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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [feat]Add SLO-aware scheduling policy
- fix(security): enforce prompt-count bound on pooling and scoring routes
- [Bug]: `prompt_logprobs` silently corrupted for some requests when MTP speculative decoding is enabled (Qwen3.5-family, chunked prefill; two builds, two checkpoints)
- docs: add GPU architecture compatibility matrix and expand KServe integration guide
- [Bugfix] Support NVIDIA short-form UUID in CUDA_VISIBLE_DEVICES (#51677)
- [Frontend] Optional post-generation hook on EndpointPlugin
- [ROCm] DeepEP: configurable dispatch timeouts, deferred legacy annotations
- [Bug]: `--reasoning-parser qwen3` returns the whole answer as `reasoning` (content=null) when the prompt already closes the think block but `enable_thinking` was not passed via chat_template_kwargs
- [New Model]: TR-HASH deterministic token-routed MoE
- Explore topK overflow/non-determinism
- Docs
- Python not yet supported