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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Model] Fix Qwen3-Omni crash when audio and image coexist in interleaved path
- [Model] Enable tower/connector LoRA for Qwen2-Audio via a native audio encoder
- [Bug]: thinking_token_budget not enforced on re-entry after natural </think>
- [Bugfix] Fix thinking_token_budget not enforced after natural </think> re-entry
- [Bugfix][Kernel][ROCm] Fix Wave32 LDS overflow in top-k merge launch
- [Bug]: [quantization] The Qwen3 4B model quantized for vLLM inference encounters errors.
- fix: update engine_kwargs for DeepSeek-V4-Pro compatibility in Ray example (closes #44949)
- [Bugfix] Use native SiLU activation in CPU fused MoE
- [Features] [Model Runner V2] Add Orthrus speculative decoding support
- [Attention Backend] add HPC-Ops Attention backend
- Docs
- Python not yet supported