Skip to content

Pull requests: MooreThreads/vllm-musa

New pull request New
8 Open 90 Closed
8 Open 90 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

MUSA: auto-dispatch FP8 MoE GEMV and GEMM on S5000
#114 opened Jul 21, 2026 by yeahdongcn Collaborator • Draft
9 tasks done
Qwen3.5 moe optimizations
#113 opened Jul 21, 2026 by zichen-kuuga Collaborator Loading…
perf: add fast top-k renormalization on MUSA
#112 opened Jul 20, 2026 by yeahdongcn Collaborator • Draft
perf: add chunked min-p sampling on MUSA
#111 opened Jul 20, 2026 by yeahdongcn Collaborator • Draft
perf: fuse residual RMSNorm and FP8 group quant
#110 opened Jul 20, 2026 by yeahdongcn Collaborator • Draft
perf: fuse SiLU and FP8 group quant before DeepGEMM
#109 opened Jul 20, 2026 by yeahdongcn Collaborator • Draft
Coerce hybrid-model speculative decode off full decode CUDAGraphs on MUSA
#97 opened Jul 12, 2026 by yeahdongcn Collaborator • Draft
5 tasks done
9
Fuse Qwen3 dense-decode q-norm + RoPE into one kernel (opt-in)
#90 opened Jul 6, 2026 by yeahdongcn Collaborator • Draft
6 tasks done
8
ProTip! Follow long discussions with comments:>50.