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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix: use .pop() with default None to avoid KeyError in chat.py (closes #44827)
- [Bugfix] Guard compressed-tensors FP8 KV cache override on SM90+
- Combined configuration of Multi-Token Prediction (MTP), fp8 KV cache, and AITER's Shuffle KV (SKV) layout
- [Kernel] Fuse softmax into grouped_topk CUDA kernel
- [Bugfix][Core][Model] Voxtral realtime: fix boot-OOM / silent-hang / max-len crash on 16 GiB
- [BugFix][Core]: pad placeholder spec tokens for new requests to match CUDA graph shapes
- [Kernel] Fuse per-group FP8 dynamic quant into Triton attention epilogue
- [Bugfix] Avoid racy accepted counts in async spec decode
- [Perf][ROCm] Use CK blockscaled w8a8 gemm for DeepSeek-V3 shapes when on gfx950
- [Bug]: Kimi-k2.6 tool call parser bug when using tool_choice
- Docs
- Python not yet supported