2026-04-20 20:22:09.865 1 kserve INFO [initializer-entrypoint:<module>():16] Initializing, args: src_uri [hf://facebook/opt-125m] dest_path[ [/mnt/models]
2026-04-20 20:22:09.866 1 kserve INFO [storage.py:download():64] Copying contents of hf://facebook/opt-125m to local
Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/wPaCkH-WbT7GsmxMKKrNZTV4nSM=.ac481c8eb05e4d2496fbe076a38a7b4835dd733d.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_862b68d4-0ef9-4d42-891f-c250baf18374'.
Continuing without setting permissions.
Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/5HHJ6px3_ZRDOG3OxNZMhuycwOk=.a591333512516f58bf2002045dece909a0ccdb8b.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_f1d4f0fb-9082-4e2a-93e6-6daf583613a7'.
Continuing without setting permissions.
Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/Xn7B-BWUGOee2Y6hCZtEhtFu4BE=.38c05904caf6e5b9f04ecda5c973d77e6c1da151.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_ec8f4c64-6642-47a7-9471-be77be4009ef'.
Continuing without setting permissions.
Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/8_PA_wEVGiVa2goH2H4KQOQpvVY=.b3fb716a3024261980becb2382e31a3780985130.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_27d7f16c-36ad-4264-a593-f0a669109f4b'.
Continuing without setting permissions.
Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/gPcsVCQDYDHk-_n0G9uADl7PXIM=.61c60ec52ed43038fff0fbbd68b080c94b0d94b4c8458dbd65965f9b17631c89.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_0004fad1-cdfc-4e6c-b7bb-4c3ad9874066'.
Continuing without setting permissions.
Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/3EVKVggOldJcKSsGjSdoUCN1AyQ=.cf739e3ba86db7791ebab2828cc34b8a5acd3a86.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_29e83e6a-bfc8-4d72-a311-78036d0468db'.
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_070877ee-462e-4989-88d8-3b617cc931ef'.
Continuing without setting permissions.
Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/Q1p2l2BzM1m6P5jKvr8WTq1TUio=.2d74da6615135c58cf3cf9ad4cb11e7c613ff9e55fe658a47ab83b6c8d1174a9.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_a49f7c7e-e801-4ef0-963d-676b6a602cca'.
Continuing without setting permissions.
Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/ahkChHUJFxEmOdq5GDFEmerRzCY=.5dfa36546b8eddce0e04df3133c30df43fcc3828.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_88c695ed-885a-4472-8b12-a9e1e12d5486'.
Continuing without setting permissions.
Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/a7eHxRFT3OeMBIFg52k2nfj5m7w=.db7090b0c8b34dd957a7e0656c718f978f9203cc874018f37dda44108be5970a.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_835fa42a-4dd1-4eb6-81b6-7dbce8782cef'.
Continuing without setting permissions.
Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/vzaExXFZNBay89bvlQv-ZcI6BTg=.27c24ca9d908d0b678b20c698aeb9e950c44d865.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_a197b27d-1fae-4635-909b-ce187639fc11'.
Continuing without setting permissions.
Could not set the permissions on the file '/mnt/models/.cache/huggingface/download/j3m-Hy6QvBddw8RXA1uSWl1AJ0c=.0a39732b2d8be8e493cab3da68b68cc3e28221de.incomplete'. Error: [Errno 13] Permission denied: '/mnt/tmp_72b4631d-9ef5-4e4a-b18d-c2efec4eb64c'.
Continuing without setting permissions.
2026-04-20 20:22:13.140 1 kserve INFO [storage.py:download():110] Successfully copied hf://facebook/opt-125m to /mnt/models
2026-04-20 20:22:13.140 1 kserve INFO [storage.py:download():111] Model downloaded in 3.274266033999993 seconds.
I0420 20:22:14.584016       1 config.go:602] "Configuration:" =<
	{
	  "IP": "10.134.0.57",
	  "PodName": "premium-simulated-simulated-premium-kserve-6b97b89985-6m7mh",
	  "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": 1776716534583530000,
	  "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"
	}
 >
I0420 20:22:14.614367       1 tokenizer.go:104] "Model is not a real HF model, using simulated tokenizer" model="facebook/opt-125m"
I0420 20:22:14.618166       1 context.go:138] "No dataset path or URL provided, using random text for responses"
I0420 20:22:14.618232       1 communication.go:49] "Starting communication layer"
I0420 20:22:14.618230       1 simulator.go:188] "Start processing routine"
I0420 20:22:14.618485       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"
I0420 20:22:14.618555       1 grpc.go:126] "Server starting" protocol="gRPC" port=8000
I0420 20:22:14.619140       1 http.go:96] "Server starting" protocol="HTTPS" port=8000