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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- WIP - Paged Eviction
- [RFC]: Sampling Optimization: move gather of logits after argmax.
- [Feature]: Make EngineCore shutdown timeout configurable via environment variable
- [Feature]: Use Kimi to support to deploy fp8 model in 8xA100-PCIE-40GB GPU
- [New Model]: Support T5Gemma
- [Feature][Cleanup]: Unify `vllm.utils.flashinfer` and `vllm.model_executor.layers.quantization.utils.flashinfer_utils`
- [CI/Build] Add source build test to catch build failures early
- [Feature]: GLM 4.7 vocab padding feature
- [Bug]: GPT-OSS-120b giving incomplete responses with gibberish \xa0\u200b ending characters
- [CI] Add sm_110 to aarch64 CUDA 13.0 builds
- Docs
- Python not yet supported