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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Kernel] Multi-LoRA MoE CUDA BGMV kernel
- [vLLM IR] Support optional output tensor in dynamic_group_quant_fp8 and refactor legacy calls
- [Core/IR] Migrate per_token_group_quant_fp8 to standardized IR Op
- [Bugfix] Fix forced tool_choice crash when reasoning_parser consumes all content
- [RFC]: Hybrid checkpoint ABI for non-KV prefix resume
- [Bug]: Weight loading for meta-llama/Llama-4-Scout-17B-16E-Instruct is extremely slow
- [Feature]: Support iterative in-place weight editing on TP workers (online RLHF / steering / abliteration)
- Auto enable pdl
- [Perf] Apply PDL optimization
- [Bug]: qwen3.5 can not use --decode-context-parallel-size with --enable-prefix-caching
- Docs
- Python not yet supported