Skip to content

Pull requests: PaddlePaddle/FastDeploy

New pull request New
445 Open 6,109 Closed
445 Open 6,109 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

[Metrics] move prompt_tokens_total report to main process
#7983 opened Jun 2, 2026 by liyonghua0910 Collaborator Loading…
5 tasks
[Metrics] move prompt_tokens_total report to main process
#7982 opened Jun 2, 2026 by liyonghua0910 Collaborator Loading…
5 tasks
1
[XPU] limit prefill fetch num
#7981 opened Jun 2, 2026 by cmcamdy Collaborator Loading…
5 tasks
4
upgrade triton moe config.
#7980 opened Jun 2, 2026 by xuanyuanminzheng Collaborator Loading…
5 tasks
5
【cherry-pick】upgrade triton moe config.
#7979 opened Jun 2, 2026 by xuanyuanminzheng Collaborator Loading…
5 tasks
5
debug allreduce fusion acc issue
#7976 opened Jun 2, 2026 by BingooYang Contributor Loading…
5 tasks
3
[Metax][CI]: skip trap asm on MetaX GPU to fix compile error
#7975 opened Jun 2, 2026 by zhang-chenyi Contributor Loading…
5 tasks
2
[Cherry-Pick] 为decode实例增加一个守护线程去监测预分配blocks超时(#7965)
#7973 opened Jun 2, 2026 by CyanScholar Contributor Loading…
5 tasks done
11
[Cherry-Pick][RL][Feature] Add GDR streaming weight update path (#7951)
#7971 opened Jun 2, 2026 by jackyYang6 Contributor Loading…
3 of 5 tasks
13
[SOT] Support flashinfer_allreduce
#7970 opened Jun 2, 2026 by ZhangX-21 Contributor Loading…
5 tasks
6
Revert blockwise CUDAGraph and support piecewise CUDAGraph in prefill
#7969 opened Jun 2, 2026 by ZhangX-21 Contributor Loading…
5 tasks
6
[OP] Remove unused parameters in produce_kv_blockwise
#7968 opened Jun 2, 2026 by zhoutianzi666 Collaborator Loading…
4
[XPU] add as timeout
#7967 opened Jun 2, 2026 by cmcamdy Collaborator Loading…
5 tasks
4
[BugFix] 为decode实例增加一个守护线程去监测预分配blocks超时
#7965 opened Jun 2, 2026 by CyanScholar Contributor Loading…
4 tasks done
13
[Models] add fleet model fallback 2
#7964 opened Jun 2, 2026 by xiaoguoguo626807 Loading…
5 tasks done
14
delete useless code
#7959 opened May 29, 2026 by zhoutianzi666 Collaborator Loading…
5 tasks
3
[Optimization] add warmup for _sample_from_probs
#7956 opened May 29, 2026 by ckl117 Collaborator Loading…
5 tasks
8
Fix score calculation and support neox rope for fleet-gqa-latent
#7952 opened May 28, 2026 by chang-wenbin Collaborator Loading…
5 tasks
5
[RL][Feature] Add GDR streaming weight update path
#7951 opened May 28, 2026 by jackyYang6 Contributor Loading…
3 of 5 tasks
30
[Feature] Support new blackwell decode attention
#7949 opened May 28, 2026 by freeliuzc Collaborator Loading…
5 tasks
12
[BugFix] Fix potential Python type error in exception tests. contributor External developers
#7945 opened May 27, 2026 by flsgavin Loading…
5 tasks
4
[Scheduler] Simplify scheduler for prefill instances
#7944 opened May 27, 2026 by liyonghua0910 Collaborator Loading…
4 of 5 tasks
6
[Feature] Support MegaMoE
#7943 opened May 27, 2026 by Wanglongzhi2001 Collaborator Loading…
5 tasks
12
[Feature]Add output fallback support for OpenAI serving
#7942 opened May 27, 2026 by luukunn Collaborator Loading…
3 of 5 tasks
72
[Cherry-Pick][XPU] Enable CudaGraph capture for MTP draft model(#7864) contributor External developers
#7941 opened May 27, 2026 by Clarity256 Loading…
4 of 5 tasks
17
ProTip! no:milestone will show everything without a milestone.