Xenova's picture
Xenova HF Staff
sync 6fdf6301e2bb
d882115 verified
Raw History Blame
46.6 kB
{
"tunableSpace": { "THREAD_QK_OUTPUT_WORKGROUPS": [0, 2] },
"cases": [
{
"name": "cross-whisper-tiny-b1-h6-kv1500-d64-qk-f32",
"preset": "model",
"vars": { "elemBytes": 4, "qkBytes": 4 },
"attrs": { "num_heads": 6, "output_qk": 1 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float32", "dist": "normal", "seed": 301, "scale": 0.2 },
"keyT": { "shape": [1, 6, 1500, 64], "dtype": "float32", "dist": "normal", "seed": 302, "scale": 0.2 },
"valueT": { "shape": [1, 6, 1500, 64], "dtype": "float32", "dist": "normal", "seed": 303, "scale": 0.2 }
},
"outputs": {
"outputT": { "shape": [1, 1, 384], "dtype": "float32" },
"qkT": { "shape": [1, 6, 1, 1500], "dtype": "float32" }
},
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "(1 * 6 * 1500 * 64 * 2 + 1 * 384 * 2) * args.elemBytes + 1 * 6 * 1500 * args.qkBytes"
}
]
}
},
{
"name": "cross-whisper-large-b1-h20-kv1500-d64-qk-f16",
"preset": "model",
"vars": { "elemBytes": 2, "qkBytes": 4 },
"attrs": { "num_heads": 20, "output_qk": 1 },
"inputs": {
"queryT": { "shape": [1, 1, 1280], "dtype": "float16", "dist": "normal", "seed": 304, "scale": 0.2 },
"keyT": { "shape": [1, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 305, "scale": 0.2 },
"valueT": { "shape": [1, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 306, "scale": 0.2 }
},
"outputs": {
"outputT": { "shape": [1, 1, 1280], "dtype": "float16" },
"qkT": { "shape": [1, 20, 1, 1500], "dtype": "float32" }
},
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "(1 * 20 * 1500 * 64 * 2 + 1 * 1280 * 2) * args.elemBytes + 1 * 20 * 1500 * args.qkBytes"
}
]
}
},
{
"name": "cross-whisper-large-b4-h20-kv1500-d64-qk-f16",
"preset": "model",
"vars": { "elemBytes": 2, "qkBytes": 4 },
"attrs": { "num_heads": 20, "output_qk": 1 },
"inputs": {
"queryT": { "shape": [4, 1, 1280], "dtype": "float16", "dist": "normal", "seed": 307, "scale": 0.2 },
"keyT": { "shape": [4, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 308, "scale": 0.2 },
"valueT": { "shape": [4, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 309, "scale": 0.2 }
},
"outputs": {
"outputT": { "shape": [4, 1, 1280], "dtype": "float16" },
"qkT": { "shape": [4, 20, 1, 1500], "dtype": "float32" }
},
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "(4 * 20 * 1500 * 64 * 2 + 4 * 1280 * 2) * args.elemBytes + 4 * 20 * 1500 * args.qkBytes"
}
]
}
},
{
"name": "cross-whisper-large-b8-h20-kv1500-d64-f16",
"preset": "model",
"vars": { "elemBytes": 2, "qkBytes": 0 },
"attrs": { "num_heads": 20 },
"inputs": {
"queryT": { "shape": [8, 1, 1280], "dtype": "float16", "dist": "normal", "seed": 310, "scale": 0.2 },
"keyT": { "shape": [8, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 311, "scale": 0.2 },
"valueT": { "shape": [8, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 312, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [8, 1, 1280], "dtype": "float16" } },
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(8 * 20 * 1500 * 64 * 2 + 8 * 1280 * 2) * args.elemBytes" }]
}
},
{
"name": "cross-whisper-large-b8-h20-kv1500-d64-f32",
"preset": "model",
"vars": { "elemBytes": 4, "qkBytes": 0 },
"attrs": { "num_heads": 20 },
"inputs": {
"queryT": { "shape": [8, 1, 1280], "dtype": "float32", "dist": "normal", "seed": 313, "scale": 0.2 },
"keyT": { "shape": [8, 20, 1500, 64], "dtype": "float32", "dist": "normal", "seed": 314, "scale": 0.2 },
"valueT": { "shape": [8, 20, 1500, 64], "dtype": "float32", "dist": "normal", "seed": 315, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [8, 1, 1280], "dtype": "float32" } },
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(8 * 20 * 1500 * 64 * 2 + 8 * 1280 * 2) * args.elemBytes" }]
}
},
{
"name": "cross-whisper-large-b16-h20-kv1500-d64-f16",
"preset": "stress",
"vars": { "elemBytes": 2, "qkBytes": 0 },
"attrs": { "num_heads": 20 },
"inputs": {
"queryT": { "shape": [16, 1, 1280], "dtype": "float16", "dist": "normal", "seed": 316, "scale": 0.2 },
"keyT": { "shape": [16, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 317, "scale": 0.2 },
"valueT": { "shape": [16, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 318, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [16, 1, 1280], "dtype": "float16" } },
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(16 * 20 * 1500 * 64 * 2 + 16 * 1280 * 2) * args.elemBytes" }]
}
},
{
"name": "cross-whisper-large-b8-h20-kv1500-d64-mask-f16",
"preset": "model",
"vars": { "elemBytes": 2, "qkBytes": 0 },
"attrs": { "num_heads": 20 },
"inputs": {
"queryT": { "shape": [8, 1, 1280], "dtype": "float16", "dist": "normal", "seed": 319, "scale": 0.2 },
"keyT": { "shape": [8, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 320, "scale": 0.2 },
"valueT": { "shape": [8, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 321, "scale": 0.2 },
"maskIndexT": { "shape": [8, 1500], "dtype": "int32", "data": { "kind": "cycle", "values": [1, 1, 1, 0] } }
},
"outputs": { "outputT": { "shape": [8, 1, 1280], "dtype": "float16" } },
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(8 * 20 * 1500 * 64 * 2 + 8 * 1280 * 2) * args.elemBytes" }]
}
},
{
"name": "cross-whisper-large-b8-h20-kv1500-d64-qk-f16",
"preset": "model",
"vars": { "elemBytes": 2, "qkBytes": 4 },
"attrs": { "num_heads": 20, "output_qk": 1 },
"inputs": {
"queryT": { "shape": [8, 1, 1280], "dtype": "float16", "dist": "normal", "seed": 322, "scale": 0.2 },
"keyT": { "shape": [8, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 323, "scale": 0.2 },
"valueT": { "shape": [8, 20, 1500, 64], "dtype": "float16", "dist": "normal", "seed": 324, "scale": 0.2 }
},
"outputs": {
"outputT": { "shape": [8, 1, 1280], "dtype": "float16" },
"qkT": { "shape": [8, 20, 1, 1500], "dtype": "float32" }
},
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "(8 * 20 * 1500 * 64 * 2 + 8 * 1280 * 2) * args.elemBytes + 8 * 20 * 1500 * args.qkBytes"
}
]
}
},
{
"name": "cross-b1-h6-kv256-d64-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 256, 64], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 256, 64], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 384], "dtype": "float32" } },
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(1 * 6 * 256 * 64 * 2 + 1 * 384 * 2) * args.elemBytes" }]
}
},
{
"name": "cross-b2-h8-kv512-d128-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0 },
"attrs": { "num_heads": 8 },
"inputs": {
"queryT": { "shape": [2, 1, 1024], "dtype": "float32", "dist": "normal", "seed": 328, "scale": 0.2 },
"keyT": { "shape": [2, 8, 512, 128], "dtype": "float32", "dist": "normal", "seed": 329, "scale": 0.2 },
"valueT": { "shape": [2, 8, 512, 128], "dtype": "float32", "dist": "normal", "seed": 330, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [2, 1, 1024], "dtype": "float32" } },
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(2 * 8 * 512 * 128 * 2 + 2 * 1024 * 2) * args.elemBytes" }]
}
},
{
"name": "self-whisper-base-b1-h8-cap448-d64-past1-f32",
"preset": "model",
"vars": { "elemBytes": 4 },
"attrs": { "num_heads": 8, "past_present_share_buffer": 1 },
"inputs": {
"queryT": { "shape": [1, 1, 512], "dtype": "float32", "dist": "normal", "seed": 331, "scale": 0.2 },
"keyT": { "shape": [1, 1, 512], "dtype": "float32", "dist": "normal", "seed": 332, "scale": 0.2 },
"valueT": { "shape": [1, 1, 512], "dtype": "float32", "dist": "normal", "seed": 333, "scale": 0.2 },
"pastKeyT": { "shape": [1, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 334, "scale": 0.2 },
"pastValueT": { "shape": [1, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 335, "scale": 0.2 },
"pastSequenceLengthT": { "shape": [1], "dtype": "int32", "data": { "kind": "values", "values": [1] } }
},
"outputs": {
"outputT": { "shape": [1, 1, 512], "dtype": "float32" },
"presentKeyT": { "shape": [1, 8, 448, 64], "dtype": "float32" },
"presentValueT": { "shape": [1, 8, 448, 64], "dtype": "float32" }
},
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(4 * 229376 + 2 * 1024 + 2 * 1 * 512) * args.elemBytes" }]
}
},
{
"name": "self-whisper-base-b1-h8-cap448-d64-past223-f32",
"preset": "model",
"vars": { "elemBytes": 4 },
"attrs": { "num_heads": 8, "past_present_share_buffer": 1 },
"inputs": {
"queryT": { "shape": [1, 1, 512], "dtype": "float32", "dist": "normal", "seed": 336, "scale": 0.2 },
"keyT": { "shape": [1, 1, 512], "dtype": "float32", "dist": "normal", "seed": 337, "scale": 0.2 },
"valueT": { "shape": [1, 1, 512], "dtype": "float32", "dist": "normal", "seed": 338, "scale": 0.2 },
"pastKeyT": { "shape": [1, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 339, "scale": 0.2 },
"pastValueT": { "shape": [1, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 340, "scale": 0.2 },
"pastSequenceLengthT": { "shape": [1], "dtype": "int32", "data": { "kind": "values", "values": [223] } }
},
"outputs": {
"outputT": { "shape": [1, 1, 512], "dtype": "float32" },
"presentKeyT": { "shape": [1, 8, 448, 64], "dtype": "float32" },
"presentValueT": { "shape": [1, 8, 448, 64], "dtype": "float32" }
},
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(4 * 229376 + 2 * 114688 + 2 * 1 * 512) * args.elemBytes" }]
}
},
{
"name": "self-whisper-base-b1-h8-cap448-d64-past447-f32",
"preset": "model",
"vars": { "elemBytes": 4 },
"attrs": { "num_heads": 8, "past_present_share_buffer": 1 },
"inputs": {
"queryT": { "shape": [1, 1, 512], "dtype": "float32", "dist": "normal", "seed": 341, "scale": 0.2 },
"keyT": { "shape": [1, 1, 512], "dtype": "float32", "dist": "normal", "seed": 342, "scale": 0.2 },
"valueT": { "shape": [1, 1, 512], "dtype": "float32", "dist": "normal", "seed": 343, "scale": 0.2 },
"pastKeyT": { "shape": [1, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 344, "scale": 0.2 },
"pastValueT": { "shape": [1, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 345, "scale": 0.2 },
"pastSequenceLengthT": { "shape": [1], "dtype": "int32", "data": { "kind": "values", "values": [446] } }
},
"outputs": {
"outputT": { "shape": [1, 1, 512], "dtype": "float32" },
"presentKeyT": { "shape": [1, 8, 448, 64], "dtype": "float32" },
"presentValueT": { "shape": [1, 8, 448, 64], "dtype": "float32" }
},
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(4 * 229376 + 2 * 228864 + 2 * 1 * 512) * args.elemBytes" }]
}
},
{
"name": "self-whisper-base-b4-h8-cap448-d64-past223-f16",
"preset": "model",
"vars": { "elemBytes": 2 },
"attrs": { "num_heads": 8, "past_present_share_buffer": 1 },
"inputs": {
"queryT": { "shape": [4, 1, 512], "dtype": "float16", "dist": "normal", "seed": 346, "scale": 0.2 },
"keyT": { "shape": [4, 1, 512], "dtype": "float16", "dist": "normal", "seed": 347, "scale": 0.2 },
"valueT": { "shape": [4, 1, 512], "dtype": "float16", "dist": "normal", "seed": 348, "scale": 0.2 },
"pastKeyT": { "shape": [4, 8, 448, 64], "dtype": "float16", "dist": "normal", "seed": 349, "scale": 0.2 },
"pastValueT": { "shape": [4, 8, 448, 64], "dtype": "float16", "dist": "normal", "seed": 350, "scale": 0.2 },
"pastSequenceLengthT": { "shape": [1], "dtype": "int32", "data": { "kind": "values", "values": [223] } }
},
"outputs": {
"outputT": { "shape": [4, 1, 512], "dtype": "float16" },
"presentKeyT": { "shape": [4, 8, 448, 64], "dtype": "float16" },
"presentValueT": { "shape": [4, 8, 448, 64], "dtype": "float16" }
},
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(4 * 917504 + 2 * 458752 + 2 * 4 * 512) * args.elemBytes" }]
}
},
{
"name": "self-b32-h8-cap448-d64-past223-f32",
"preset": "model",
"vars": { "elemBytes": 4 },
"attrs": { "num_heads": 8, "past_present_share_buffer": 1 },
"inputs": {
"queryT": { "shape": [32, 1, 512], "dtype": "float32", "dist": "normal", "seed": 351, "scale": 0.2 },
"keyT": { "shape": [32, 1, 512], "dtype": "float32", "dist": "normal", "seed": 352, "scale": 0.2 },
"valueT": { "shape": [32, 1, 512], "dtype": "float32", "dist": "normal", "seed": 353, "scale": 0.2 },
"pastKeyT": { "shape": [32, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 354, "scale": 0.2 },
"pastValueT": { "shape": [32, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 355, "scale": 0.2 },
"pastSequenceLengthT": { "shape": [1], "dtype": "int32", "data": { "kind": "values", "values": [223] } }
},
"outputs": {
"outputT": { "shape": [32, 1, 512], "dtype": "float32" },
"presentKeyT": { "shape": [32, 8, 448, 64], "dtype": "float32" },
"presentValueT": { "shape": [32, 8, 448, 64], "dtype": "float32" }
},
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(4 * 7340032 + 2 * 3670016 + 2 * 32 * 512) * args.elemBytes" }]
}
},
{
"name": "self-b32-h8-cap448-d64-past223-f16",
"preset": "model",
"vars": { "elemBytes": 2 },
"attrs": { "num_heads": 8, "past_present_share_buffer": 1 },
"inputs": {
"queryT": { "shape": [32, 1, 512], "dtype": "float16", "dist": "normal", "seed": 356, "scale": 0.2 },
"keyT": { "shape": [32, 1, 512], "dtype": "float16", "dist": "normal", "seed": 357, "scale": 0.2 },
"valueT": { "shape": [32, 1, 512], "dtype": "float16", "dist": "normal", "seed": 358, "scale": 0.2 },
"pastKeyT": { "shape": [32, 8, 448, 64], "dtype": "float16", "dist": "normal", "seed": 359, "scale": 0.2 },
"pastValueT": { "shape": [32, 8, 448, 64], "dtype": "float16", "dist": "normal", "seed": 360, "scale": 0.2 },
"pastSequenceLengthT": { "shape": [1], "dtype": "int32", "data": { "kind": "values", "values": [223] } }
},
"outputs": {
"outputT": { "shape": [32, 1, 512], "dtype": "float16" },
"presentKeyT": { "shape": [32, 8, 448, 64], "dtype": "float16" },
"presentValueT": { "shape": [32, 8, 448, 64], "dtype": "float16" }
},
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(4 * 7340032 + 2 * 3670016 + 2 * 32 * 512) * args.elemBytes" }]
}
},
{
"name": "self-b32-h8-cap448-d64-past447-f32",
"preset": "stress",
"vars": { "elemBytes": 4 },
"attrs": { "num_heads": 8, "past_present_share_buffer": 1 },
"inputs": {
"queryT": { "shape": [32, 1, 512], "dtype": "float32", "dist": "normal", "seed": 361, "scale": 0.2 },
"keyT": { "shape": [32, 1, 512], "dtype": "float32", "dist": "normal", "seed": 362, "scale": 0.2 },
"valueT": { "shape": [32, 1, 512], "dtype": "float32", "dist": "normal", "seed": 363, "scale": 0.2 },
"pastKeyT": { "shape": [32, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 364, "scale": 0.2 },
"pastValueT": { "shape": [32, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 365, "scale": 0.2 },
"pastSequenceLengthT": { "shape": [1], "dtype": "int32", "data": { "kind": "values", "values": [446] } }
},
"outputs": {
"outputT": { "shape": [32, 1, 512], "dtype": "float32" },
"presentKeyT": { "shape": [32, 8, 448, 64], "dtype": "float32" },
"presentValueT": { "shape": [32, 8, 448, 64], "dtype": "float32" }
},
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(4 * 7340032 + 2 * 7323648 + 2 * 32 * 512) * args.elemBytes" }]
}
},
{
"name": "self-b32-h8-cap448-d64-past223-mask-f32",
"preset": "model",
"vars": { "elemBytes": 4 },
"attrs": { "num_heads": 8, "past_present_share_buffer": 1 },
"inputs": {
"queryT": { "shape": [32, 1, 512], "dtype": "float32", "dist": "normal", "seed": 366, "scale": 0.2 },
"keyT": { "shape": [32, 1, 512], "dtype": "float32", "dist": "normal", "seed": 367, "scale": 0.2 },
"valueT": { "shape": [32, 1, 512], "dtype": "float32", "dist": "normal", "seed": 368, "scale": 0.2 },
"maskIndexT": { "shape": [32, 224], "dtype": "int32", "data": { "kind": "cycle", "values": [1, 1, 1, 0] } },
"pastKeyT": { "shape": [32, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 369, "scale": 0.2 },
"pastValueT": { "shape": [32, 8, 448, 64], "dtype": "float32", "dist": "normal", "seed": 370, "scale": 0.2 },
"pastSequenceLengthT": { "shape": [1], "dtype": "int32", "data": { "kind": "values", "values": [223] } }
},
"outputs": {
"outputT": { "shape": [32, 1, 512], "dtype": "float32" },
"presentKeyT": { "shape": [32, 8, 448, 64], "dtype": "float32" },
"presentValueT": { "shape": [32, 8, 448, 64], "dtype": "float32" }
},
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(4 * 7340032 + 2 * 3670016 + 2 * 32 * 512) * args.elemBytes" }]
}
},
{
"name": "self-b16-h12-cap2048-d64-past1023-f16",
"preset": "stress",
"vars": { "elemBytes": 2 },
"attrs": { "num_heads": 12, "past_present_share_buffer": 1 },
"inputs": {
"queryT": { "shape": [16, 1, 768], "dtype": "float16", "dist": "normal", "seed": 371, "scale": 0.2 },
"keyT": { "shape": [16, 1, 768], "dtype": "float16", "dist": "normal", "seed": 372, "scale": 0.2 },
"valueT": { "shape": [16, 1, 768], "dtype": "float16", "dist": "normal", "seed": 373, "scale": 0.2 },
"pastKeyT": { "shape": [16, 12, 2048, 64], "dtype": "float16", "dist": "normal", "seed": 374, "scale": 0.2 },
"pastValueT": { "shape": [16, 12, 2048, 64], "dtype": "float16", "dist": "normal", "seed": 375, "scale": 0.2 },
"pastSequenceLengthT": { "shape": [1], "dtype": "int32", "data": { "kind": "values", "values": [1023] } }
},
"outputs": {
"outputT": { "shape": [16, 1, 768], "dtype": "float16" },
"presentKeyT": { "shape": [16, 12, 2048, 64], "dtype": "float16" },
"presentValueT": { "shape": [16, 12, 2048, 64], "dtype": "float16" }
},
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(4 * 25165824 + 2 * 12582912 + 2 * 16 * 768) * args.elemBytes" }]
}
},
{
"name": "self-b1-h4-cap64-d64-past31-f32",
"preset": "smoke",
"vars": { "elemBytes": 4 },
"attrs": { "num_heads": 4, "past_present_share_buffer": 1 },
"inputs": {
"queryT": { "shape": [1, 1, 256], "dtype": "float32", "dist": "normal", "seed": 376, "scale": 0.2 },
"keyT": { "shape": [1, 1, 256], "dtype": "float32", "dist": "normal", "seed": 377, "scale": 0.2 },
"valueT": { "shape": [1, 1, 256], "dtype": "float32", "dist": "normal", "seed": 378, "scale": 0.2 },
"pastKeyT": { "shape": [1, 4, 64, 64], "dtype": "float32", "dist": "normal", "seed": 379, "scale": 0.2 },
"pastValueT": { "shape": [1, 4, 64, 64], "dtype": "float32", "dist": "normal", "seed": 380, "scale": 0.2 },
"pastSequenceLengthT": { "shape": [1], "dtype": "int32", "data": { "kind": "values", "values": [31] } }
},
"outputs": {
"outputT": { "shape": [1, 1, 256], "dtype": "float32" },
"presentKeyT": { "shape": [1, 4, 64, 64], "dtype": "float32" },
"presentValueT": { "shape": [1, 4, 64, 64], "dtype": "float32" }
},
"bench": {
"metrics": [{ "type": "bandwidth", "value": "(4 * 16384 + 2 * 8192 + 2 * 1 * 256) * args.elemBytes" }]
}
},
{
"name": "cross-b1-h6-kv16-d64-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 16, "headDim": 64, "maskBytes": 0 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 16, 64], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 16, 64], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 384], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b1-h6-kv16-d64-f16",
"preset": "smoke",
"vars": { "elemBytes": 2, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 16, "headDim": 64, "maskBytes": 0 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float16", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 16, 64], "dtype": "float16", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 16, 64], "dtype": "float16", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 384], "dtype": "float16" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b1-h6-kv64-d64-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 64, "headDim": 64, "maskBytes": 0 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 64, 64], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 64, 64], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 384], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b1-h6-kv64-d64-f16",
"preset": "smoke",
"vars": { "elemBytes": 2, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 64, "headDim": 64, "maskBytes": 0 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float16", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 64, 64], "dtype": "float16", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 64, 64], "dtype": "float16", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 384], "dtype": "float16" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b1-h6-kv255-d64-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 255, "headDim": 64, "maskBytes": 0 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 255, 64], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 255, 64], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 384], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b1-h6-kv255-d64-f16",
"preset": "smoke",
"vars": { "elemBytes": 2, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 255, "headDim": 64, "maskBytes": 0 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float16", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 255, 64], "dtype": "float16", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 255, 64], "dtype": "float16", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 384], "dtype": "float16" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b1-h6-kv257-d64-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 257, "headDim": 64, "maskBytes": 0 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 257, 64], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 257, 64], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 384], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b1-h6-kv257-d64-f16",
"preset": "smoke",
"vars": { "elemBytes": 2, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 257, "headDim": 64, "maskBytes": 0 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float16", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 257, 64], "dtype": "float16", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 257, 64], "dtype": "float16", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 384], "dtype": "float16" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-mask-qk-b1-h6-kv64-d64-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 1536, "batch": 1, "heads": 6, "keys": 64, "headDim": 64, "maskBytes": 256 },
"attrs": { "num_heads": 6, "output_qk": 1, "mask_filter_value": -4 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 64, 64], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 64, 64], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 },
"maskIndexT": { "dtype": "int32", "shape": [1, 64], "data": { "kind": "cycle", "values": [1, 0, 1] } }
},
"outputs": {
"outputT": { "shape": [1, 1, 384], "dtype": "float32" },
"qkT": { "dtype": "float32", "shape": [1, 6, 1, 64] }
},
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-mask-qk-b1-h6-kv64-d64-f16",
"preset": "smoke",
"vars": { "elemBytes": 2, "qkBytes": 768, "batch": 1, "heads": 6, "keys": 64, "headDim": 64, "maskBytes": 256 },
"attrs": { "num_heads": 6, "output_qk": 1, "mask_filter_value": -4 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float16", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 64, 64], "dtype": "float16", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 64, 64], "dtype": "float16", "dist": "normal", "seed": 327, "scale": 0.2 },
"maskIndexT": { "dtype": "int32", "shape": [1, 64], "data": { "kind": "cycle", "values": [1, 0, 1] } }
},
"outputs": {
"outputT": { "shape": [1, 1, 384], "dtype": "float16" },
"qkT": { "dtype": "float16", "shape": [1, 6, 1, 64] }
},
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-mask-qk-b1-h6-kv257-d64-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 6168, "batch": 1, "heads": 6, "keys": 257, "headDim": 64, "maskBytes": 1028 },
"attrs": { "num_heads": 6, "output_qk": 1, "mask_filter_value": -4 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 257, 64], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 257, 64], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 },
"maskIndexT": { "dtype": "int32", "shape": [1, 257], "data": { "kind": "cycle", "values": [1, 0, 1] } }
},
"outputs": {
"outputT": { "shape": [1, 1, 384], "dtype": "float32" },
"qkT": { "dtype": "float32", "shape": [1, 6, 1, 257] }
},
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-mask-qk-b1-h6-kv257-d64-f16",
"preset": "smoke",
"vars": { "elemBytes": 2, "qkBytes": 3084, "batch": 1, "heads": 6, "keys": 257, "headDim": 64, "maskBytes": 1028 },
"attrs": { "num_heads": 6, "output_qk": 1, "mask_filter_value": -4 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float16", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 257, 64], "dtype": "float16", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 257, 64], "dtype": "float16", "dist": "normal", "seed": 327, "scale": 0.2 },
"maskIndexT": { "dtype": "int32", "shape": [1, 257], "data": { "kind": "cycle", "values": [1, 0, 1] } }
},
"outputs": {
"outputT": { "shape": [1, 1, 384], "dtype": "float16" },
"qkT": { "dtype": "float16", "shape": [1, 6, 1, 257] }
},
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes + args.maskBytes + args.qkBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b1-h6-kv256-d32-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 256, "headDim": 32 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 192], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 256, 32], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 256, 32], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 192], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b1-h6-kv256-d128-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 256, "headDim": 128 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 768], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 256, 128], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 256, 128], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 768], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b1-h6-kv256-d256-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 256, "headDim": 256 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 1536], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 256, 256], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 256, 256], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 1536], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b1-h6-kv1500-d64-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 6, "keys": 1500, "headDim": 64 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [1, 1, 384], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 6, 1500, 64], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 6, 1500, 64], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 384], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b2-h6-kv1500-d64-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 2, "heads": 6, "keys": 1500, "headDim": 64 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [2, 1, 384], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [2, 6, 1500, 64], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [2, 6, 1500, 64], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [2, 1, 384], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "cross-b4-h6-kv1500-d64-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 4, "heads": 6, "keys": 1500, "headDim": 64 },
"attrs": { "num_heads": 6 },
"inputs": {
"queryT": { "shape": [4, 1, 384], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [4, 6, 1500, 64], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [4, 6, 1500, 64], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [4, 1, 384], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "qk-policy-b1-h4-kv256-d512-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 4, "keys": 256, "headDim": 512 },
"attrs": { "num_heads": 4 },
"inputs": {
"queryT": { "shape": [1, 1, 2048], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 4, 256, 512], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 4, 256, 512], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 2048], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "qk-policy-b1-h2-kv256-d1024-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 2, "keys": 256, "headDim": 1024 },
"attrs": { "num_heads": 2 },
"inputs": {
"queryT": { "shape": [1, 1, 2048], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 2, 256, 1024], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 2, 256, 1024], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 2048], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "qk-policy-b1-h15-kv256-d128-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 15, "keys": 256, "headDim": 128 },
"attrs": { "num_heads": 15 },
"inputs": {
"queryT": { "shape": [1, 1, 1920], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 15, 256, 128], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 15, 256, 128], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 1920], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "qk-policy-b1-h16-kv256-d128-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 16, "keys": 256, "headDim": 128 },
"attrs": { "num_heads": 16 },
"inputs": {
"queryT": { "shape": [1, 1, 2048], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 16, 256, 128], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 16, 256, 128], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 2048], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "qk-policy-b1-h17-kv256-d128-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 17, "keys": 256, "headDim": 128 },
"attrs": { "num_heads": 17 },
"inputs": {
"queryT": { "shape": [1, 1, 2176], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 17, 256, 128], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 17, 256, 128], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 2176], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "qk-policy-b1-h15-kv1500-d128-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 15, "keys": 1500, "headDim": 128 },
"attrs": { "num_heads": 15 },
"inputs": {
"queryT": { "shape": [1, 1, 1920], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 15, 1500, 128], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 15, 1500, 128], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 1920], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "qk-policy-b1-h16-kv1500-d128-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 16, "keys": 1500, "headDim": 128 },
"attrs": { "num_heads": 16 },
"inputs": {
"queryT": { "shape": [1, 1, 2048], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 16, 1500, 128], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 16, 1500, 128], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 2048], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
},
{
"name": "qk-policy-b1-h17-kv1500-d128-f32",
"preset": "smoke",
"vars": { "elemBytes": 4, "qkBytes": 0, "batch": 1, "heads": 17, "keys": 1500, "headDim": 128 },
"attrs": { "num_heads": 17 },
"inputs": {
"queryT": { "shape": [1, 1, 2176], "dtype": "float32", "dist": "normal", "seed": 325, "scale": 0.2 },
"keyT": { "shape": [1, 17, 1500, 128], "dtype": "float32", "dist": "normal", "seed": 326, "scale": 0.2 },
"valueT": { "shape": [1, 17, 1500, 128], "dtype": "float32", "dist": "normal", "seed": 327, "scale": 0.2 }
},
"outputs": { "outputT": { "shape": [1, 1, 2176], "dtype": "float32" } },
"bench": {
"metrics": [
{
"type": "bandwidth",
"value": "2 * args.batch * args.heads * args.headDim * (args.keys + 1) * args.elemBytes",
"provenance": "logical"
}
]
}
}
]
}