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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [ROCm] Enable AITER fused allreduce + RMSNorm compilation pass
- Fix autotuned config selection for active LoRA & LoRA CUDA Graph Memory Reduction
- fix: clean shutdown for AR Fusion workspace on ctrl-c
- [Core] Decouple draft-token hook from speculative decoding
- fix: register atexit handler to prevent ImportError during FlashInfer shutdown
- [Bugfix][ROCm] full graph capture on triton-attn fix - Option1
- [Bugfix] Fix KV-cache head-of-line blocking in scheduler
- fix: handle model validation error in realtime WebSocket session.update
- fix: guard against ZeroDivisionError in layerwise profiler
- tests(v1): cover parallel sampling output_kind matrix for AsyncLLM and LLMEngine
- Docs
- Python not yet supported