Skip to content

Pull requests: GeeeekExplorer/nano-vllm

New pull request New
14 Open 30 Closed
14 Open 30 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

增加了MiniCPM4的支持，以及新注册模型的功能
#95 opened Aug 11, 2025 by LDLINGLINGLING Loading…
future: add qwen2 and llama support
#88 opened Jul 28, 2025 by leo-hancock Loading…
[ROCm] add amd gpu guide and performance
#84 opened Jul 25, 2025 by billishyahao Loading…
6
Update README.md to add AMD GPU instructions
#83 opened Jul 25, 2025 by zhangnju Loading…
1
Add comprehensive documentation suite
#75 opened Jul 13, 2025 by hsliuustc Loading…
fix: update can_append and may_append logic for block allocation
#71 opened Jul 6, 2025 by skyloevil Loading…
5
add Qwen2 model support
#70 opened Jul 6, 2025 by Zlzzzupup Loading…
Optimize block management in decode phase
#68 opened Jul 4, 2025 by xiaohajiayou Loading…
2
fix(model_runner): correct position indexing to be 0-based
#67 opened Jul 4, 2025 by PeterDing Loading…
Fix bug in block manager's may_append
#66 opened Jul 3, 2025 by yue-zhang-2025 Loading…
1
Fix: can_append function returns incorrect result
#65 opened Jul 2, 2025 by YjyJeff Loading…
ModelRunner.write_shm(), explicit check for master node
#61 opened Jun 27, 2025 by n1teshy Loading…
Fix: Add device_ids to dist.barrier for robust GPU synchronization
#33 opened Jun 22, 2025 by sjy0727 Loading…
1
Add Serving Benchmark Script
#29 opened Jun 21, 2025 by tiannuo-yang Loading…
2
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.