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": 4,
|
||
|
|
"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": "2026-09-11T17:14:44Z",
|
||
|
|
"avg_ns": 2304834712,
|
||
|
|
"stddev_ns": 9004426,
|
||
|
|
"avg_ts": 222.144447,
|
||
|
|
"stddev_ts": 0.865236,
|
||
|
|
"samples_ns": [ 2319430963, 2305311298, 2304610521, 2298020765, 2296800014 ],
|
||
|
|
"samples_ts": [ 220.744, 222.096, 222.163, 222.8, 222.919 ]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"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": 4,
|
||
|
|
"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": "2026-09-11T17:14:58Z",
|
||
|
|
"avg_ns": 5335792102,
|
||
|
|
"stddev_ns": 59840580,
|
||
|
|
"avg_ts": 23.991343,
|
||
|
|
"stddev_ts": 0.267723,
|
||
|
|
"samples_ns": [ 5425666503, 5348961684, 5341956156, 5275207674, 5287168494 ],
|
||
|
|
"samples_ts": [ 23.5916, 23.9299, 23.9613, 24.2644, 24.2096 ]
|
||
|
|
}
|
||
|
|
]
|