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 supported48 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature Request]: Per-rank log files (especially per-actor for Ray)
- [Bug]: `assert request.num_output_placeholders >= 0` can fail in async scheduling
- [Bug][ROCm]: `vision_embeddings` in transformers inaccurate without math SDP
- blackwell
- fix(gguf): Auto-select compatible dtype for GGUF models on Blackwell
- [Misc] Add JSON format logging support
- [Bug][RL]: Port Conflict
- Starscream Changes to support CPX NPS4
- [Feature]: Add support for fused fp8 output to FlashAttention 3
- [Feature]: Prometheus Metrics Abstraction
- Docs
- Python not yet supported