Skip to content

Pull requests: PaddlePaddle/FastDeploy

New pull request New
283 Open 4,225 Closed
283 Open 4,225 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

[OPs] ep_moe_expert_dispatch.cu dispatch num_experts_per_rank 5
#5890 opened Jan 5, 2026 by yuanlehome Loading…
5 tasks
4
[Cherry-Pick][OPs] ep_moe_expert_dispatch.cu dispatch num_experts_per_rank 5
#5889 opened Jan 5, 2026 by yuanlehome Loading…
5 tasks
2
【BugFixfix】Adapt to hadamard_block_size
#5888 opened Jan 5, 2026 by lizexu123 Loading…
5 tasks
2
support attention tp
#5887 opened Jan 5, 2026 by zhoutianzi666 Loading…
5 tasks
2
[Speculative Decoding]Support multi-step mtp with cudagraph
#5886 opened Jan 5, 2026 by freeliuzc Loading…
5 tasks
12
[Cherry-Pick] [BugFix] fix mtp cache attaching for pd disaggregation (#5884)
#5885 opened Jan 5, 2026 by liyonghua0910 Loading…
5 tasks
2
[BugFix] fix mtp cache attaching for pd disaggregation
#5884 opened Jan 5, 2026 by liyonghua0910 Loading…
5 tasks
2
[Feature] add golang router contributor External developers
#5882 opened Jan 5, 2026 by mouxinqq Loading…
5 tasks
2
[BugFix][Cherry-Pick] Cp fix eb5 prefix cache(#5879)
#5881 opened Jan 5, 2026 by kevincheng2 Loading…
5 tasks
2
[Optimization] Accelerate Qwen3 QK RMSNorm via Fused Triton Kernel
#5880 opened Jan 5, 2026 by Sunny-bot1 Loading…
5 tasks done
2
[BugFix] fix eb5 prefix bug
#5879 opened Jan 5, 2026 by kevincheng2 Loading…
5 tasks
2
[XPU] move xpu_attn_backend.py to FastDeploy/fastdeploy/model_executor/layers/backends/xpu
#5878 opened Jan 5, 2026 by zccjjj Loading…
5 tasks
2
[Metax] optimize flash attention backend contributor External developers
#5876 opened Jan 5, 2026 by neilzhuu Loading…
5 tasks
3
[KVCache] launch cache transfer processes only if hierarchical cache or kv cache storage is enabled
#5871 opened Jan 5, 2026 by liyonghua0910 Loading…
5 tasks
2
[XPU]xpu support ep4tp1 in pd disaggregation
#5860 opened Jan 4, 2026 by ddchenhao66 Loading…
5 tasks
3
[Cherry-Pick] [KVCache] launch cache transfer processes only if hierarchical cache or kv cache storage is enabled (#5871)
#5859 opened Jan 4, 2026 by liyonghua0910 Loading…
5 tasks
2
[Intel HPU] enable MoE EP for hpu contributor External developers
#5855 opened Jan 4, 2026 by yanfeich Loading…
2 tasks
10
[Optim] When the token is small, use a gemm with a smaller N
#5853 opened Jan 4, 2026 by yangjianfengo1 Loading…
5 tasks
2
[XPU]Cherry-pick Support ZMQ logprobs
#5852 opened Dec 31, 2025 by iosmers Loading…
5 tasks
2
[Cherry-Pick][Feature] support rl_tp_degree(#5850)
#5851 opened Dec 31, 2025 by lizhenyun01 Loading…
5 tasks
1
[Feature] support rl_tp_degree
#5850 opened Dec 31, 2025 by lizhenyun01 Loading…
5 tasks
1
[Graph Optimization] Wrap m_grouped_gemm_fp8_fp8_bf16_nt_contiguous as custom pyop
#5847 opened Dec 31, 2025 by DrRyanHuang Loading…
5 tasks done
3
[Feature] get_output_kv_signal blocking read mode & send_first_token
#5836 opened Dec 30, 2025 by ST-XX Loading…
5 tasks done
2
[Cherry-Pick][Optimization]Decode attention support(#5767)
#5833 opened Dec 30, 2025 by lizhenyun01 Loading…
5 tasks
6
[BugFix] Fix redundant prompt_logprobs in the second chunk of streaming response when return_token_ids is enabled for v1/completions and fix trace file name
#5829 opened Dec 30, 2025 by qwes5s5 Loading…
5 tasks
3
ProTip! Exclude everything labeled bug with -label:bug.