{ "cases": [ { "name": "rmsnorm-f32-256x1024", "preset": "smoke", "vars": { "dtype": "float32", "rows": 256, "dim": 1024 }, "attrs": { "epsilon": 0.000001, "axis": -1 }, "inputs": { "x": { "shape": [256, 1024], "dtype": "float32", "dist": "normal", "seed": 710, "scale": 0.5 }, "scale": { "shape": [1024], "dtype": "float32", "dist": "uniform", "seed": 711, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [256, 1024], "dtype": "float32" } }, "bench": { "primary": true, "metrics": [{ "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype)" }] } }, { "name": "rmsnorm-f32-4096x4096", "preset": "smoke", "vars": { "dtype": "float32", "rows": 4096, "dim": 4096 }, "attrs": { "epsilon": 0.000001, "axis": -1 }, "inputs": { "x": { "shape": [4096, 4096], "dtype": "float32", "dist": "normal", "seed": 712, "scale": 0.5 }, "scale": { "shape": [4096], "dtype": "float32", "dist": "uniform", "seed": 713, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [4096, 4096], "dtype": "float32" } }, "bench": { "primary": true, "metrics": [{ "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype)" }] } }, { "name": "rmsnorm-f16-4096x4096", "preset": "smoke", "vars": { "dtype": "float16", "rows": 4096, "dim": 4096 }, "attrs": { "epsilon": 0.000001, "axis": -1 }, "inputs": { "x": { "shape": [4096, 4096], "dtype": "float16", "dist": "normal", "seed": 714, "scale": 0.5 }, "scale": { "shape": [4096], "dtype": "float16", "dist": "uniform", "seed": 715, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [4096, 4096], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype)" }] } }, { "name": "rmsnorm-f16-1x4096-rows1-decode", "preset": "smoke", "vars": { "dtype": "float16", "rows": 1, "dim": 4096 }, "attrs": { "epsilon": 0.000001, "axis": -1 }, "inputs": { "x": { "shape": [1, 4096], "dtype": "float16", "dist": "normal", "seed": 7200, "scale": 0.5 }, "scale": { "shape": [4096], "dtype": "float16", "dist": "uniform", "seed": 7201, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 4096], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype)" }] } }, { "name": "rmsnorm-f16-256x4096-aligned-vec4", "preset": "smoke", "vars": { "dtype": "float16", "rows": 256, "dim": 4096 }, "attrs": { "epsilon": 0.000001, "axis": -1 }, "inputs": { "x": { "shape": [256, 4096], "dtype": "float16", "dist": "normal", "seed": 7210, "scale": 0.5 }, "scale": { "shape": [4096], "dtype": "float16", "dist": "uniform", "seed": 7211, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [256, 4096], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype)" }] } }, { "name": "rmsnorm-f16-256x4094-unaligned-alignmentcliff", "preset": "smoke", "vars": { "dtype": "float16", "rows": 256, "dim": 4094 }, "attrs": { "epsilon": 0.000001, "axis": -1 }, "inputs": { "x": { "shape": [256, 4094], "dtype": "float16", "dist": "normal", "seed": 7220, "scale": 0.5 }, "scale": { "shape": [4094], "dtype": "float16", "dist": "uniform", "seed": 7221, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [256, 4094], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype)" }] } }, { "name": "rmsnorm-f32-8x256x1024-suffixaxis1-generic", "preset": "smoke", "vars": { "dtype": "float32", "outer": 8, "normSize": 262144 }, "attrs": { "epsilon": 0.000001, "axis": 1 }, "inputs": { "x": { "shape": [8, 256, 1024], "dtype": "float32", "dist": "normal", "seed": 7230, "scale": 0.5 }, "scale": { "shape": [256, 1024], "dtype": "float32", "dist": "uniform", "seed": 7231, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [8, 256, 1024], "dtype": "float32" } }, "bench": { "metrics": [ { "type": "bandwidth", "value": "(args.outer * args.normSize * 2 + args.normSize) * dtypeBytes(args.dtype)" } ] } }, { "name": "rmsnorm-f32-65535x512-undercliff", "preset": "stress", "vars": { "dtype": "float32", "rows": 65535, "dim": 512 }, "attrs": { "epsilon": 0.000001, "axis": -1 }, "inputs": { "x": { "shape": [65535, 512], "dtype": "float32", "dist": "normal", "seed": 7240, "scale": 0.5 }, "scale": { "shape": [512], "dtype": "float32", "dist": "uniform", "seed": 7241, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [65535, 512], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype)" }] } }, { "name": "rmsnorm-f32-70000x512-rows-dispatchcliff", "preset": "stress", "provenance": { "notes": "Stress-only dispatch/capacity case: declared tensors occupy 273 MiB of GPU storage." }, "vars": { "dtype": "float32", "rows": 70000, "dim": 512 }, "attrs": { "epsilon": 0.000001, "axis": -1 }, "inputs": { "x": { "shape": [70000, 512], "dtype": "float32", "dist": "normal", "seed": 7250, "scale": 0.5 }, "scale": { "shape": [512], "dtype": "float32", "dist": "uniform", "seed": 7251, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [70000, 512], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype)" }] } }, { "name": "rmsnorm-f16-8x262144-suffixaxis0-nosplitk-occupancy-starve", "preset": "stress", "vars": { "dtype": "float16", "outer": 8, "normSize": 262144 }, "attrs": { "epsilon": 0.000001, "axis": 0 }, "inputs": { "x": { "shape": [8, 262144], "dtype": "float16", "dist": "normal", "seed": 7260, "scale": 0.5 }, "scale": { "shape": [262144], "dtype": "float16", "dist": "uniform", "seed": 7261, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [8, 262144], "dtype": "float16", "dist": "empty" } }, "bench": { "metrics": [ { "type": "bandwidth", "value": "(args.outer * args.normSize * 2 + args.normSize) * dtypeBytes(args.dtype)" } ] } }, { "name": "rmsnorm-f32-4x262144-lastaxis-scalarscale-fallback-starve", "preset": "stress", "vars": { "dtype": "float32", "rows": 4, "dim": 262144 }, "attrs": { "epsilon": 0.000001, "axis": -1 }, "inputs": { "x": { "shape": [4, 262144], "dtype": "float32", "dist": "normal", "seed": 7270, "scale": 0.5 }, "scale": { "shape": [1], "dtype": "float32", "dist": "uniform", "seed": 7271, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [4, 262144], "dtype": "float32", "dist": "empty" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": "(args.rows * args.dim * 2 + args.dim) * dtypeBytes(args.dtype)" }] } }, { "name": "split_f32-1x16384", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 16384], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 16384], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 131076 }] } }, { "name": "split_f32-1x16385", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 16385], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 16385], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 131084 }] } }, { "name": "split_f32-1x32769", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 32769], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 32769], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 262156 }] } }, { "name": "split_f32-1x65536", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 65536], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 65536], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 524292 }] } }, { "name": "split_f32-1x131072", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 131072], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 131072], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 1048580 }] } }, { "name": "split_f32-1x262144", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 262144], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 262144], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 2097156 }] } }, { "name": "split_f32-1x524288", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 524288], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 524288], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 4194308 }] } }, { "name": "split_f32-1x1048576", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 1048576], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 1048576], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 8388612 }] } }, { "name": "split_f32-1x2097152", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 2097152], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 2097152], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 16777220 }] } }, { "name": "split_f32-2x131073", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [2, 131073], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [2, 131073], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 2097172 }] } }, { "name": "split_f32-3x524289", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [3, 524289], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [3, 524289], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 12582940 }] } }, { "name": "split_f32-4x1048576", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [4, 1048576], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [4, 1048576], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 33554436 }] } }, { "name": "split_f32-8x16384", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [8, 16384], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [8, 16384], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 1048580 }] } }, { "name": "split_f32-16x65536", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [16, 65536], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [16, 65536], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 8388612 }] } }, { "name": "split_f32-32x32769", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [32, 32769], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [32, 32769], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 8388868 }] } }, { "name": "split_f32-128x16384", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [128, 16384], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [128, 16384], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 16777220 }] } }, { "name": "split_f16-1x16385", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 16385], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 16385], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 65542 }] } }, { "name": "split_f16-1x131072", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 131072], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 131072], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 524290 }] } }, { "name": "split_f16-1x524288", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 524288], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 524288], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 2097154 }] } }, { "name": "split_f16-1x2097152", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [1, 2097152], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 2097152], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 8388610 }] } }, { "name": "split_f16-3x524289", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [3, 524289], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [3, 524289], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 6291470 }] } }, { "name": "split_f16-16x65536", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [16, 65536], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [16, 65536], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 4194306 }] } }, { "name": "split_f32-f16-2x32769", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [2, 32769], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float16", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [2, 32769], "dtype": "float16" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 393230 }] } }, { "name": "split_f16-f32-2x32769", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": {}, "inputs": { "x": { "shape": [2, 32769], "dtype": "float16", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [2, 32769], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 393232 }] } }, { "name": "split_f32-1x16384-split1", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "MAX_SPLITS": 1 }, "inputs": { "x": { "shape": [1, 16384], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 16384], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 131076 }] } }, { "name": "split_f32-1x16385-split3", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "MAX_SPLITS": 3 }, "inputs": { "x": { "shape": [1, 16385], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [1, 16385], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 131084 }] } }, { "name": "split_f32-2x262145-wg64", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "WORKGROUP_SIZE": 64 }, "inputs": { "x": { "shape": [2, 262145], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [2, 262145], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 4194324 }] } }, { "name": "split_f32-2x262145-wg128", "preset": "stress", "attrs": { "axis": -1, "epsilon": 0.000001 }, "tunables": { "WORKGROUP_SIZE": 128 }, "inputs": { "x": { "shape": [2, 262145], "dtype": "float32", "dist": "normal", "seed": 8123, "scale": 0.5 }, "scale": { "shape": [], "dtype": "float32", "dist": "uniform", "seed": 8124, "scale": 0.25, "offset": 1 } }, "outputs": { "y": { "shape": [2, 262145], "dtype": "float32" } }, "bench": { "metrics": [{ "type": "bandwidth", "value": 4194324 }] } } ] }