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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: GPT-OSS: Unify harmony workflows with other model type workflows
- [Bugfix] Fix step3p5 tool parser and unnecessary unstreamed tool args in serving.
- [Feature]: Make Prometheus histogram buckets configurable
- [Bug]: Qwen3 Next with heterogeneous GPU (FP8 overflow?)
- Add devcontainer configuration file
- [ROCm] [CI] fix test_unrecognized_env (#34350)
- [Bug Fix] Enable non-gated MoE support in Triton backends (#34356)
- fix(exaone4): pad MLP intermediate size for group quant TP alignment
- [DRAFT] Async Allgather
- [Bug]: FP8 MoE Backend Regression: Nemotron-3 Models Fail in vLLM 0.15.0/0.15.1
- Docs
- Python not yet supported