# refer to https://github.com/pytorch/serve/blob/master/docs/configuration.md inference_address=http://0.0.0.0:8080 management_address=http://0.0.0.0:8081 metrics_address=http://0.0.0.0:8082 max_request_size=878837280 max_response_size=878837280 install_py_dep_per_model=true vmargs=-Dlog4j.configurationFile=config_files/log4j2.xml async_logging=true default_workers_per_model=12 number_of_gpu=2 batch_size=2 model_snapshot={\ "yolov5": {\ "1.0": {\ "minWorkers": 12,\ "maxWorkers": 12,\ "batchSize"\: 1,\ }\ } ################### Example ####################### # refer to https://github.com/pytorch/serve/blob/a95ef13eb735efba6168ed485d7ab943f5e65ac3/frontend/server/src/test/resources/snapshots #Saving snapshot #Sun Mar 29 04:53:34 UTC 2020 #inference_address=https\://127.0.0.1\:8443 #default_response_timeout=120 #enable_envvars_config=true #load_models=noop.mar #private_key_file=src/test/resources/key.pem #default_workers_per_model=4 #model_store=../archive/src/test/resources/models #async_logging=true #number_of_gpu=0 #model_snapshot={\n "name"\: "20200329045334828-startup.cfg",\n "modelCount"\: 1,\n "created"\: 1585457614832,\n "models"\: {\n "noop"\: {\n "1.11"\: {\n "defaultVersion"\: true,\n "marName"\: "noop.mar",\n "minWorkers"\: 4,\n "maxWorkers"\: 4,\n "batchSize"\: 1,\n "maxBatchDelay"\: 100,\n "responseTimeout"\: 120\n }\n }\n }\n} #tsConfigFile=src/test/resources/config.properties #max_response_size=2047093252 #max_request_size=2047093252 #unregister_model_timeout=120 #certificate_file=src/test/resources/certs.pem #management_address=https\://127.0.0.1\:8444 #metrics_address=https\://127.0.0.1\:8445 #workflow_store=../archive/src/test/resources/workflows