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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: /inference/v1/generate returns HTTP 200 on internal generation errors instead of 500
- [Bug]: vLLM serving Qwen3.6-27B with multimodal inputs causes InternalServerError due to CUDA OOM despite sufficient GPU memory
- [Bug]: StreamingParserEngine leaks a bare tag fragment (e.g. '<tool_') into content when a PreLexedTerminal supersedes a buffered text-token prefix of the same tag
- fix: resolve silent request skipping in PRIORITY scheduling
- [Misc] Bump `openai` to `>=2.25.0` to support namespace tools types
- [Bug]: Regression ; v0.24.0 -> v0.25.1 / v0.26.0 breaks MinimaxM2.7 TP2 on NVIDIA GH200NVL2
- [Docs] Add macOS/CPU build path to contributing guide
- observability: Make prefix cache hit-rate sliding window size configurable
- [Bug][KV Offload]: failed secondary-tier load livelocks the request — async lookup cache is never invalidated on load failure
- [Model] Honor fp32 head_dtype in Inkling muP logits (target + MTP draft)
- Docs
- Python not yet supported