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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [XPU] use xpu topk topp sample kernel
- [Feature]: Support routed_experts export in disaggregated Prefill/Decode serving
- feat: skip-softmax support for FlashInfer attention path
- [Feature]: Use torch.compile Dynamo to see full trace for model forward pass
- [Perf] Downgrade mxfp4 triton_kernels to 3.5
- Fix fp8_e5m2 KV cache blocked for AWQ/GPTQ models
- [vLLM IR][RMSNorm] Port Mixer2RMSNormGated to vLLM IR Ops
- [Model Runner V2] Skip draft propose for disagg prefill instance
- [ROCm][Perf] Add Fused Shared Expert (FSE) support for Qwen3-Next
- fix: minor fixes in preparation for #36786
- Docs
- Python not yet supported