state handling Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * [RL] Clear Requests status of R3 (#6569) * [Cherry-Pick] [BugFix] fix prefix tree updating timeout (#6615)(#6617) * [Cherry-Pick][BugFix] fix mtp_config in rl (#6595)(#6597) Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> * [BugFix][MTP] Skip empty_input_forward during dummy run (#6655) When `is_dummy_run=True`, calling `empty_input_forward` can cause unexpected behavior. Add `and not is_dummy_run` guard for both `_propose_cuda` and `_propose_xpu` paths. Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> * redefine tmp_workspace using full tensor in append_attn * fix test * fix pre-commit --------- Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> Co-authored-by: kevin <chengyf112@gmail.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: RAM <gstian5555@outlook.com> Co-authored-by: Yonghua Li <39643373+liyonghua0910@users.noreply.github.com> Co-authored-by: GoldPancake <56388518+Deleter-D@users.noreply.github.com> Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> Co-authored-by: Yuanle Liu <yuanlehome@163.com>
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## develop #6999 +/- ##
==========================================
Coverage ? 73.96%
==========================================
Files ? 399
Lines ? 56060
Branches ? 8850
==========================================
Hits ? 41467
Misses ? 11646
Partials ? 2947
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
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
3 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
将append_attn算子 split_kv场景下中使用的tmp_workspace以及tmp_m,tmp_d buffer改为由backend传入并在层间共享
Modifications
Usage or Command
Accuracy Tests
Checklist
[FDConfig],[APIServer],[Engine],[Scheduler],[PD Disaggregation],[Executor],[Graph Optimization],[Speculative Decoding],[RL],[Models],[Quantization],[Loader],[OP],[KVCache],[DataProcessor],[BugFix],[Docs],[CI],[Optimization],[Feature],[Benchmark],[Others],[XPU],[HPU],[GCU],[DCU],[Iluvatar],[Metax]]pre-commitbefore commit.releasebranch, make sure the PR has been submitted to thedevelopbranch, then cherry-pick it to thereleasebranch with the[Cherry-Pick]PR tag.