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
- [Bug]: vLLM (TP=8) on 235B model triggers "CUDA error: unspecified launch failure" and persistent "ERR!" state in nvidia-smi
- [Usage]: how to pass multi turn multimode messages to Vllm?
- [Bug]: Crashing when use PIECEWISE compilation
- [Bug]: Low GPU utilization with Embedding Model
- [Bug]: Llama-3.2-1b-instruct prepending extra bos token
- [Bug]: NaN's in MLA with chunked-prefill
- [Bug]: Qwen 3 MOE support on GH200
- [Usage]: `add_vision_id` ignored for Qwen 2.5-VL-32B-Instruct
- [Bug]: Value error, Found conflicts between 'rope_type=default' (modern field) and 'type=mrope'
- [Bug]: vllm0.10.1 can deploy deepseek-70b model with tp=2 and max-model-len 20000 on the machine with two NVIDIA A800(80GiB) , But vllm 0.11.0 failed
- Docs
- Python not yet supported