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
- [Bugfix][Quantization] Do not select DeepGEMM with float32 scales on SM12x
- [Test]
- Enable manual fusion in DeepseekV2, Mistral, Qwen2 and Qwen3MoE
- fix: resolve memory accumulation during weight loading
- [Bugfix][Benchmark] Fail streams that end in a server error event
- [Bug][Perf][DSpark] #54674 stacked context WKV regresses TTFT ~3.3% on 2-node DGX Spark (GB10, TP=2), with no decode gain
- [ROCm][DSv4.1][Perf] Read the V4.1 MXFP8 KV record on gfx950
- [Bugfix] Cast the staged-write and bincount row offsets to int64 to avoid an int32 wrap
- [Security] Bound OpenCV video decode frame walks
- [Rust Frontend] Support `--max-log-len`
- Docs
- Python not yet supported