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
- [Bug]: Mixed prompt embedding masks are omitted from prefix cache keys, causing incorrect outputs
- [Bug]: Qwen parser discards prose and final answers after a literal <tool_call> marker
- [Bugfix][Kernel] Honor leading strides in SM120 blockwise FP8 GEMM
- Enable ModelOpt FP8 on SM75
- [Bugfix][Parser] Preserve literal Qwen tool markers and following answers
- [Bugfix] Buffer and validate provisional DSML tool-call recovery (#56482)
- [Core] Implement kv compression algorithms
- [ROCm] Fuse RMSNorm into MXFP8 activation quant on CDNA4
- fix(bench): use half-open intervals for peak concurrency
- [ROCm][CI] Stage H multi-GPU and MI250 gating
- Docs
- Python not yet supported