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
- [Kernel] Support Nvfp4 Cutedsl Moe Swiglu-oai and Relu2(non-gated) Activation
- Bump actions/setup-python from 6.1.0 to 6.3.0
- [Frontend] Enforce max_tool_calls for Responses built-in tools
- [Bugfix] Fix misclassification of prefill as uniform decode for hybrid models
- [Quantization][Autoround][XPU] Add W4A16(moe) / MXFP4(linear/moe) Support
- [Bug]: DiffusionGemma fails to start with RuntimeError in _compiled_sample_step during torch.compile (matmul shape mismatch)
- Topk softplus sqrt
- [XPU][DeepSeekV4] Dispatch MXFP4 compress kernel to SYCL on XPU
- Gemma-4-26B-A4B-NVFP4 + MTP4 is slower on v0.23.0 than v0.21.0 on RTX PRO 6000 Blackwell
- [Doc] Add Tigris example to S3-compatible object store section
- Docs
- Python not yet supported