22 lines
866 B
JSON
22 lines
866 B
JSON
|
{
|
||
|
|
"date": "2026-10-12",
|
||
|
|
"model": "google/embeddinggemma-2",
|
||
|
|
"runtime": "llama.cpp b11461 with pinned no-logits patch",
|
||
|
|
"device": "cpu",
|
||
|
|
"threads": 1,
|
||
|
|
"test": "google_cpu_debug_query_reports_actual_worker_stages_without_changing_vectors",
|
||
|
|
"test_elapsed_seconds_including_initialization_and_two_queries": 18.09,
|
||
|
|
"debug_normal_cosine": 0.99999999,
|
||
|
|
"diagnostics": {
|
||
|
|
"request_encode_us": 24,
|
||
|
|
"request_write_us": 52,
|
||
|
|
"response_validate_us": 92,
|
||
|
|
"worker_batch_prepare_us": 22,
|
||
|
|
"worker_inference_us": 112914,
|
||
|
|
"worker_pool_normalize_us": 17,
|
||
|
|
"worker_token_count": 13,
|
||
|
|
"worker_tokenization_us": 149,
|
||
|
|
"worker_wait_and_response_decode_us": 113960
|
||
|
|
},
|
||
|
|
"scope": "One actual query diagnostic; native worker clocks are not aligned to Rust. VM had concurrent media inference. No production latency or broad overhead claim."
|
||
|
|
}
|