forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 10
Pull requests: MooreThreads/vllm-musa
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix(musa): fix Qwen Eagle3 Gumbel RNG bitcast
#204
opened Aug 28, 2026 by
zichen-kuuga
Collaborator
Loading…
perf(musa): select AOT and JIT tiles by active MP
#202
opened Aug 28, 2026 by
yeahdongcn
Collaborator
•
Draft
[Model] Enable Qwen3.8-Flash-Next on MUSA
#200
opened Aug 27, 2026 by
Joey-gvwal
Collaborator
•
Draft
perf(musa): tune fused MoE dispatch by active MP and graph bucket
#193
opened Aug 25, 2026 by
yeahdongcn
Collaborator
•
Draft
10 of 11 tasks
[Draft] feat(musa): unify RuntimePlan and add in-tree engine autotuning
#185
opened Aug 17, 2026 by
yeahdongcn
Collaborator
•
Draft
Port DeepSeek-V4 optimization PR #174 to v0.26 and fix MTP multi-batch Graph staging
#178
opened Aug 11, 2026 by
Joey-gvwal
Collaborator
Loading…
MUSA: switch Ubuntu 22.04 image to system Python 3.12
#119
opened Jul 24, 2026 by
yeahdongcn
Collaborator
•
Draft
ProTip!
Updated in the last three days: updated:>2026-08-25.