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
- [Bug]: Incosistent logprobs across multiple runs
- [Installation]: `Dockerfile.rocm` requires a torch nightly build that's no longer hosted: requires 2024-07-26, earliest is 2024-08-31.
- [Kernel][ROCm][AMD] fp8 moe configs for MI300X. Mixtral-8x(7B,22B) TP=1,2,4,8
- [Bug]: The Qwen series models produce garbled output when generating long texts.
- [Feature]: host wheel via pypi index?
- [Core] Some performance optimizations
- [Feature]: soft limit-mm-per-prompt for MM OAI API
- [Bug]: Attempting to profile VLLM with TPU errors
- [Feature]: Is it supported Qwen2.5 tool_choice: auto?
- [Usage]: prefix caching support for multimodal models
- Docs
- Python not yet supported