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
- [Bug]: Port binding keep failing due to unnecessary code
- [Bug]: AttributeError: '_OpNamespace' '_C_cache_ops' object has no attribute 'reshape_and_cache'
- [Feature]: Enabling MSS for larger number of sequences (>256)
- [Feature]: Support custom `max_mm_tokens`
- [Bug]: quantization does not work with dummy weight format
- [Core]: (1/N) Support prefill only models by Workflow Defined Engine - Prefill only scheduler
- [Performance]: phi 3.5 vision model consuming high CPU RAM and the process getting killed
- [Bug]: vLLM OpenAI-api server `/docs` endpoint fails to load
- [Bug]: Extreme low throughput when using pipeline parallelism when Batch Size(running req) is small
- [Bug]: Error Running Qwen2.5-7B-Instruct on CPU
- Docs
- Python not yet supported