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
- optimizations
- [Usage]: How do I set default temperature for openai compatible server?
- [Feature]: Make `auto` load format handle bitsandbytes models
- [Kernel] Update `cutlass_scaled_mm` to support 2d group (blockwise) scaling
- [Hardware][Gaudi] Support loading checkpoints quantized using Autofp8
- [Usage]: Is there a more refined control method for VLLM caching strategy?
- Updating the high performance vllm docker for AMD Rocm.
- [CI] Add auto update workflow for Dockerfile graph
- [Feature]: Support sigmoid for classification models
- Add `device` as parameter to TP and rotary_embedding functions
- Docs
- Python not yet supported