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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Support ViT SP parallelism in the encode section of qwen2.5vl/qwen3vl
- [Refactor] Move MXFP4/MXFP6 logic from fused_experts to Quark
- [Bugfix] interleaved multimodal feature concatenation
- Benchmarks: add receipts harness (telemetry + logs)
- [Feature]: Support Gemma 3 QAT series
- [Bug]: How to Offload KV Cache to CPU without initializing in GPU Memory ?
- [Model] Systematic support for fp32 head, generation models part
- [Bugfix] Fix triton cache path for standalone_compile
- [Core] Remote Instance Model Loader: A loader used to fetch model weights from a ready vLLM instance.
- Flashrl
- Docs
- Python not yet supported