62 lines
1.7 KiB
JSON
62 lines
1.7 KiB
JSON
{
|
|
"probe": {
|
|
"torch": "2.12.0+cu130",
|
|
"kitchen": "0.2.35",
|
|
"status": "finite_sparse_output",
|
|
"relative_error": 0.46068075299263,
|
|
"forced_all_keys_exact_relative_error": 0.013319959864020348,
|
|
"first_call_seconds": 1.1965116760111414,
|
|
"shape": [
|
|
1,
|
|
2,
|
|
1248,
|
|
128
|
|
],
|
|
"bias_elements": 8736,
|
|
"gpu": "NVIDIA RTX PRO 6000 Blackwell Workstation Edition",
|
|
"peak_allocated_bytes": 29803008
|
|
},
|
|
"benchmark": {
|
|
"torch": "2.12.0+cu130",
|
|
"kitchen": "0.2.35",
|
|
"status": "passed",
|
|
"seconds": {
|
|
"flash_partitions": 0.017417979950550944,
|
|
"sol_frame_bias": 0.16037049802253023
|
|
},
|
|
"shape": [
|
|
1,
|
|
2,
|
|
42836,
|
|
128
|
|
],
|
|
"frames": 22,
|
|
"guide_rows": 7062,
|
|
"bias_elements": 942392,
|
|
"gpu": "NVIDIA RTX PRO 6000 Blackwell Workstation Edition",
|
|
"peak_allocated_bytes": 210820096,
|
|
"conditions": "One warmup and one timed evaluation per backend; 2 heads, not full H3; concurrent Swap Anything training; not an end-to-end speed benchmark"
|
|
},
|
|
"benchmark_h56": {
|
|
"torch": "2.12.0+cu130",
|
|
"kitchen": "0.2.35",
|
|
"status": "passed",
|
|
"seconds": {
|
|
"flash_partitions": 0.41910952096804976,
|
|
"sol_frame_bias": 2.6489629900315776
|
|
},
|
|
"shape": [
|
|
1,
|
|
56,
|
|
42836,
|
|
128
|
|
],
|
|
"frames": 22,
|
|
"guide_rows": 7062,
|
|
"bias_elements": 942392,
|
|
"gpu": "NVIDIA RTX PRO 6000 Blackwell Workstation Edition",
|
|
"peak_allocated_bytes": 5760942592,
|
|
"conditions": "One warmup and one timed evaluation per backend; 56 heads; isolated attention, not a full H3 model evaluation; concurrent Swap Anything training; not an end-to-end speed benchmark"
|
|
}
|
|
}
|