I0601 22:15:06.857420 1 config.go:602] "Configuration:" =< { "IP": "10.132.0.31", "PodName": "facebook-opt-125m-simulated-kserve-59dcdf78f5-p2l47", "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": 1780352106856968400, "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" } > I0601 22:15:06.885159 1 tokenizer.go:104] "Model is not a real HF model, using simulated tokenizer" model="facebook/opt-125m" I0601 22:15:06.889260 1 context.go:138] "No dataset path or URL provided, using random text for responses" I0601 22:15:06.889321 1 communication.go:49] "Starting communication layer" I0601 22:15:06.889364 1 simulator.go:188] "Start processing routine" I0601 22:15:06.889622 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" I0601 22:15:06.889649 1 grpc.go:126] "Server starting" protocol="gRPC" port=8000 I0601 22:15:06.890319 1 http.go:96] "Server starting" protocol="HTTPS" port=8000 2026-06-01 22:15:05.422 1 storage.initializer INFO [initializer-entrypoint:():16] Initializing, args: (src_uri, dest_path): [('hf://sshleifer/tiny-gpt2', '/mnt/models')] 2026-06-01 22:15:05.423 1 storage.initializer INFO [kserve_storage.py:download():161] Copying contents of hf://sshleifer/tiny-gpt2 to local Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/wPaCkH-WbT7GsmxMKKrNZTV4nSM=.ae8c63daedbd4206d7d40126955d4e6ab1c80f8f.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_d19cdae8-23f6-4391-9057-df7ffe3a81f8'. Continuing without setting permissions. Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/8_PA_wEVGiVa2goH2H4KQOQpvVY=.2c81a6c4c984e95a45338c64a7445c1f0f88077f.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_a140ab3b-6714-48bc-8ada-ac5cdf126a9f'. Continuing without setting permissions. Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/gPcsVCQDYDHk-_n0G9uADl7PXIM=.3cd4987249615ca870f2c18e657a62f0962aecad0eac790dd89362227310fd30.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_7cce2993-08ec-49e5-b529-6f6fa95c7eea'. Continuing without setting permissions. Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/PtHk0z_I45atnj23IIRhTExwT3w=.226b0752cac7789c48f0cb3ec53eda48b7be36cc.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_f4b596cd-524d-40b5-a971-93f2dd703253'. Continuing without setting permissions. Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/Q1p2l2BzM1m6P5jKvr8WTq1TUio=.b706b24034032bdfe765ded5ab6403d201d295a995b790cb24c74becca5c04e6.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_b7774d52-b305-4f40-956f-2b8e4ff9f431'. Continuing without setting permissions. Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/ahkChHUJFxEmOdq5GDFEmerRzCY=.817762d631ad6f9c799f6b9dc713c46420e65546.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_4408ba39-f476-4601-90ac-a6f679aa4b11'. Continuing without setting permissions. Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/a7eHxRFT3OeMBIFg52k2nfj5m7w=.09166c56d46ec8eca5f1e46e4e4a62265fca5975a70a2b263c1795291a685cf7.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_4cd6e25e-3325-40f1-a8d9-fe024f90cbe5'. Continuing without setting permissions. Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/vzaExXFZNBay89bvlQv-ZcI6BTg=.be4d21d94f3b4687e5a54d84bf6ab46ed0f8defd.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_5035afec-0fb3-4a91-ab98-55a385966327'. Continuing without setting permissions. Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/j3m-Hy6QvBddw8RXA1uSWl1AJ0c=.b00361fece0387ca34b4b8b8539ed830d644dbeb.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_a2a70c1c-5d73-4acf-8157-4cf8df96312e'. Continuing without setting permissions. 2026-06-01 22:15:06.407 1 storage.initializer INFO [kserve_storage.py:download():229] Successfully copied hf://sshleifer/tiny-gpt2 to /mnt/models 2026-06-01 22:15:06.407 1 storage.initializer INFO [kserve_storage.py:download():230] Model downloaded in 0.9843728830001055 seconds.