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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature][Profiler] Meta-device operator capture
- [ROCm][Perf] Fold Q fp8 quantization into QkNormRopeKvCacheFusionPass (drop per-layer scaled_quant)
- Check nested JSON schemas in structural_tag for xgrammar support
- [Bugfix][Frontend] Parse split GLM tool-call markers
- [Perf][MRV2] Share GDN, Mamba and Kimi-K3 KDA batch metadata across KV cache groups
- [HiSparse] Allow backing the host KV pool with hugetlbfs
- [Security] Fail EC NIXL reads when the ack block count mismatches
- [Test] Cover aligned Mamba state-index kernel invariants
- [Security] Do not abort the engine when a producer request has no disagg spec
- [Kimi-K3][ROCm] AttnRes: runtime strides, packed D loads, and per-phase launch tuning
- Docs
- Python not yet supported