generator_server.sh

export ASCEND_RT_VISIBLE_DEVICES=1 
export VLLM_USE_V1=1
python -m vllm.entrypoints.openai.api_server \
    --model "FreedomIntelligence/openPangu-Embedded-7B" \
    --tensor-parallel-size 1 \
    --port 8000 \
    --host localhost \
    --trust-remote-code \
    --dtype bfloat16 \
    --gpu-memory-utilization 0.90 \