File size: 336 Bytes
1482463 |
1 2 3 4 5 6 7 8 9 10 11 |
export ASCEND_RT_VISIBLE_DEVICES=3
export VLLM_USE_V1=1
python -m vllm.entrypoints.openai.api_server \
--model "FreedomIntelligence/openPangu-Embedded-7B" \
--tensor-parallel-size 1 \
--port 8001 \
--host localhost \
--gpu-memory-utilization 0.4 \
--trust-remote-code \
--task embed \
--dtype bfloat16 \ |