Skip to content

Pull requests: voipmonitor/vllm

New pull request New
11 Open 0 Closed
11 Open 0 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

[SpecDecode][EXL3] deepseek_mtp: normalize rank-sliced weight names (fixes MTP trellis overlay loading)
#11 opened Jul 25, 2026 by malaiwah Loading…
2
[Local] Carry current Triton MLA tuning
#10 opened Apr 22, 2026 by voipmonitor Owner • Draft
[Local] Add PCIe custom allreduce opt-in
#9 opened Apr 22, 2026 by voipmonitor Owner • Draft
[Local] Add seq-length gate for speculative decode
#8 opened Apr 22, 2026 by voipmonitor Owner • Draft
[SpecDecode] Add local argmax helper for Llama Eagle3
#7 opened Apr 22, 2026 by voipmonitor Owner • Draft
[SpecDecode] Add local argmax helpers for Qwen3 drafts
#6 opened Apr 22, 2026 by voipmonitor Owner • Draft
[SpecDecode] Allow draft-specific attention backend and KV dtype
#5 opened Apr 22, 2026 by voipmonitor Owner • Draft
[SpecDecode] Fix async proposer synchronization
#4 opened Apr 22, 2026 by voipmonitor Owner • Draft
[Core] Enable FP8 KV cache with DCP for MLA
#3 opened Apr 22, 2026 by voipmonitor Owner • Draft
Tracking: Kimi MLA upstream split simulation
#2 opened Apr 22, 2026 by voipmonitor Owner • Draft
2
[MTP][Runtime] Reuse draft attention metadata across MTP steps
#1 opened Apr 12, 2026 by voipmonitor Owner Loading…
1
ProTip! Filter pull requests by the default branch with base:main.