run.sh

#!/bin/sh


printf "Running vLLM OpenAI compatible API Server at port %s\n" "7860"

#python -u /app/openai_compatible_api_server.py \
#    --model meta-llama/Llama-3.2-3B-Instruct \
#    --revision 0cb88a4f764b7a12671c53f0838cd831a0843b95 \
#    --host 0.0.0.0 \
#    --port 7860 \
#    --max-num-batched-tokens 32768 \
#    --max-model-len 32768 \
#    --dtype half \
#    --enforce-eager \
#    --gpu-memory-utilization 0.85


python -u /app/openai_compatible_api_server.py \
    --model sail/Sailor-4B-Chat \
    --revision 89a866a7041e6ec023dd462adeca8e28dd53c83e \
    --host 0.0.0.0 \
    --port 7860 \
    --dtype half \
    --enforce-eager \
    --gpu-memory-utilization 0.85