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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: is vllm support sequence-parallel?
- [Misc]: Does prefix caching work together with multi lora?
- [Usage]: flash_attn vs xformers
- [Installation]: Any plans on providing vLLM pre-compiled for ROCm?
- [Feature][Chunked Prefill]: Enable cuda graph for chunked prefill.
- [Bug]: RuntimeError: Unknown layout
- [Bug]: deepseek-coder-33b-instruct and deepseek-coder-6.7b-instruct broken, but deepseek-llm-7b-chat and deepseek-llm-67b-chat work well
- [Feature]: No `outlines` strong dependency
- [Installation]: import llm meet error
- [Model] Add moondream vision language model
- Docs
- Python not yet supported