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]: GPU memory usage is inconsistent with gpu_memory_utilization settings
- [Bug]: RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
- [Feature]: Make a unstable latest docker image
- [Installation]: Compiling VLLM for cpu only.
- Add CD to PyPI
- Add a baseline with dynamic growing KV cache size for the paper
- Support Kuberenetes for Distributed Serving
- Use multi-turn prompts for benchmark_throughput.py
- Update config.py for models which use_dynamic_ntk
- Proposal: Add model registration to support proprietary models
- Docs
- Python not yet supported