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 supported25 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Revert "Bug/test eagle dp v0" (#38938)
- [Feature]: vllm 的 api 添加支持 ollama 的风格
- [Bug]: Qwen3Coder tool parser crashes on malformed <parameter=...> (ValueError: substring not found)
- [Bugfix] Skip malformed parameters in qwen3coder tool parser
- [Bug]: Inference qwen3.5 with tensor-parallel-size>1, RuntimeError: NCCL error: unhandled system error
- [Bug]: ReRank API online inference doesn't work well with given template
- [Bug]: prefix_caching_hash_algo="xxhash" silently returns empty outputs when xxhash not installed
- [Performance]: Significant TTFT Regression with Speculative Decoding (EAGLE3)
- [CI Failure]: LoRA TP (Distributed) _get_lora_aux_cuda_stream is not defined
- [Bug]: FlashInferFP8ScaledMMLinearKernel segfaults on Blackwell (sm100)
- Docs
- Python not yet supported