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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: [CI] wheels released for CPU cannot be installed with `uv pip install`
- [Bug]: Qwen3-Omni/ASR audio encoder skips quant_config, host-syncs chunk metadata, and replicates the tower when heads are not divisible by TP
- [Feat][1/2] Add Transformers TPSP dense baseline support
- [Bugfix][Multimodal] Match mistral_common's EXIF handling for mistral-tokenizer models
- [Bugfix] Respect root_path when formatting Cohere errors
- [Bugfix][NIXL] Fix host-buffer P/D for hybrid Mamba models
- [Bug][Rust Frontend] /v1/completions rejects an array of prompts
- [Bug]: CPU build fails with 'Torch not compiled with CUDA enabled' in gumbel_sample when an NVIDIA driver is visible (e.g. WSL2)
- [Model][Hardware][AMD] Use AITER Gluon MLA for Small FP8-KV Decode Batches
- [Bugfix][Rust Frontend] Support batch prompts in completions
- Docs
- Python not yet supported