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]: EAGLE-3 + prompts >2048 tokens: device-side assert (Triton `index < 2048`) in inductor-compiled eagle_head kernels; eager works, cudagraph_mode=NONE still crashes (v0.24.0)
- [Attention] Add direct symmetric-memory DCP A2A
- [Frontend][Core][Spec Decode] Per-request acceptance stats in OpenAI API responses
- [ROCm] Support MiniMax-M3 NVFP4 SwiGLU-OAI
- [ROCm][Quark][7/N] Use MXFP4 linear kernel abstraction for `emulation` backend
- Add pushed-based ZMQ metrics logger support
- [ROCm] DeepSeek-V4-Pro PD Disaggregation through MORI IO KV Connector on AMD GPUs
- [ROCm][Bugfix] Fix Triton W4A16 bug in determining if transpose is required for GPTQ/AutoGPTQ
- [Bug]: Speculative Decoding + Structured Output(tool call)组合下,decode 阶段出现秒级卡顿
- [Feature]: nvfp4 KV cache on SM120 — flashinfer ships the kernels, vLLM isn't wired to them (working prototype, 245K ctx on a 5090)
- Docs
- Python not yet supported