Skip to content

Pull requests: PaddlePaddle/FastDeploy

New pull request New
23 Open 1,513 Closed
23 Open 1,513 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

【Fix】sync paddlenlp_ops build use_fast_math
#2823 opened Jul 12, 2025 by gzy19990617 Loading…
1
【Fix】sync paddlenlp_ops build use_fast_math
#2821 opened Jul 12, 2025 by gzy19990617 Loading…
1
[Feature] Add DeepGEMM pre-compile tools. contributor
#2819 opened Jul 11, 2025 by Deleter-D Loading…
1
[Perf][MTP] Improve speculative decoding efficiency
#2818 opened Jul 11, 2025 by freeliuzc Loading…
1
[BugFix] support prompt repetition_penalty
#2806 opened Jul 10, 2025 by ming1753 Loading…
1
Fixed the garbled text issues in Qwen3-8B
#2782 opened Jul 9, 2025 by lizexu123 Loading…
Logprob contributor
#2775 opened Jul 9, 2025 by zhenwenDang Loading…
2
[SOT] Mark dynamic dims by type annotations
#2771 opened Jul 9, 2025 by SigureMo • Draft
1
Simplify the Config code
#2770 opened Jul 9, 2025 by YuanRisheng Loading…
24
[Docs] Optimal Deployment
#2768 opened Jul 9, 2025 by ming1753 Loading…
4
[Feature] support c16 prefix_cache in flash_attention_v3
#2766 opened Jul 9, 2025 by lizhenyun01 Loading…
5
[Feature] mm and thinking model support structred output
#2749 opened Jul 8, 2025 by kevincheng2 Loading…
5
Opt wint2
#2741 opened Jul 8, 2025 by baoqiwen Loading…
1
[draft] change rejectionsampling topk=40
#2734 opened Jul 7, 2025 by vivienfanghuagood Loading…
1
Support use safetensors with paddle.MmapStorage to load model files contributor
#2730 opened Jul 7, 2025 by zeroRains Loading…
2 tasks
2
[Stop Sequences] support stop sequences
#2712 opened Jul 4, 2025 by zoooo0820 Loading…
2
[feat]add loadtimequantization modelloader
#2711 opened Jul 4, 2025 by bukejiyu Loading…
2
Add with_output version AppendAttention contributor
#2694 opened Jul 3, 2025 by Lmywl Loading…
2
update iluvatar gpu fastdeploy whl
#2674 opened Jul 2, 2025 by yongqiangma Loading…
1
[WIP] optimzie wint2 moe_group_gemm.
#2661 opened Jul 1, 2025 by Xreki Loading…
1
Add maca platform contributor
#2648 opened Jun 30, 2025 by gfxdev8 Loading…
2
add marlin moe wint4 contributor
#2629 opened Jun 18, 2025 by RbRe145 Loading…
3
Wint4 contributor
#2628 opened Jun 18, 2025 by RbRe145 Loading…
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.