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
- Fix Kimi K2 thinking model nvfp4 vocab size
- [Feature]: FLASHMLA_SPARSE (SM90/SM100 only) fallback to TILELANG reference kernel (supports ALL)
- [Performance]: DeepSeek-V3.2 on 8xH20 30 decode tokens/sec
- [New Model]: FunAudioLLM/Fun-ASR-Nano-2512
- [Feature]: Models with different quantization for different layers/blocks
- [New Model]: T5Gemma 2
- [Bug]: Incorrect warning message for tensor parallel size in Ray executor (ray_utils.py:331-340)
- [Bug]: FlashInfer Incompatible with Sleep Mode
- [Bug]: Qwen3VL-8B-instruct-FP8 has larger result diff rate than sglang compared with transformers
- Fix formatting of softmax equation in documentation
- Docs
- Python not yet supported