vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- add 5090 Triton MoE Config
- Increase robustness for triton moe kernel benchmark to ignore/continue w/ Triton known issue
- fix: the hf3fs_utils in hf3fs_utils.cpp
- Enable CPU_Offload on XPU
- [feat] Add explicit `/start_weight_update` and `/finish_weight_update` APIs for weight transfer
- [Bug] WSL2: Ctrl+C shows shutdown complete but requires pkill -9 (lingering processes)
- [Usage]: The qwen3.5 model generates a random stream of words in thought mode.
- [Bug]: Complex tool json schemas not dereferenced before passing to chat templates
- [ROCm] Fix broken logger.warning and typos in quick_all_reduce
- [Bug]: `--reasoning-parser gemma4` silently disables structured output (xgrammar) when `enable_thinking=false`
- Docs
- Python not yet supported