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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Latest Nightly build with TurboQuant KV cache crashes on large chunked continuation prefill after workspace lock ( testing PR #39931 implementing TQ on Hybrid Attention Models e.g Qwen3.5-9B)
- [vLLM IR] Nits
- [Bug]: cuda graph capture hipErrorCapturedEvent crash on AMD ROCM when LoRA is enabled
- [New Model]: minicpm-sala
- [Bug]: Unable to start Gemma4 with 2 GPUs
- [Model] Use AutoWeightsLoader for MiMo
- [Usage]: ValueError: mismatch of LoRA layer names for Gemma4 E2B trained with unsloth
- [ROCm] Fix platform detection failures in unprivileged containers
- [ROCm] Add VLLM_SKIP_MM_PROFILING env var as alternative to --skip-mm-profiling
- [ROCm] Fix circular import in GCN arch detection
- Docs
- Python not yet supported