I0616 20:01:51.720363 1 config.go:602] "Configuration:" =< { "IP": "10.132.0.48", "PodName": "premium-simulated-simulated-premium-kserve-6cfb9f9b9c-52d8q", "PodNameSpace": "llm", "VllmDevMode": false, "block-size": 16, "data-parallel-rank": -1, "data-parallel-size": 1, "dataset-in-memory": false, "dataset-path": "", "dataset-table-name": "llmd", "dataset-url": "", "default-embedding-dimensions": 384, "ec-transfer-config": "", "enable-kvcache": false, "enable-prefix-caching": false, "enable-request-id-headers": false, "enable-sleep-mode": false, "enforce-eager": false, "event-batch-size": 16, "failure-injection-rate": 0, "failure-types": null, "fake-metrics": null, "fake-metrics-refresh-interval": 100000000, "global-cache-hit-threshold": 0, "hash-seed": "", "inter-token-latency": 0, "inter-token-latency-std-dev": 0, "kv-cache-size": 1024, "kv-cache-transfer-latency": 0, "kv-cache-transfer-latency-std-dev": 0, "kv-cache-transfer-time-per-token": 0, "kv-cache-transfer-time-std-dev": 0, "latency-calculator": "", "lora-modules": null, "max-cpu-loras": 1, "max-loras": 1, "max-model-len": 1024, "max-num-seqs": 5, "max-tool-call-array-param-length": 5, "max-tool-call-integer-param": 100, "max-tool-call-number-param": 100, "max-waiting-queue-length": 1000, "min-tool-call-array-param-length": 1, "min-tool-call-integer-param": 0, "min-tool-call-number-param": 0, "mm-encoder-only": false, "mm-processor-kwargs": "", "mode": "random", "model": "facebook/opt-125m", "object-tool-call-not-required-field-probability": 50, "port": 8000, "prefill-overhead": 0, "prefill-time-per-token": 0, "prefill-time-std-dev": 0, "seed": 1781640111719914200, "self-signed-certs": false, "served-model-name": [ "facebook/opt-125m" ], "ssl-certfile": "/var/run/kserve/tls/tls.crt", "ssl-keyfile": "/var/run/kserve/tls/tls.key", "time-factor-under-load": 1, "time-to-first-token": 0, "time-to-first-token-std-dev": 0, "tool-call-not-required-param-probability": 50, "uds-socket-path": "/tmp/tokenizer/tokenizer-uds.socket", "zmq-endpoint": "tcp://127.0.0.1:5557" } > I0616 20:01:51.758626 1 tokenizer.go:104] "Model is not a real HF model, using simulated tokenizer" model="facebook/opt-125m" I0616 20:01:51.762283 1 context.go:138] "No dataset path or URL provided, using random text for responses" I0616 20:01:51.762345 1 simulator.go:188] "Start processing routine" I0616 20:01:51.762357 1 communication.go:49] "Starting communication layer" I0616 20:01:51.762722 1 http_server_tls.go:44] "HTTPS server starting with certificate files" cert="/var/run/kserve/tls/tls.crt" key="/var/run/kserve/tls/tls.key" I0616 20:01:51.762781 1 grpc.go:126] "Server starting" protocol="gRPC" port=8000 I0616 20:01:51.763381 1 http.go:96] "Server starting" protocol="HTTPS" port=8000