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 supported50 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: DecodeBenchConnector repeats KV cache fills for shared state tensors at large batch sizes
- [Kernel][Qwen] Tune the SM103 MoE router skinny GEMM
- [Bugfix][LoRA] Handle leading missing packed groups
- [Bug]: A weight update issued while the engine is asleep segfaults the EngineCore instead of being rejected
- [Perf] Use custom all-gather for full-vocabulary logits
- [ROCm][Perf] MXFP8 K-loop mask and activation sharing for DeepSeek-V4.1-Flash on gfx950
- [ROCm][Perf] Candidate-only MQA scorer for DSA sparse indexer prefill on gfx950
- [ROCm][Perf] Candidate-only paged MQA scorer for DSA sparse indexer decode on gfx950
- [ROCm][Perf] Fuse indptr prefix sum into DSA decode pack kernel for DeepSeek-V4.1-Flash
- [Bugfix][ROCm] Avoid RowWise FP8 scaled MM on RDNA4
- Docs
- Python not yet supported