export CUDA_VISIBLE_DEVICES=0
export PYTHONPATH="/app"
# export VLLM_LOGGING_CONFIG_PATH=/app/logging_config.json
export TZ="Asia/Tehran"



# mkdir -p /app/logs

# sleep 200

text-embeddings-router \
  --model-id /app/data/models/Qwen3-Embedding-0.6B/model \
  --port 8080 \
  --dtype float16 \
  --max-client-batch-size 1024 \
  --max-concurrent-requests 1024 \
  --max-batch-requests 1024 \
  --max-batch-tokens 32768