| #!/bin/bash | |
| # Start the local Mongo database | |
| mongod & | |
| # Start the text-generation-inference process | |
| text-generation-launcher --model-id ${MODEL_NAME} --num-shard 1 --port 8080 --trust-remote-code --shard-uds-path /tmp/text-generation-model-a --master-port 25000 --cuda-memory-fraction 0.5 & | |
| text-generation-launcher --model-id HuggingFaceH4/starcoder2-15b-dpo-v40-deploy --num-shard 1 --port 8081 --trust-remote-code --shard-uds-path /tmp/text-generation-model-b --master-port 25001 --cuda-memory-fraction 0.5 & | |
| # Wait for text-generation-inference to start | |
| curl --retry 60 --retry-delay 10 --retry-connrefused http://127.0.0.1:8080/health | |
| # Start the chat-ui process | |
| pm2 start /app/build/index.js -i $CPU_CORES --no-daemon & | |
| # Wait for any process to exit | |
| wait -n | |
| # Exit with status of process that exited first | |
| exit $? |