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] Restore unloaded FP8 scale params during layerwise reload
- [CI] Add test suite for PoolsideV1ToolParser
- [ROCm] Convert MXFP8 MoE weights to block FP8 on gfx94x
- [Quantization] Extend ModelOpt mixed precision and NVFP4 runtime formats
- [Bugfix] Invalidate CPU metadata shadows after query extension
- [Bug]: Qwen3.6 27B pd disagg failed
- [fuse_norm_quant] Support mixed input/weight dtype in fused RMSNorm+FP8 quant kernels (fixes Qwen3.5-FP8)
- [DiffusionGemma-26B-A4B-it][XPU] Fix DiffusionGemma for TP>1 and enable XPU
- [Tracking] Enable MiMo-V2.5-Pro-FP4 with DFlash speculative decoding
- [DiffusionGemma-26B-A4B-it FP8][XPU][Quant] Enable native XPU FP8 MoE for per-token dynamic activations
- Docs
- Python not yet supported