Skip to content

Pull requests: PaddlePaddle/FastDeploy

New pull request New
244 Open 3,836 Closed
244 Open 3,836 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

FA3 support qwen3
#5441 opened Dec 8, 2025 by zhoutianzi666 Loading…
5 tasks
2
Remove CUDA ERROR 9 of inputs of get_padding_offset kernel
#5440 opened Dec 8, 2025 by K11OntheBoat Loading…
5 tasks
3
[PD Disaggregation] Unify the disaggregation info and the pd communication
#5438 opened Dec 8, 2025 by juncaipeng Loading…
5 tasks done
21
[NewFeature]support dynamic load for normal
#5437 opened Dec 8, 2025 by gzy19990617 Loading…
5 tasks
4
[Feature] Support prefill batch inference for pooling models.
#5436 opened Dec 8, 2025 by lizexu123 Loading…
5 tasks
2
Support MXFP4 for GPT-OSS contributor External developers
#5435 opened Dec 8, 2025 by Limerances Loading…
5 tasks
16
[BugFix] [RL] remove shutdown_process_group/restart_process_group for RL
#5433 opened Dec 8, 2025 by liyonghua0910 Loading…
5 tasks
2
[Cherry-Pick][BugFix] 0 not into cuda graph to save memory (#5426)
#5432 opened Dec 8, 2025 by zhoutianzi666 Loading…
5 tasks done
2
[Optimization] compulte real max_logprobs in batch
#5430 opened Dec 8, 2025 by ckl117 Loading…
5 tasks done
5
fix
#5428 opened Dec 8, 2025 by liyonghua0910 • Draft
5 tasks
2
[PD Disaggregation] Decode does not cache requests for preallocating resource in default
#5427 opened Dec 8, 2025 by juncaipeng Loading…
5 tasks done
6
remove add_bias option contributor External developers
#5425 opened Dec 8, 2025 by Limerances Loading…
5 tasks
4
【Feature】support trace part1
#5420 opened Dec 8, 2025 by xiaolei373 Loading…
3 of 5 tasks
2
[BugFix] fix init RequestOutput
#5419 opened Dec 8, 2025 by juncaipeng Loading…
5 tasks done
8
[Feature] Tracing: Fine-Grained Tracing for Request Latency Part1
#5417 opened Dec 7, 2025 by xiaolei373 Loading…
5 tasks
17
[Feature] [PD Disaggregation] simplify configuration for pd-disaggregated deployment, and refactor post-init and usage for all ports
#5415 opened Dec 6, 2025 by liyonghua0910 Loading…
5 tasks
18
【Hackathon 9th Sprint No.60】【RFC】为 FastDeploy 新增支持 DeepSeek 模型的 Reason ing Parser & Tool Parser contributor External developers PaddlePaddle Hackathon
#5412 opened Dec 5, 2025 by fgeygfe Loading…
@luotao1 @LiqinruiG
13
[CI][DEBUG for RL] Lock paddlepaddle-gpu==3.3.0.dev20251203 contributor External developers
#5406 opened Dec 5, 2025 by EmmonsCurse Loading…
5 tasks done
2
[Feature] support stop_token_ids
#5399 opened Dec 5, 2025 by lizexu123 Loading…
5 tasks
7
[XPU] add speculate_step_system_cache XPU
#5397 opened Dec 5, 2025 by RuohengMa Loading…
5 tasks
2
[Optimize][Cherry-pick] Robust stabilty for PD deployment #5338
#5395 opened Dec 5, 2025 by rainyfly Loading…
5 tasks
2
[Scheduler] supports pipeline parallel part 1: basic configuration
#5392 opened Dec 5, 2025 by carryyu Loading…
5 tasks
1
[WIP][Model] support Qwen3-VL model
#5391 opened Dec 5, 2025 by aquagull • Draft
5 tasks
2
[Optim] Improve task-checking performance in engine-worker-queue
#5376 opened Dec 4, 2025 by Jiang-Jia-Jun Loading…
5 tasks
16
[CI] Add error log in run_tests_with_coverage contributor External developers
#5370 opened Dec 4, 2025 by EmmonsCurse Loading…
5 tasks done
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.