Skip to content

Pull requests: UbiquitousLearning/mllm

New pull request New
10 Open 474 Closed
10 Open 474 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

Add compressed-tensors Marlin support for Qwen3-VL AWQ in pymllm
#663 opened Apr 5, 2026 by jialilve Loading…
11
Added Qwen3.5 0.8B
#657 opened Mar 22, 2026 by FarmersWrap • Draft
14
fix(pymllm): fix RadixCache evictable size accounting bug
#656 opened Mar 20, 2026 by FarmersWrap Loading…
1 of 2 tasks
16
fix(pymllm): reduce scheduler CPU busy-loop from 100% to ~2% during decode
#655 opened Mar 20, 2026 by FarmersWrap Loading…
4 tasks done
15
feat: add probing service and update mobile adapter
#652 opened Mar 14, 2026 by yuerqiqi Loading…
8
feat(kernel): add vocab embedding CUDA kernels
#645 opened Mar 2, 2026 by huangzhenhua111 Loading…
1
feat(benchmark): Add CPU benchmark tool with context length sweep
#639 opened Feb 14, 2026 by huangzhenhua111 Loading…
46
feat : Add Support of Qwen2.5Omni Model and MiniCPM-o-4_5 Model
#612 opened Jan 23, 2026 by KKkai0315 Loading…
43
feat: add support of internlm2.5-1.8B-chat model
#515 opened Nov 12, 2025 by Sp0tless Loading…
9
fix small bugs with run_qwen_npu.sh.
#295 opened Jun 12, 2025 by yinrun Loading…
ProTip! Exclude everything labeled bug with -label:bug.