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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Cleanup] Unify vllm.utils.flashinfer and flashinfer_utils
- [Bugfix] Fix Qwen3 context length limited to sliding_window when use_sliding_window=False
- [Bugfix] Fix negative local_cache_hit in P/D disaggregation metrics
- [Frontend, grpc] add support for Embed RPC in grpc_server
- Fix DeepSeek-OCR tensor validation for all size variants
- [Docs] Clean up speculators docs
- Add validation to reject non-text content in system messages
- [BUGFIX] Fix accuracy bugs in Qwen3-Next MTP
- Move the Python kernel abstraction package (selectors + interfaces) under `vllm/model_executor` so unquantized linear kernels don’t need to be referenced from a quantization-specific directory.
- [Bug]: vLLM crashes when trying to load Devstral-2-123B-Instruct-2512 directly from S3
- Docs
- Python not yet supported