92 lines
2.7 KiB
JSON
92 lines
2.7 KiB
JSON
|
[
|
||
|
|
{
|
||
|
|
"build_commit": "e71b80510",
|
||
|
|
"build_number": 10849,
|
||
|
|
"cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
|
||
|
|
"gpu_info": "",
|
||
|
|
"backends": "CPU",
|
||
|
|
"model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B-Q4_K_M.gguf",
|
||
|
|
"model_type": "spark2_5 1.7B Q4_K - Medium",
|
||
|
|
"model_size": 1102073856,
|
||
|
|
"model_n_params": 1707657216,
|
||
|
|
"n_batch": 2048,
|
||
|
|
"n_ubatch": 512,
|
||
|
|
"n_threads": 24,
|
||
|
|
"cpu_mask": "0x0",
|
||
|
|
"cpu_strict": false,
|
||
|
|
"poll": 50,
|
||
|
|
"type_k": "f16",
|
||
|
|
"type_v": "f16",
|
||
|
|
"n_gpu_layers": -1,
|
||
|
|
"n_cpu_moe": 0,
|
||
|
|
"split_mode": "layer",
|
||
|
|
"main_gpu": 0,
|
||
|
|
"no_kv_offload": false,
|
||
|
|
"flash_attn": -1,
|
||
|
|
"devices": "auto",
|
||
|
|
"tensor_split": "0.00",
|
||
|
|
"tensor_buft_overrides": "none",
|
||
|
|
"load_mode": "auto",
|
||
|
|
"lazy_mode": "auto",
|
||
|
|
"embeddings": false,
|
||
|
|
"no_op_offload": 0,
|
||
|
|
"no_host": false,
|
||
|
|
"fit_target": 0,
|
||
|
|
"fit_min_ctx": 0,
|
||
|
|
"n_prompt": 512,
|
||
|
|
"n_gen": 0,
|
||
|
|
"n_depth": 0,
|
||
|
|
"test_time": "2026-09-11T19:14:20Z",
|
||
|
|
"avg_ns": 464927159,
|
||
|
|
"stddev_ns": 22146638,
|
||
|
|
"avg_ts": 1103.200971,
|
||
|
|
"stddev_ts": 51.267874,
|
||
|
|
"samples_ns": [ 453191976, 479254490, 448568607, 496875740, 446744984 ],
|
||
|
|
"samples_ts": [ 1129.76, 1068.33, 1141.41, 1030.44, 1146.07 ]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"build_commit": "e71b80510",
|
||
|
|
"build_number": 10849,
|
||
|
|
"cpu_info": "Intel(R) Xeon(R) Platinum 8480C",
|
||
|
|
"gpu_info": "",
|
||
|
|
"backends": "CPU",
|
||
|
|
"model_filename": "/data/zhoutaichang/.cache/huggingface/hub/models--XHToken--Spark-X2.5-1.7B-GGUF/snapshots/23e1fcac55e7dd71e4c12a23723cc228ba0e5e85/Spark-X2.5-1.7B-Q4_K_M.gguf",
|
||
|
|
"model_type": "spark2_5 1.7B Q4_K - Medium",
|
||
|
|
"model_size": 1102073856,
|
||
|
|
"model_n_params": 1707657216,
|
||
|
|
"n_batch": 2048,
|
||
|
|
"n_ubatch": 512,
|
||
|
|
"n_threads": 24,
|
||
|
|
"cpu_mask": "0x0",
|
||
|
|
"cpu_strict": false,
|
||
|
|
"poll": 50,
|
||
|
|
"type_k": "f16",
|
||
|
|
"type_v": "f16",
|
||
|
|
"n_gpu_layers": -1,
|
||
|
|
"n_cpu_moe": 0,
|
||
|
|
"split_mode": "layer",
|
||
|
|
"main_gpu": 0,
|
||
|
|
"no_kv_offload": false,
|
||
|
|
"flash_attn": -1,
|
||
|
|
"devices": "auto",
|
||
|
|
"tensor_split": "0.00",
|
||
|
|
"tensor_buft_overrides": "none",
|
||
|
|
"load_mode": "auto",
|
||
|
|
"lazy_mode": "auto",
|
||
|
|
"embeddings": false,
|
||
|
|
"no_op_offload": 0,
|
||
|
|
"no_host": false,
|
||
|
|
"fit_target": 0,
|
||
|
|
"fit_min_ctx": 0,
|
||
|
|
"n_prompt": 0,
|
||
|
|
"n_gen": 128,
|
||
|
|
"n_depth": 0,
|
||
|
|
"test_time": "2026-09-11T19:14:23Z",
|
||
|
|
"avg_ns": 1422234679,
|
||
|
|
"stddev_ns": 12240631,
|
||
|
|
"avg_ts": 90.004494,
|
||
|
|
"stddev_ts": 0.767183,
|
||
|
|
"samples_ns": [ 1422285965, 1416723437, 1414194914, 1414611159, 1443357923 ],
|
||
|
|
"samples_ts": [ 89.996, 90.3493, 90.5109, 90.4842, 88.6821 ]
|
||
|
|
}
|
||
|
|
]
|