You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
The text was updated successfully, but these errors were encountered:
Your current environment
export CUDA_VISIBLE_DEVICES=2,3 && vllm serve QwQ-32B
--dtype half
--tensor-parallel-size 2
--cpu-offload-gb 1
--gpu-memory-utilization 0.9
--port 9000
指定了GPU为2和3,但是启动模型依旧选择了0显卡,vllm版本0.7.2
🐛 Describe the bug
export CUDA_VISIBLE_DEVICES=2,3 && vllm serve QwQ-32B
--dtype half
--tensor-parallel-size 2
--cpu-offload-gb 1
--gpu-memory-utilization 0.9
--port 9000
指定了GPU为2和3,但是启动模型依旧选择了0显卡,vllm版本0.7.2
Before submitting a new issue...
The text was updated successfully, but these errors were encountered: