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 supported4 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature] [Spec Decode]: Simplify the Use of Eagle Spec Decode
- [RFC]: Pipeline-Parallelism for vLLM V1
- [Feature]: Support for serving two llms at the same time
- [Bug]: The random seed behavior when loading a model in vLLM is confusing.
- [V1] Add prefix caching hit rate
- [Ignore] Test
- [Misc] Add helpers to get pipeline rank & world size
- [Bug]: How to run LanguageBind/Video-LLaVA-7B-hf
- [WIP] [V1] TPU support
- [V1][WIP] Hybrid allocator for full attention & sliding window attention interleaved models (Reference PR, do not merge)
- Docs
- Python not yet supported