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
- [Bugfix][Multimodal] Fix PyNvVideoCodec video backend returning NCHW instead of NHWC
- [Bug]: TurboQuant hybrid model crashes at determine_available_memory with 'Unknown cache dtype: auto' on v0.25.0+
- [Bugfix] Preserve non-logitproc entry points in tests
- [ROCm] Enable shared-expert multi-stream overlap on ROCm
- [CI] Prune redundant sequence-parallel test cases
- [Feature]: Follow Up from inital ROCm DI CI enablement PR to break it up into smaller chunks - Use production grade vLLM router in ROCm nightly DI CI instead of "toy proxy"
- [Rust][Benchmark] Support HF ShareGPT datasets in multi-turn mode
- [Bugfix][Frontend] Return 400 for invalid PyNvVideoCodec video input
- [ROCm] Defer `tilelang` import through its import `from vllm.tilelang_utils import tilelang` and relaxed `has_tilelang`
- Feature/zoomkv v020 latest
- Docs
- Python not yet supported