Skip to content

Pull requests: PaddlePaddle/FastDeploy

New pull request New
164 Open 2,816 Closed
164 Open 2,816 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 bugs of splitwise_complete_prefilled_step IPCsignal clear
#4309 opened Sep 28, 2025 by K11OntheBoat Loading…
1
[BugFix] Send all token include empty result to Adapter
#4308 opened Sep 28, 2025 by Jiang-Jia-Jun Loading…
1
[feature]2.2 custom_allreduce support cudagraph recapture
#4307 opened Sep 28, 2025 by ckl117 Loading…
2
[NewFeature]custom_allreduce support cudagraph recapture
#4305 opened Sep 28, 2025 by ckl117 Loading…
4
【fix】Remove the logic that assigns the default value of 80% to reasoning_max_tokens in the offline component of FastDeploy
#4304 opened Sep 28, 2025 by kxz2002 Loading…
1
[Feature]add model status contributor External developers
#4302 opened Sep 28, 2025 by luukunn Loading…
1
dummy run
#4301 opened Sep 28, 2025 by lizexu123 Loading…
1
Simplify CUDAGraph creation logic
#4298 opened Sep 26, 2025 by yuanlehome Loading…
[pooling]Fix weight loading for st_projector in embed models
#4297 opened Sep 26, 2025 by bukejiyu Loading…
3
[Feature] update mm chunked_prefill op
#4293 opened Sep 26, 2025 by TBD1 Loading…
supports spec dynamic cfp8
#4290 opened Sep 26, 2025 by carryyu Loading…
Test cov report v2
#4288 opened Sep 26, 2025 by XieYunshen Loading…
[Feat] Add draft_logprobs for Speculative Decode MTP
#4287 opened Sep 26, 2025 by sunlei1024 Loading…
[BugFix] Clear request
#4285 opened Sep 26, 2025 by ltd0924 Loading…
1
【Hackathon 9th No.79】功能模块 fastdeploy/entrypoints/openai 单测补充 contributor External developers PaddlePaddle Hackathon
#4281 opened Sep 26, 2025 by playasdw Loading…
@luotao1 @ltd0924
4
Optimizing the performance of think length limit using custom operators
#4279 opened Sep 25, 2025 by yuanlehome • Draft
1
[BUG] fix ep bug
#4275 opened Sep 25, 2025 by kevincheng2 Loading…
1
【feature】support n parameter contributor External developers
#4273 opened Sep 25, 2025 by kxz2002 Loading…
10
【New Feature】W4afp8 supports per group quantization
#4272 opened Sep 25, 2025 by yangjianfengo1 Loading…
Temp PR, DO NOT MERGE (support mtp logprob)
#4269 opened Sep 25, 2025 by Deleter-D Loading…
add release images build job contributor External developers
#4265 opened Sep 25, 2025 by XieYunshen Loading…
1
【Inference Optimize】support mla cache buffer
#4261 opened Sep 25, 2025 by chang-wenbin Loading…
1
[Executor]CUDAGraph support Speculate Decode contributor External developers
#4258 opened Sep 25, 2025 by littledgg Loading…
1
【Hackathon 9th No.86】Integrate append_attention kernel template_instantiation -part contributor External developers PaddlePaddle Hackathon
#4256 opened Sep 24, 2025 by ccsuzzh Loading…
@luotao1
1
[Cherry-Pick][BugFix]fix the bug for prefilled_step_idx signal of cache_messager in cudagraph and PD
#4252 opened Sep 24, 2025 by zeroRains Loading…
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.