Skip to content

Pull requests: PaddlePaddle/FastDeploy

New pull request New
445 Open 6,000 Closed
445 Open 6,000 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[CI] Skip CI for non-runtime directories and add unittest Claude skill
#7870 opened May 20, 2026 by EmmonsCurse Collaborator Loading…
2 of 5 tasks
14
Ck
#7869 opened May 20, 2026 by lizexu123 Collaborator Loading…
5 tasks
7
[RL] Reset buffer size of slot_mapping
#7868 opened May 20, 2026 by gongshaotian Collaborator Loading…
5 tasks done
5
[RL] Reset buffer size of slot_mapping
#7866 opened May 20, 2026 by gongshaotian Collaborator Loading…
5 tasks done
5
[Metric] Support custom metric labels
#7865 opened May 20, 2026 by liyonghua0910 Collaborator Loading…
2 of 5 tasks
5
[XPU] Fix mtp cudagraph
#7864 opened May 20, 2026 by cmcamdy Collaborator Loading…
2 of 5 tasks
5
[KVCache] Add free_cpu_block_num gauge metric
#7856 opened May 19, 2026 by liyonghua0910 Collaborator Loading…
2 of 5 tasks
4
[Cherry-Pick][KVCache] Support request-level prefix cache disable(#7854)
#7855 opened May 19, 2026 by kevincheng2 Collaborator Loading…
4 of 5 tasks
3
[KVCache] Support request-level prefix cache disable
#7854 opened May 19, 2026 by kevincheng2 Collaborator Loading…
3 of 5 tasks
7
[DataProcessor] Refactor and unify text/multimodal processor pipeline
#7853 opened May 19, 2026 by luukunn Collaborator Loading…
3 of 5 tasks
11
Support Triton MLA Attention Backend
#7852 opened May 19, 2026 by chang-wenbin Collaborator Loading…
5 tasks
4
[Speculative Decoding]【Hackathon 10th Spring No.54】hybrid_mtp_ngram 端到端验证 contributor External developers
#7849 opened May 19, 2026 by NKNaN Contributor Loading…
5 tasks done
17
[Cherry-Pick][Feature][Log]console metrics log for pd disaggregation #7843
#7845 opened May 18, 2026 by CSWYF3634076 Collaborator Loading…
5 tasks done
4
[Feature] Add server-level token limits and prompt truncation control
#7842 opened May 18, 2026 by luukunn Collaborator Loading…
3 of 5 tasks
53
[BugFix] Fix attention mask for multimodal models
#7841 opened May 18, 2026 by TBD1 Collaborator Loading…
2 of 5 tasks
5
[PD] PD send cache via storage & Refine swap_cache_layout op
#7839 opened May 17, 2026 by juncaipeng Collaborator Loading…
1 of 5 tasks
61
support MLA overlap-schedule
#7836 opened May 15, 2026 by chang-wenbin Collaborator Loading…
5 tasks
8
Add inner benchmark metrics component
#7831 opened May 15, 2026 by Deleter-D Collaborator Loading…
5 tasks
22
[Cherry-Pick][Loader] Add values natural order check to layers grouped validation
#7822 opened May 14, 2026 by bukejiyu Collaborator Loading…
1 of 5 tasks
9
Revert "[PD] prepare request in prefill instance by multi threads"
#7821 opened May 14, 2026 by Jiang-Jia-Jun Collaborator • Draft
7
[Others] update flash mask version
#7819 opened May 14, 2026 by BingooYang Contributor Loading…
5 tasks done
20
[Feature] GPU Model Runner V1
#7810 opened May 13, 2026 by ming1753 Collaborator • Draft
5 tasks
14
[bugfix] free blocks even if AS write failed
#7807 opened May 13, 2026 by zccjjj Contributor Loading…
5 tasks
15
Triton mla
#7804 opened May 13, 2026 by Linboyan-trc Loading…
58
[Others]Benchmark compare skill contributor External developers
#7803 opened May 13, 2026 by Linboyan-trc Loading…
30
ProTip! Add no:assignee to see everything that’s not assigned.