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 supported2 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Misc] guard against change in cuda library name
- [Doc] Add documentation for GGUF quantization
- [Core] simplify logits resort in _apply_top_k_top_p
- [Feature]: Output logps of given output
- [Usage]: doesn't work on pascal tesla P100
- [Bugfix] Handle `best_of>1` case by disabling multi-step speculation.
- fix validation: Only set tool_choice `auto` if at least one tool is provided
- [Core] Allow IPv6 in VLLM_HOST_IP with zmq
- [Frontend] Use MQLLMEngine for embeddings models too
- [Bugfix][Model] enable internvl running with num_scheduler_steps > 1
- Docs
- Python not yet supported