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 supported14 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: Does vllm support use TokensPrompt for Qwen3VL model
- [Kernel] Mamba2 SSD add fused kernel for 1.5-2.5x SSD (prefill) speedup
- [Frontend] Speed up online server preprocess by using sync tokenizer.
- [RFC]: KV cache layout combining all layers per block
- [Feature] Add MetaShufflingMoE as Optional MoE backend to Llama4 models
- add serving_prefix_hashing
- [build] fix: only build FA3 for Hopper
- [Bug]: `repetition_penalty` leads to engine failure when using vllm serve...
- Normalize OpenPangu RoPE scaling defaults
- [Kernel] Improve 2D Triton Attention Kernel
- Docs
- Python not yet supported