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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: prefix cache bug happens when use w4a16 for GLM5
- [Fix] always use loopback ip for `UniProcExecutor`
- feat(dcp, flashinfer): support FULL_DECODE_ONLY for flashinfer with DCP>1
- [Kernel] Add swap AB optimization to fused_moe_kernel
- [ROCm] Add AITER fused decode kernel for MLA attention
- Guard AWQ-Marlin auto-selection on CUDA driver/toolkit mismatch
- [Models] Align nemotron-nano-vl's `audio_in_video` processing
- [ROCm][Quantization] improve quant dtype parser robust for W4A8
- [Bugfix] Fix prefix caching for hybrid models with non-uniform page sizes
- fix mtp launch error in vllm-0.17.1-rc, about cuda graph during memory profile
- Docs
- Python not yet supported