28 lines
1.0 KiB
JSON
28 lines
1.0 KiB
JSON
{
|
|
"measured_at": "2026-08-31",
|
|
"notes": [
|
|
"Cold starts were measured separately from warm inference.",
|
|
"The vLLM model was already present in the Hugging Face cache; zero bytes were downloaded.",
|
|
"vLLM launch-to-ready is derived from the recorded epoch and second-resolution API startup log.",
|
|
"Ollama's daemon was already running, but the model was fully unloaded before the request.",
|
|
"The Ollama request used one output token and keep_alive=0 so generation time was negligible and the model was unloaded afterward."
|
|
],
|
|
"vllm_metal": {
|
|
"process_start_epoch": 1788177244.465068,
|
|
"api_ready_local_time": "2026-08-31T13:54:33+02:00",
|
|
"approx_launch_to_api_ready_s": 28.535,
|
|
"model_load_s": 3.25,
|
|
"engine_profile_cache_warmup_s": 9.71,
|
|
"download_bytes": 0
|
|
},
|
|
"ollama": {
|
|
"client_total_s": 3.455159667,
|
|
"server_total_s": 3.448873125,
|
|
"model_load_s": 3.244982292,
|
|
"prompt_eval_s": 0.13364925,
|
|
"decode_s": 0.069530292,
|
|
"prompt_tokens": 7,
|
|
"output_tokens": 1
|
|
}
|
|
}
|