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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm] Return Kimi-K3 MLA output directly
- Fix CUDA graph profiling for long GDN warmups
- [ROCm] Skip fresh Kimi-K3 KDA state copies
- [Doc]: recipe for MiniMax-M3- crushes on 8xH200
- [CI/Release] Add XPU wheel release build
- [Bug]: Resumable (realtime) sessions retain raw mm_feature.data for every committed frame → unbounded engine-core host memory
- [Bugfix][Frontend] Coerce non-dict tool_call arguments to `{}` and return 400 on malformed JSON
- fix: Extend Blackwell kernel selection to include SM120 (consumer RTX 5090)
- [ROCm][Bugfix] Split multi-stream launch/sync into CUDA and ROCm platform methods
- [BugFix][Kernel] Pass kv_cache_dtype as int to avoid stable-ABI host leak
- Docs
- Python not yet supported