Skip to content

Pull requests: PaddlePaddle/FastDeploy

New pull request New
430 Open 6,205 Closed
430 Open 6,205 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

[BugFix] Seperate prometheus multiproc dir for single-server multi-dp…
#8062 opened Jun 17, 2026 by liyonghua0910 Collaborator Loading…
5 tasks
5
[XPU][Speculative Decoding] Enable CudaGraph capture for MTP draft model
#8061 opened Jun 17, 2026 by Clarity256 Contributor Loading…
3 of 5 tasks
12
[BugFix] Seperate prometheus multiproc dir for single-server multi-dp services
#8059 opened Jun 16, 2026 by liyonghua0910 Collaborator Loading…
5 tasks
9
swa
#8054 opened Jun 16, 2026 by zhoutianzi666 Collaborator Loading…
5 tasks
4
Support swa mha
#8053 opened Jun 16, 2026 by zhoutianzi666 Collaborator Loading…
5 tasks
5
[Refactor] Remove redundant code in MLA cache management
#8050 opened Jun 15, 2026 by HayzelHan Loading…
5
[Models] Support MLA_SWA functionality
#8049 opened Jun 15, 2026 by chang-wenbin Collaborator Loading…
2 of 5 tasks
10
clean code
#8044 opened Jun 15, 2026 by zhoutianzi666 Collaborator Loading…
5 tasks
6
[XPU] fix_same_req_id
#8040 opened Jun 11, 2026 by cmcamdy Collaborator Loading…
5 tasks
5
Diff kv head
#8037 opened Jun 10, 2026 by chang-wenbin Collaborator Loading…
5 tasks
14
fp8 triton moe config.
#8036 opened Jun 10, 2026 by xuanyuanminzheng Collaborator Loading…
5 tasks
2
support qkdim!=vdim
#8023 opened Jun 8, 2026 by chang-wenbin Collaborator Loading…
5 tasks
16
Jj
#8013 opened Jun 6, 2026 by zhoutianzi666 Collaborator Loading…
5 tasks
8
[CI] DEBUG switch CI test env to new driver
#8007 opened Jun 4, 2026 by EmmonsCurse Collaborator Loading…
2 of 5 tasks
10
Integrate Elastic-Attention (PawQwen3) into FastDeploy
#8001 opened Jun 4, 2026 by tianzhenxu Loading…
27
[Others]Prefill-Decode Batch Invariant in glm
#8000 opened Jun 4, 2026 by bukejiyu Collaborator Loading…
5 tasks
7
[Iluvatar] Support CINN for PaddleOCR-VL by converting max_seqlens to Tensor inputs
#7997 opened Jun 4, 2026 by wuyujiji Contributor Loading…
5 tasks done
20
Fix moe acc
#7988 opened Jun 3, 2026 by BingooYang Contributor 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
[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
[XPU] add as timeout
#7967 opened Jun 2, 2026 by cmcamdy Collaborator Loading…
5 tasks
4
delete useless code
#7959 opened May 29, 2026 by zhoutianzi666 Collaborator Loading…
5 tasks
3
[BugFix] Fix potential Python type error in exception tests. contributor External developers
#7945 opened May 27, 2026 by flsgavin Loading…
5 tasks
4
ProTip! Mix and match filters to narrow down what you’re looking for.