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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [CI] Allow empty final audio streaming chunk
- [Bug]: Long term continuous operation leads to an increase in model output illusion
- [Rust Frontend][RFC] Add Qwen3-ASR WebSocket `/v1/realtime`
- [Rust Frontend] Resumable streaming sessions in engine-core-client and Llm facade
- [Feature]: Optional torch.compile support for NVIDIA DeepSeek-V4
- [Perf] Indexer score GEMM uses fp32 accumulate on DeepSeek-V4; bf16 may be sufficient
- [Bugfix][Distributed] Gate MNNVL allreduce workspace creation on fabric support
- [Bug]: Qwen3.5-family native MTP crashes with compressed-tensors WNA16 checkpoints (unquantized mtp.fc)
- [Docs] Explain how to measure prefix cache effectiveness
- [Docs] Add Qwen3-0.6B to batch invariance tested models
- Docs
- Python not yet supported