| { |
| "cases": [ |
| { |
| "name": "ort_gate_float", |
| "provenance": { |
| "source": "ORT: onnxruntime/test/contrib_ops/engram_ops_test.cc", |
| "test": "EngramOpsTest.EngramGateFloat", |
| "notes": "The upstream tiny case verbatim: key {0, 2.5}, query {3, 4}, value {2, -1.5}, unit scales, one token and one hyper-connection. Expected values recomputed in float32 from the upstream kernel's own ordering." |
| }, |
| "attrs": { "epsilon": 0.00001 }, |
| "inputs": { |
| "keyT": { "dtype": "float32", "shape": [1, 1, 1, 2], "data": { "kind": "values", "values": [0.0, 2.5] } }, |
| "queryT": { "dtype": "float32", "shape": [1, 1, 1, 2], "data": { "kind": "values", "values": [3.0, 4.0] } }, |
| "valueT": { "dtype": "float32", "shape": [1, 1, 2], "data": { "kind": "values", "values": [2.0, -1.5] } }, |
| "keyNormScaleT": { "dtype": "float32", "shape": [1, 2], "data": { "kind": "values", "values": [1.0, 1.0] } }, |
| "queryNormScaleT": { "dtype": "float32", "shape": [1, 2], "data": { "kind": "values", "values": [1.0, 1.0] } } |
| }, |
| "outputs": { |
| "outputT": { |
| "dtype": "float32", |
| "shape": [1, 1, 1, 2], |
| "data": { "kind": "values", "values": [1.4867780208587646, -1.1150834560394287] }, |
| "tolerance": 0.000002, |
| "relTolerance": 0.00002 |
| } |
| } |
| }, |
| { |
| "name": "ort_gate_float16", |
| "provenance": { |
| "source": "ORT: onnxruntime/test/contrib_ops/engram_ops_test.cc", |
| "test": "EngramOpsTest.EngramGateFloat16", |
| "notes": "The upstream tiny case verbatim: key {0, 2.5}, query {3, 4}, value {2, -1.5}, unit scales, one token and one hyper-connection. Expected values recomputed in float32 from the upstream kernel's own ordering." |
| }, |
| "attrs": { "epsilon": 0.00001 }, |
| "inputs": { |
| "keyT": { "dtype": "float16", "shape": [1, 1, 1, 2], "data": { "kind": "values", "values": [0.0, 2.5] } }, |
| "queryT": { "dtype": "float16", "shape": [1, 1, 1, 2], "data": { "kind": "values", "values": [3.0, 4.0] } }, |
| "valueT": { "dtype": "float16", "shape": [1, 1, 2], "data": { "kind": "values", "values": [2.0, -1.5] } }, |
| "keyNormScaleT": { "dtype": "float16", "shape": [1, 2], "data": { "kind": "values", "values": [1.0, 1.0] } }, |
| "queryNormScaleT": { "dtype": "float16", "shape": [1, 2], "data": { "kind": "values", "values": [1.0, 1.0] } } |
| }, |
| "outputs": { |
| "outputT": { |
| "dtype": "float16", |
| "shape": [1, 1, 1, 2], |
| "data": { "kind": "values", "values": [1.486328125, -1.115234375] }, |
| "tolerance": 0.0005, |
| "relTolerance": 0.002 |
| } |
| } |
| }, |
| { |
| "name": "ort_zero_dot_product", |
| "provenance": { |
| "source": "ORT: onnxruntime/test/contrib_ops/engram_ops_test.cc", |
| "test": "EngramOpsTest.EngramGateZeroDotProduct", |
| "notes": "Orthogonal key and query make the dot product vanish, and the gate must be exactly 0.5 rather than sigmoid(sqrt(1e-6)). A copysign spelling of the signed square root fails this case and nothing else." |
| }, |
| "attrs": { "epsilon": 0.00001 }, |
| "inputs": { |
| "keyT": { "dtype": "float32", "shape": [1, 1, 1, 2], "data": { "kind": "values", "values": [1.0, 0.0] } }, |
| "queryT": { "dtype": "float32", "shape": [1, 1, 1, 2], "data": { "kind": "values", "values": [0.0, 1.0] } }, |
| "valueT": { "dtype": "float32", "shape": [1, 1, 2], "data": { "kind": "values", "values": [1.0, -1.0] } }, |
| "keyNormScaleT": { "dtype": "float32", "shape": [1, 2], "data": { "kind": "values", "values": [1.0, 1.0] } }, |
| "queryNormScaleT": { "dtype": "float32", "shape": [1, 2], "data": { "kind": "values", "values": [1.0, 1.0] } } |
| }, |
| "outputs": { |
| "outputT": { |
| "dtype": "float32", |
| "shape": [1, 1, 1, 2], |
| "data": { "kind": "values", "values": [0.5, -0.5] }, |
| "tolerance": 0.00001, |
| "relTolerance": 0.00001 |
| } |
| } |
| }, |
| { |
| "name": "ort_vectorized_h4_float", |
| "provenance": { |
| "source": "ORT: onnxruntime/test/contrib_ops/engram_ops_test.cc", |
| "test": "EngramOpsTest.EngramGateVectorizedFloat", |
| "notes": "Upstream's vectorized case verbatim, including its bounded sine generator: batch 1, sequence 2, hc_mult 2, hidden 4, with distinct per-stream norm scales so a wrong scale row is visible. Expected values recomputed in float32." |
| }, |
| "attrs": { "epsilon": 0.00001 }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float32", |
| "shape": [1, 2, 2, 4], |
| "data": { |
| "kind": "values", |
| "values": [-0.7833269238471985, -0.5646424293518066, -0.295520156621933, 5.960464477539063e-8, 0.29552027583122253, 0.5646424889564514, 0.7833269834518433, 0.9320391416549683, 0.9974949955940247, 0.9738476276397705, 0.8632094264030457, 0.6754631400108337, 0.4273796081542969, 0.14112000167369843, -0.15774588286876678, -0.4425203502178192] |
| } |
| }, |
| "queryT": { |
| "dtype": "float32", |
| "shape": [1, 2, 2, 4], |
| "data": { |
| "kind": "values", |
| "values": [0.9320390820503235, 0.81341552734375, 0.6442177295684814, 0.434965580701828, 0.19866937398910522, -0.04997912049293518, -0.295520156621933, -0.5226871967315674, -0.7173560857772827, -0.8674232363700867, -0.9635581374168396, -0.9997837543487549, -0.9738476276397705, -0.8873624205589294, -0.745705246925354, -0.5576837658882141] |
| } |
| }, |
| "valueT": { |
| "dtype": "float32", |
| "shape": [1, 2, 4], |
| "data": { |
| "kind": "values", |
| "values": [0.3894183337688446, 0.681638777256012, 0.8912073373794556, 0.9927129745483398, 0.9738476276397705, 0.8368987441062927, 0.5984721779823303, 0.28747788071632385] |
| } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 4], |
| "data": { |
| "kind": "values", |
| "values": [0.5646424889564514, 0.6442177295684814, 0.7173560857772827, 0.7833269238471985, 0.8414710164070129, 0.8912073373794556, 0.9320390820503235, 0.9635581374168396] |
| } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 4], |
| "data": { |
| "kind": "values", |
| "values": [0.9854497313499451, 0.9489846229553223, 0.8912073373794556, 0.8134154677391052, 0.7173560857772827, 0.605186402797699, 0.47942548990249634, 0.3428977131843567] |
| } |
| } |
| }, |
| "outputs": { |
| "outputT": { |
| "dtype": "float32", |
| "shape": [1, 2, 2, 4], |
| "data": { |
| "kind": "values", |
| "values": [0.10116856545209885, 0.17708569765090942, 0.23153036832809448, 0.2579009234905243, 0.1250687837600708, 0.21892069280147552, 0.28622743487358093, 0.3188278377056122, 0.2453785240650177, 0.21087177097797394, 0.15079589188098907, 0.07243525236845016, 0.3465985059738159, 0.2978575527667999, 0.21300002932548523, 0.10231518745422363] |
| }, |
| "tolerance": 0.000002, |
| "relTolerance": 0.00002 |
| } |
| } |
| }, |
| { |
| "name": "ort_vectorized_h4_float16", |
| "provenance": { |
| "source": "ORT: onnxruntime/test/contrib_ops/engram_ops_test.cc", |
| "test": "EngramOpsTest.EngramGateVectorizedFloat16", |
| "notes": "Upstream's vectorized case verbatim, including its bounded sine generator: batch 1, sequence 2, hc_mult 2, hidden 4, with distinct per-stream norm scales so a wrong scale row is visible. Expected values recomputed in float32." |
| }, |
| "attrs": { "epsilon": 0.00001 }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float16", |
| "shape": [1, 2, 2, 4], |
| "data": { |
| "kind": "values", |
| "values": [-0.783203125, -0.564453125, -0.29541015625, 5.960464477539063e-8, 0.29541015625, 0.564453125, 0.783203125, 0.93212890625, 0.99755859375, 0.9736328125, 0.86328125, 0.67529296875, 0.427490234375, 0.14111328125, -0.15771484375, -0.442626953125] |
| } |
| }, |
| "queryT": { |
| "dtype": "float16", |
| "shape": [1, 2, 2, 4], |
| "data": { |
| "kind": "values", |
| "values": [0.93212890625, 0.8134765625, 0.64404296875, 0.43505859375, 0.1986083984375, -0.04998779296875, -0.29541015625, -0.5224609375, -0.71728515625, -0.8671875, -0.96337890625, -1.0, -0.9736328125, -0.88720703125, -0.74560546875, -0.5576171875] |
| } |
| }, |
| "valueT": { |
| "dtype": "float16", |
| "shape": [1, 2, 4], |
| "data": { |
| "kind": "values", |
| "values": [0.389404296875, 0.681640625, 0.89111328125, 0.99267578125, 0.9736328125, 0.8369140625, 0.5986328125, 0.28759765625] |
| } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float16", |
| "shape": [2, 4], |
| "data": { |
| "kind": "values", |
| "values": [0.564453125, 0.64404296875, 0.71728515625, 0.783203125, 0.84130859375, 0.89111328125, 0.93212890625, 0.96337890625] |
| } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float16", |
| "shape": [2, 4], |
| "data": { |
| "kind": "values", |
| "values": [0.9853515625, 0.94921875, 0.89111328125, 0.8134765625, 0.71728515625, 0.60498046875, 0.4794921875, 0.343017578125] |
| } |
| } |
| }, |
| "outputs": { |
| "outputT": { |
| "dtype": "float16", |
| "shape": [1, 2, 2, 4], |
| "data": { |
| "kind": "values", |
| "values": [0.1011962890625, 0.1771240234375, 0.2315673828125, 0.2578125, 0.125, 0.2188720703125, 0.2861328125, 0.31884765625, 0.245361328125, 0.2109375, 0.15087890625, 0.07244873046875, 0.3466796875, 0.2978515625, 0.213134765625, 0.10235595703125] |
| }, |
| "tolerance": 0.0005, |
| "relTolerance": 0.002 |
| } |
| } |
| }, |
| { |
| "name": "ort_multi_iteration_h260_float", |
| "provenance": { |
| "notes": "Upstream's multi-iteration reduction geometry: batch 1, sequence 2, hc_mult 2, hidden 260, the smallest multiple of four above both of the upstream accumulation strides. The inputs use a bounded fill rather than upstream's sine wave, so the expectation comes from the reference." |
| }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float32", |
| "shape": [1, 2, 2, 260], |
| "data": { "kind": "fillFloat32", "sinStep": 0.12, "cosStep": 0.3, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float32", |
| "shape": [1, 2, 2, 260], |
| "data": { "kind": "fillFloat32", "sinStep": 0.18, "cosStep": 0.34, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float32", |
| "shape": [1, 2, 260], |
| "data": { "kind": "fillFloat32", "sinStep": 0.24, "cosStep": 0.39999999999999997, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 260], |
| "data": { "kind": "fillFloat32", "sinStep": 0.14, "cosStep": 0.42, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 260], |
| "data": { "kind": "fillFloat32", "sinStep": 0.16, "cosStep": 0.48, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float32", "shape": [1, 2, 2, 260], "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "ort_multi_iteration_h260_float16", |
| "provenance": { "notes": "The float16 half of the same multi-iteration reduction geometry." }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float16", |
| "shape": [1, 2, 2, 260], |
| "data": { "kind": "fillFloat32", "sinStep": 0.18000000000000002, "cosStep": 0.36, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float16", |
| "shape": [1, 2, 2, 260], |
| "data": { "kind": "fillFloat32", "sinStep": 0.24000000000000002, "cosStep": 0.4, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float16", |
| "shape": [1, 2, 260], |
| "data": { |
| "kind": "fillFloat32", |
| "sinStep": 0.30000000000000004, |
| "cosStep": 0.45999999999999996, |
| "scale": 1.0 |
| } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float16", |
| "shape": [2, 260], |
| "data": { "kind": "fillFloat32", "sinStep": 0.2, "cosStep": 0.48, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float16", |
| "shape": [2, 260], |
| "data": { |
| "kind": "fillFloat32", |
| "sinStep": 0.22000000000000003, |
| "cosStep": 0.54, |
| "scale": 0.5, |
| "offset": 1.0 |
| } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float16", "shape": [1, 2, 2, 260], "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "nanowhale_decode_h320_f32", |
| "provenance": { |
| "notes": "One decoded token of the DeepSeek-V4 nanowhale geometry: four hyper-connection streams of 320 channels. Four rows in the whole dispatch, the launch-bound end of the operator." |
| }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float32", |
| "shape": [1, 1, 4, 320], |
| "data": { |
| "kind": "fillFloat32", |
| "sinStep": 0.24000000000000002, |
| "cosStep": 0.42000000000000004, |
| "scale": 1.0 |
| } |
| }, |
| "queryT": { |
| "dtype": "float32", |
| "shape": [1, 1, 4, 320], |
| "data": { "kind": "fillFloat32", "sinStep": 0.30000000000000004, "cosStep": 0.46, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float32", |
| "shape": [1, 1, 320], |
| "data": { "kind": "fillFloat32", "sinStep": 0.36, "cosStep": 0.52, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float32", |
| "shape": [4, 320], |
| "data": { "kind": "fillFloat32", "sinStep": 0.26, "cosStep": 0.54, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float32", |
| "shape": [4, 320], |
| "data": { "kind": "fillFloat32", "sinStep": 0.28, "cosStep": 0.6, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float32", "shape": [1, 1, 4, 320], "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "nanowhale_prefill_s5_hc3_h320_f16", |
| "provenance": { |
| "notes": "Fifteen rows of 320 at three streams: neither the row count nor the stream count divides the rows a workgroup carries, so the trailing lane groups fold an empty row." |
| }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float16", |
| "shape": [1, 5, 3, 320], |
| "data": { "kind": "fillFloat32", "sinStep": 0.3, "cosStep": 0.48, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float16", |
| "shape": [1, 5, 3, 320], |
| "data": { "kind": "fillFloat32", "sinStep": 0.36, "cosStep": 0.52, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float16", |
| "shape": [1, 5, 320], |
| "data": { "kind": "fillFloat32", "sinStep": 0.42, "cosStep": 0.58, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float16", |
| "shape": [3, 320], |
| "data": { "kind": "fillFloat32", "sinStep": 0.31999999999999995, "cosStep": 0.6, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float16", |
| "shape": [3, 320], |
| "data": { |
| "kind": "fillFloat32", |
| "sinStep": 0.33999999999999997, |
| "cosStep": 0.6599999999999999, |
| "scale": 0.5, |
| "offset": 1.0 |
| } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float16", "shape": [1, 5, 3, 320], "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "v4flash_decode_h4096_f32", |
| "provenance": { |
| "notes": "One decoded token of the DeepSeek-V4 v4flash geometry: four streams of 4096 channels, the widest row that still stages in registers." |
| }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float32", |
| "shape": [1, 1, 4, 4096], |
| "data": { "kind": "fillFloat32", "sinStep": 0.32, "cosStep": 0.5, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float32", |
| "shape": [1, 1, 4, 4096], |
| "data": { "kind": "fillFloat32", "sinStep": 0.38, "cosStep": 0.54, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float32", |
| "shape": [1, 1, 4096], |
| "data": { "kind": "fillFloat32", "sinStep": 0.44, "cosStep": 0.6, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float32", |
| "shape": [4, 4096], |
| "data": { |
| "kind": "fillFloat32", |
| "sinStep": 0.33999999999999997, |
| "cosStep": 0.62, |
| "scale": 0.5, |
| "offset": 1.0 |
| } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float32", |
| "shape": [4, 4096], |
| "data": { "kind": "fillFloat32", "sinStep": 0.36, "cosStep": 0.6799999999999999, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float32", "shape": [1, 1, 4, 4096], "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "v4flash_decode_h4096_f16", |
| "provenance": { "notes": "The float16 half of the v4flash decode geometry." }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float16", |
| "shape": [1, 1, 4, 4096], |
| "data": { "kind": "fillFloat32", "sinStep": 0.38, "cosStep": 0.56, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float16", |
| "shape": [1, 1, 4, 4096], |
| "data": { "kind": "fillFloat32", "sinStep": 0.44, "cosStep": 0.6, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float16", |
| "shape": [1, 1, 4096], |
| "data": { "kind": "fillFloat32", "sinStep": 0.5, "cosStep": 0.6599999999999999, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float16", |
| "shape": [4, 4096], |
| "data": { "kind": "fillFloat32", "sinStep": 0.4, "cosStep": 0.6799999999999999, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float16", |
| "shape": [4, 4096], |
| "data": { "kind": "fillFloat32", "sinStep": 0.42, "cosStep": 0.74, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float16", "shape": [1, 1, 4, 4096], "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "batched_hc2_h64_f32", |
| "provenance": { |
| "notes": "Batch 3, sequence 5, two streams of 64 channels: a row is far narrower than a subgroup here, so several rows fold inside one subgroup and a wrong batch, token or stream index moves the gate." |
| }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float32", |
| "shape": [3, 5, 2, 64], |
| "data": { "kind": "fillFloat32", "sinStep": 0.42, "cosStep": 0.6, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float32", |
| "shape": [3, 5, 2, 64], |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.64, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float32", |
| "shape": [3, 5, 64], |
| "data": { "kind": "fillFloat32", "sinStep": 0.54, "cosStep": 0.7, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 64], |
| "data": { |
| "kind": "fillFloat32", |
| "sinStep": 0.43999999999999995, |
| "cosStep": 0.72, |
| "scale": 0.5, |
| "offset": 1.0 |
| } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 64], |
| "data": { |
| "kind": "fillFloat32", |
| "sinStep": 0.45999999999999996, |
| "cosStep": 0.78, |
| "scale": 0.5, |
| "offset": 1.0 |
| } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float32", "shape": [3, 5, 2, 64], "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "batched_hc3_h128_f16", |
| "provenance": { "notes": "Batch 2, sequence 3, three streams of 128 channels in float16." }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float16", |
| "shape": [2, 3, 3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.44, "cosStep": 0.62, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float16", |
| "shape": [2, 3, 3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.5, "cosStep": 0.66, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float16", |
| "shape": [2, 3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.56, "cosStep": 0.72, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float16", |
| "shape": [3, 128], |
| "data": { |
| "kind": "fillFloat32", |
| "sinStep": 0.45999999999999996, |
| "cosStep": 0.74, |
| "scale": 0.5, |
| "offset": 1.0 |
| } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float16", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.8, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float16", "shape": [2, 3, 3, 128], "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "hc_one_h512_f32", |
| "provenance": { |
| "notes": "A single hyper-connection stream: the degenerate case where the per-stream scale lookup and a shared scale agree, kept because upstream's own smallest tests are shaped this way." |
| }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float32", |
| "shape": [2, 2, 1, 512], |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.6599999999999999, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float32", |
| "shape": [2, 2, 1, 512], |
| "data": { "kind": "fillFloat32", "sinStep": 0.54, "cosStep": 0.7, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float32", |
| "shape": [2, 2, 512], |
| "data": { "kind": "fillFloat32", "sinStep": 0.6, "cosStep": 0.76, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float32", |
| "shape": [1, 512], |
| "data": { "kind": "fillFloat32", "sinStep": 0.5, "cosStep": 0.78, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float32", |
| "shape": [1, 512], |
| "data": { "kind": "fillFloat32", "sinStep": 0.52, "cosStep": 0.84, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float32", "shape": [2, 2, 1, 512], "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "wide_h8192_f16", |
| "provenance": { |
| "notes": "8192 channels per row: the row fills a whole workgroup and every lane stages the maximum eight vector words." |
| }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float16", |
| "shape": [1, 1, 2, 8192], |
| "data": { "kind": "fillFloat32", "sinStep": 0.54, "cosStep": 0.72, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float16", |
| "shape": [1, 1, 2, 8192], |
| "data": { "kind": "fillFloat32", "sinStep": 0.6000000000000001, "cosStep": 0.76, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float16", |
| "shape": [1, 1, 8192], |
| "data": { "kind": "fillFloat32", "sinStep": 0.66, "cosStep": 0.8200000000000001, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float16", |
| "shape": [2, 8192], |
| "data": { "kind": "fillFloat32", "sinStep": 0.56, "cosStep": 0.8400000000000001, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float16", |
| "shape": [2, 8192], |
| "data": { "kind": "fillFloat32", "sinStep": 0.5800000000000001, "cosStep": 0.9, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float16", "shape": [1, 1, 2, 8192], "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "wide_h16384_f32", |
| "provenance": { |
| "notes": "16384 channels per row: too wide to stage, so the statistic pass and the store pass each walk the row." |
| }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float32", |
| "shape": [1, 1, 2, 16384], |
| "data": { "kind": "fillFloat32", "sinStep": 0.6, "cosStep": 0.78, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float32", |
| "shape": [1, 1, 2, 16384], |
| "data": { "kind": "fillFloat32", "sinStep": 0.6599999999999999, "cosStep": 0.82, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float32", |
| "shape": [1, 1, 16384], |
| "data": { "kind": "fillFloat32", "sinStep": 0.72, "cosStep": 0.8799999999999999, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 16384], |
| "data": { "kind": "fillFloat32", "sinStep": 0.62, "cosStep": 0.8999999999999999, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 16384], |
| "data": { "kind": "fillFloat32", "sinStep": 0.64, "cosStep": 0.96, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float32", "shape": [1, 1, 2, 16384], "tolerance": 0.000002, "relTolerance": 0.00005 } |
| } |
| }, |
| { |
| "name": "scalar_h6_f32", |
| "provenance": { |
| "notes": "Six channels per row: not a multiple of four, so the scalar route runs, and narrow enough that one lane group covers three rows of a subgroup." |
| }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float32", |
| "shape": [1, 5, 3, 6], |
| "data": { "kind": "fillFloat32", "sinStep": 0.62, "cosStep": 0.8, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float32", |
| "shape": [1, 5, 3, 6], |
| "data": { "kind": "fillFloat32", "sinStep": 0.6799999999999999, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float32", |
| "shape": [1, 5, 6], |
| "data": { "kind": "fillFloat32", "sinStep": 0.74, "cosStep": 0.8999999999999999, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float32", |
| "shape": [3, 6], |
| "data": { "kind": "fillFloat32", "sinStep": 0.64, "cosStep": 0.9199999999999999, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float32", |
| "shape": [3, 6], |
| "data": { "kind": "fillFloat32", "sinStep": 0.66, "cosStep": 0.98, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float32", "shape": [1, 5, 3, 6], "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "scalar_h130_f16", |
| "provenance": { "notes": "130 channels per row in float16: the scalar route with several words per lane." }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float16", |
| "shape": [2, 3, 2, 130], |
| "data": { "kind": "fillFloat32", "sinStep": 0.68, "cosStep": 0.8600000000000001, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float16", |
| "shape": [2, 3, 2, 130], |
| "data": { "kind": "fillFloat32", "sinStep": 0.74, "cosStep": 0.9, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float16", |
| "shape": [2, 3, 130], |
| "data": { "kind": "fillFloat32", "sinStep": 0.8, "cosStep": 0.96, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float16", |
| "shape": [2, 130], |
| "data": { "kind": "fillFloat32", "sinStep": 0.7000000000000001, "cosStep": 0.98, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float16", |
| "shape": [2, 130], |
| "data": { "kind": "fillFloat32", "sinStep": 0.7200000000000001, "cosStep": 1.04, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float16", "shape": [2, 3, 2, 130], "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "scalar_h1_f32", |
| "provenance": { |
| "notes": "One channel per row: a single lane owns the whole row, so no fold runs at all and the statistic is the lane's own accumulator." |
| }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float32", |
| "shape": [1, 4, 2, 1], |
| "data": { "kind": "fillFloat32", "sinStep": 0.72, "cosStep": 0.8999999999999999, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float32", |
| "shape": [1, 4, 2, 1], |
| "data": { "kind": "fillFloat32", "sinStep": 0.78, "cosStep": 0.94, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float32", |
| "shape": [1, 4, 1], |
| "data": { "kind": "fillFloat32", "sinStep": 0.84, "cosStep": 1.0, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 1], |
| "data": { "kind": "fillFloat32", "sinStep": 0.74, "cosStep": 1.02, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 1], |
| "data": { "kind": "fillFloat32", "sinStep": 0.76, "cosStep": 1.08, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float32", "shape": [1, 4, 2, 1], "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "scalar_wide_h2050_f32", |
| "provenance": { |
| "notes": "2050 channels per row: an unvectorizable width too wide to stage, the streaming scalar route." |
| }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float32", |
| "shape": [1, 1, 2, 2050], |
| "data": { "kind": "fillFloat32", "sinStep": 0.74, "cosStep": 0.9199999999999999, "scale": 1.0 } |
| }, |
| "queryT": { |
| "dtype": "float32", |
| "shape": [1, 1, 2, 2050], |
| "data": { "kind": "fillFloat32", "sinStep": 0.8, "cosStep": 0.96, "scale": 1.0 } |
| }, |
| "valueT": { |
| "dtype": "float32", |
| "shape": [1, 1, 2050], |
| "data": { "kind": "fillFloat32", "sinStep": 0.86, "cosStep": 1.02, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 2050], |
| "data": { "kind": "fillFloat32", "sinStep": 0.76, "cosStep": 1.04, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 2050], |
| "data": { "kind": "fillFloat32", "sinStep": 0.78, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float32", "shape": [1, 1, 2, 2050], "tolerance": 0.000002, "relTolerance": 0.00005 } |
| } |
| }, |
| { |
| "name": "epsilon_dominant_h8_f32", |
| "provenance": { |
| "notes": "An epsilon of 1 against key and query rows two orders of magnitude smaller: the epsilon term, not the mean of squares, sets both inverse-RMS factors, which pins epsilon to the normalization denominators and away from the gate's own floor." |
| }, |
| "attrs": { "epsilon": 1 }, |
| "inputs": { |
| "keyT": { |
| "dtype": "float32", |
| "shape": [1, 3, 2, 8], |
| "data": { "kind": "fillFloat32", "sinStep": 0.8, "cosStep": 0.98, "scale": 0.01 } |
| }, |
| "queryT": { |
| "dtype": "float32", |
| "shape": [1, 3, 2, 8], |
| "data": { "kind": "fillFloat32", "sinStep": 0.8600000000000001, "cosStep": 1.02, "scale": 0.01 } |
| }, |
| "valueT": { |
| "dtype": "float32", |
| "shape": [1, 3, 8], |
| "data": { "kind": "fillFloat32", "sinStep": 0.92, "cosStep": 1.08, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 8], |
| "data": { "kind": "fillFloat32", "sinStep": 0.8200000000000001, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "dtype": "float32", |
| "shape": [2, 8], |
| "data": { |
| "kind": "fillFloat32", |
| "sinStep": 0.8400000000000001, |
| "cosStep": 1.1600000000000001, |
| "scale": 0.5, |
| "offset": 1.0 |
| } |
| } |
| }, |
| "outputs": { |
| "outputT": { "dtype": "float32", "shape": [1, 3, 2, 8], "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h63_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 63], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 63], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 63], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 63], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 63], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 63], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h63_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 63], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 63], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 63], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 63], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 63], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 63], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h65_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 65], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h65_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 65], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h129_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 129], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 129], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 129], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 129], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 129], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 129], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h129_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 129], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 129], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 129], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 129], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 129], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 129], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h130_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 130], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 130], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 130], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 130], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 130], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 130], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h130_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 130], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 130], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 130], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 130], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 130], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 130], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h131_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 131], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h131_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 131], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h255_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 255], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 255], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 255], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 255], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 255], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 255], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h255_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 255], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 255], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 255], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 255], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 255], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 255], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h257_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 257], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 257], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 257], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 257], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 257], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 257], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float32_h257_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 257], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 257], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 257], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 257], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 257], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 257], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h63_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 63], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 63], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 63], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 63], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 63], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 63], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h63_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 63], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 63], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 63], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 63], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 63], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 63], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h65_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 65], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h65_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 65], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h129_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 129], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 129], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 129], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 129], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 129], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 129], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h129_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 129], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 129], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 129], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 129], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 129], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 129], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h130_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 130], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 130], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 130], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 130], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 130], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 130], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h130_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 130], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 130], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 130], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 130], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 130], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 130], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h131_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 131], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h131_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 131], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h255_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 255], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 255], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 255], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 255], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 255], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 255], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h255_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 255], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 255], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 255], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 255], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 255], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 255], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h257_r3", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 257], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 257], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 257], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 257], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 257], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 257], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_float16_h257_r260", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 257], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 257], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 257], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 257], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 257], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 257], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| } |
| }, |
| { |
| "name": "packing_override_float32_h65_wg64_depth1", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 65], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 65], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| }, |
| "tunables": { "WORKGROUP_SIZE": 64, "LANE_WORDS": 1 } |
| }, |
| { |
| "name": "packing_override_float32_h131_wg128_depth16", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 131], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 131], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| }, |
| "tunables": { "WORKGROUP_SIZE": 128, "LANE_WORDS": 16 } |
| }, |
| { |
| "name": "packing_override_float16_h65_wg64_depth1", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 65], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 65], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| }, |
| "tunables": { "WORKGROUP_SIZE": 64, "LANE_WORDS": 1 } |
| }, |
| { |
| "name": "packing_override_float16_h131_wg128_depth16", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 4, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 4, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [4, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [4, 131], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 4, 131], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| }, |
| "tunables": { "WORKGROUP_SIZE": 128, "LANE_WORDS": 16 } |
| }, |
| { |
| "name": "vector_depth_float32_h252_r195_wg256", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 3, 252], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 3, 252], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 252], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 252], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 252], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 3, 252], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| }, |
| { |
| "name": "vector_depth_float32_h260_r195_wg256", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 3, 260], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 3, 260], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 260], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 260], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 260], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 3, 260], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| }, |
| { |
| "name": "vector_depth_float32_h320_r129_wg256", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 43, 3, 320], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 43, 3, 320], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 43, 320], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 320], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 320], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 43, 3, 320], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| }, |
| { |
| "name": "vector_depth_float32_h516_r129_wg256", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 43, 3, 516], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 43, 3, 516], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 43, 516], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 516], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 516], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 43, 3, 516], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| }, |
| { |
| "name": "vector_depth_float32_h1028_r195_wg64", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 3, 1028], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 3, 1028], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 1028], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 1028], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 1028], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 3, 1028], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| }, |
| "tunables": { "WORKGROUP_SIZE": 64 }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| }, |
| { |
| "name": "vector_depth_float32_h320_r3_wg256", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 320], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 320], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 320], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 320], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 320], |
| "dtype": "float32", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 320], "dtype": "float32", "tolerance": 0.000002, "relTolerance": 0.00002 } |
| }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| }, |
| { |
| "name": "vector_depth_float16_h252_r195_wg256", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 3, 252], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 3, 252], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 252], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 252], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 252], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 3, 252], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| }, |
| { |
| "name": "vector_depth_float16_h260_r195_wg256", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 3, 260], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 3, 260], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 260], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 260], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 260], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 3, 260], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| }, |
| { |
| "name": "vector_depth_float16_h320_r129_wg256", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 43, 3, 320], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 43, 3, 320], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 43, 320], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 320], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 320], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 43, 3, 320], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| }, |
| { |
| "name": "vector_depth_float16_h516_r129_wg256", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 43, 3, 516], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 43, 3, 516], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 43, 516], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 516], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 516], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 43, 3, 516], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| }, |
| { |
| "name": "vector_depth_float16_h1028_r195_wg64", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 65, 3, 1028], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 65, 3, 1028], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 65, 1028], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 1028], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 1028], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 65, 3, 1028], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| }, |
| "tunables": { "WORKGROUP_SIZE": 64 }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| }, |
| { |
| "name": "vector_depth_float16_h320_r3_wg256", |
| "inputs": { |
| "keyT": { |
| "shape": [1, 1, 3, 320], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.71, "scale": 1.0 } |
| }, |
| "queryT": { |
| "shape": [1, 1, 3, 320], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.48, "cosStep": 0.84, "scale": 1.0 } |
| }, |
| "valueT": { |
| "shape": [1, 1, 320], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.59, "cosStep": 0.97, "scale": 1.0 } |
| }, |
| "keyNormScaleT": { |
| "shape": [3, 320], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.7, "cosStep": 1.1, "scale": 0.5, "offset": 1.0 } |
| }, |
| "queryNormScaleT": { |
| "shape": [3, 320], |
| "dtype": "float16", |
| "data": { "kind": "fillFloat32", "sinStep": 0.81, "cosStep": 1.23, "scale": 0.5, "offset": 1.0 } |
| } |
| }, |
| "outputs": { |
| "outputT": { "shape": [1, 1, 3, 320], "dtype": "float16", "tolerance": 0.0005, "relTolerance": 0.002 } |
| }, |
| "provenance": { |
| "notes": "Lane-depth boundary with nonuniform affine scales and hyper-connection value reuse; row and vector tails exercise shared row groups at the default dtype tolerance." |
| } |
| } |
| ] |
| } |
|
|
