File size: 347 Bytes
ee3af03 |
1 2 3 4 5 6 7 8 |
CUDA_VISIBLE_DEVICES=0 python -m vllm.entrypoints.openai.api_server \
--model /root/autodl-tmp/output_7B_FULL_cotSFT/v0-20250621-230827/Qwen2.5-Omni-7B \
--tokenizer /root/autodl-tmp/output_7B_FULL_cotSFT/v0-20250621-230827/Qwen2.5-Omni-7B \
--dtype bfloat16 \
--host 127.0.0.1 \
--port 8000 \
--gpu-memory-utilization 0.9
|