{ "fixtureArrays": { "bnb4_weight_cycle_b_t": [1, 35, 69, 103, 137, 171, 205, 239, 254, 220, 186, 152, 118, 84, 50, 16, 90] }, "cases": [ { "name": "nf4_scalar_small", "attrs": { "K": 16, "N": 4, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [3, 16], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [32], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [4], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00001 } } }, { "name": "fp4_scalar_small", "attrs": { "K": 16, "N": 4, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [3, 16], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [32], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [4], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00001 } } }, { "name": "nf4_scalar_block_straddle", "attrs": { "K": 24, "N": 3, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [2, 24], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [36], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [5], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [2, 3], "tolerance": 0.00001 } } }, { "name": "nf4_scalar_odd_k", "attrs": { "K": 33, "N": 5, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [3, 33], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [83], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [11], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [3, 5], "tolerance": 0.00001 } } }, { "name": "nf4_gemv_decode", "attrs": { "K": 128, "N": 64, "block_size": 64, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [1, 128], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [4096], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [128], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [1, 64], "tolerance": 0.00002 } } }, { "name": "fp4_gemv_decode", "attrs": { "K": 64, "N": 32, "block_size": 32, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [1, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [1024], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [64], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [1, 32], "tolerance": 0.00001 } } }, { "name": "nf4_gemv_ragged_k", "attrs": { "K": 100, "N": 12, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [1, 100], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [600], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [75], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [1, 12], "tolerance": 0.00001 } } }, { "name": "nf4_tiled_prefill", "attrs": { "K": 64, "N": 48, "block_size": 32, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [32, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [1536], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [96], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [32, 48], "tolerance": 0.00002 } } }, { "name": "fp4_tiled_prefill", "attrs": { "K": 64, "N": 48, "block_size": 32, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [32, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [1536], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [96], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [32, 48], "tolerance": 0.00002 } } }, { "name": "nf4_sgmat_tall_aligned", "attrs": { "K": 64, "N": 64, "block_size": 32, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [128, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [128], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [128, 64], "tolerance": 0.00002 } } }, { "name": "fp4_sgmat_aligned", "attrs": { "K": 64, "N": 64, "block_size": 32, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [64, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [128], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [64, 64], "tolerance": 0.00002 } } }, { "name": "nf4_tiled_tail", "attrs": { "K": 33, "N": 19, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [20, 33], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [314], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [40], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [20, 19], "tolerance": 0.00001 } } }, { "name": "nf4_tiled_tail_bk32", "attrs": { "K": 33, "N": 19, "block_size": 16, "quant_type": 1 }, "tunables": { "PORTABLE_TILE_K": 32 }, "inputs": { "aT": { "dtype": "float32", "shape": [20, 33], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [314], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [40], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [20, 19], "tolerance": 0.00001 } } }, { "name": "fp4_tiled_tail_bk64", "attrs": { "K": 33, "N": 19, "block_size": 16, "quant_type": 0 }, "tunables": { "PORTABLE_TILE_K": 64 }, "inputs": { "aT": { "dtype": "float32", "shape": [20, 33], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [314], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [40], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [20, 19], "tolerance": 0.00001 } } }, { "name": "nf4_f16_scalar", "attrs": { "K": 32, "N": 8, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [3, 32], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [128], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [16], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [3, 8], "tolerance": 0.02 } } }, { "name": "nf4_f16_gemv", "attrs": { "K": 64, "N": 16, "block_size": 32, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [1, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [512], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [32], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [1, 16], "tolerance": 0.02 } } }, { "name": "nf4_f16_tiled", "attrs": { "K": 32, "N": 16, "block_size": 32, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [16, 32], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [256], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [16], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [16, 16], "tolerance": 0.02 } } }, { "name": "nf4_f16_tiled_longk_m32_k512_n32", "attrs": { "K": 512, "N": 32, "block_size": 64, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [32, 512], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [8192], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [32, 32], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "The other f16 fixtures all run K <= 64, where an f16 accumulator is indistinguishable from an f32 one. This one accumulates over K=512 so the tiled path's f32 accumulation is actually pinned." } }, { "name": "nf4_sgmat_widened_f16", "provenance": { "notes": "A float16 request on an aligned subgroup-matrix shape widens activations to float32 around the multiply, accumulates in float32, and narrows the result afterward." }, "attrs": { "K": 64, "N": 64, "block_size": 32, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [128, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [128], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [128, 64], "tolerance": 0.002, "relTolerance": 0.002 } } }, { "name": "nf4_tiled_speculative_band_m5", "provenance": { "notes": "A five-row speculative-decoder multiply exercises the tiled route within the 2-to-15-row band, using a ragged K dimension and NF4 block-quantized weights." }, "attrs": { "K": 33, "N": 19, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [5, 33], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [314], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [40], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [5, 19], "tolerance": 0.00001 } } }, { "name": "rows_float32_q0_m2_k64_n64", "attrs": { "K": 64, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [2, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [2, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q1_m3_k128_n128", "attrs": { "K": 128, "N": 128, "block_size": 32, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [3, 128], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [8192], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [3, 128], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q0_m7_k512_n64", "attrs": { "K": 512, "N": 64, "block_size": 64, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [7, 512], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [16384], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [7, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q1_m8_k64_n128", "attrs": { "K": 64, "N": 128, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [8, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [4096], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [8, 128], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q0_m9_k128_n64", "attrs": { "K": 128, "N": 64, "block_size": 32, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [9, 128], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [4096], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [9, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q1_m15_k512_n128", "attrs": { "K": 512, "N": 128, "block_size": 64, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [15, 512], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [32768], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [1024], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [15, 128], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q0_m16_k64_n64", "attrs": { "K": 64, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [16, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [16, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q1_m17_k128_n128", "attrs": { "K": 128, "N": 128, "block_size": 32, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [17, 128], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [8192], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [17, 128], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q0_m24_k512_n64", "attrs": { "K": 512, "N": 64, "block_size": 64, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [24, 512], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [16384], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [24, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q1_m31_k64_n128", "attrs": { "K": 64, "N": 128, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [31, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [4096], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [31, 128], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q0_m33_k128_n64", "attrs": { "K": 128, "N": 64, "block_size": 32, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [33, 128], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [4096], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [33, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q1_m63_k512_n128", "attrs": { "K": 512, "N": 128, "block_size": 64, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [63, 512], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [32768], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [1024], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [63, 128], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q0_m65_k64_n64", "attrs": { "K": 64, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [65, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [65, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float32_q1_m129_k128_n128", "attrs": { "K": 128, "N": 128, "block_size": 32, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [129, 128], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [8192], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [129, 128], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q0_m2_k64_n64", "attrs": { "K": 64, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float16", "shape": [2, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [2, 64], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q1_m3_k128_n128", "attrs": { "K": 128, "N": 128, "block_size": 32, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [3, 128], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [8192], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [3, 128], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q0_m7_k512_n64", "attrs": { "K": 512, "N": 64, "block_size": 64, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float16", "shape": [7, 512], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [16384], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [7, 64], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q1_m8_k64_n128", "attrs": { "K": 64, "N": 128, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [8, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [4096], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [8, 128], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q0_m9_k128_n64", "attrs": { "K": 128, "N": 64, "block_size": 32, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float16", "shape": [9, 128], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [4096], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [9, 64], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q1_m15_k512_n128", "attrs": { "K": 512, "N": 128, "block_size": 64, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [15, 512], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [32768], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [1024], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [15, 128], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q0_m16_k64_n64", "attrs": { "K": 64, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float16", "shape": [16, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [16, 64], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q1_m17_k128_n128", "attrs": { "K": 128, "N": 128, "block_size": 32, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [17, 128], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [8192], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [17, 128], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q0_m24_k512_n64", "attrs": { "K": 512, "N": 64, "block_size": 64, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float16", "shape": [24, 512], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [16384], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [24, 64], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q1_m31_k64_n128", "attrs": { "K": 64, "N": 128, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [31, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [4096], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [31, 128], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q0_m33_k128_n64", "attrs": { "K": 128, "N": 64, "block_size": 32, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float16", "shape": [33, 128], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [4096], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [33, 64], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q1_m63_k512_n128", "attrs": { "K": 512, "N": 128, "block_size": 64, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [63, 512], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [32768], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [1024], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [63, 128], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q0_m65_k64_n64", "attrs": { "K": 64, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float16", "shape": [65, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [65, 64], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "rows_float16_q1_m129_k128_n128", "attrs": { "K": 128, "N": 128, "block_size": 32, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [129, 128], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [8192], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [512], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [129, 128], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "matrix_tunable_float32_q0_m15_k192_n64_32_8", "attrs": { "K": 192, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [15, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [6144], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [768], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [15, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 32, "SGMAT_TILE_K": 8 } }, { "name": "matrix_tunable_float32_q0_m128_k192_n64_32_8", "attrs": { "K": 192, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [128, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [6144], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [768], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [128, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 32, "SGMAT_TILE_K": 8 } }, { "name": "matrix_tunable_float16_q1_m15_k192_n128_64_16", "attrs": { "K": 192, "N": 128, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [15, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [12288], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [1536], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [15, 128], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 64, "SGMAT_TILE_K": 16 } }, { "name": "matrix_tunable_float16_q1_m128_k192_n128_64_16", "attrs": { "K": 192, "N": 128, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [128, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [12288], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [1536], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [128, 128], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 64, "SGMAT_TILE_K": 16 } }, { "name": "matrix_tunable_float32_q0_m15_k192_n192_96_24", "attrs": { "K": 192, "N": 192, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [15, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [18432], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [2304], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [15, 192], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 96, "SGMAT_TILE_K": 24 } }, { "name": "matrix_tunable_float32_q0_m128_k192_n192_96_24", "attrs": { "K": 192, "N": 192, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [128, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [18432], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [2304], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [128, 192], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 96, "SGMAT_TILE_K": 24 } }, { "name": "matrix_tunable_float16_q1_m15_k192_n256_128_64", "attrs": { "K": 192, "N": 256, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [15, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [24576], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [3072], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [15, 256], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 128, "SGMAT_TILE_K": 64 } }, { "name": "matrix_tunable_float16_q1_m128_k192_n256_128_64", "attrs": { "K": 192, "N": 256, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [128, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [24576], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [3072], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [128, 256], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 128, "SGMAT_TILE_K": 64 } }, { "name": "matrix_tunable_float32_q0_m15_k192_n64_32_64", "attrs": { "K": 192, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [15, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [6144], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [768], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [15, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 32, "SGMAT_TILE_K": 64 } }, { "name": "matrix_tunable_float32_q0_m128_k192_n64_32_64", "attrs": { "K": 192, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [128, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [6144], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [768], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [128, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 32, "SGMAT_TILE_K": 64 } }, { "name": "matrix_tunable_float16_q1_m15_k192_n256_128_8", "attrs": { "K": 192, "N": 256, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [15, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [24576], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [3072], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [15, 256], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 128, "SGMAT_TILE_K": 8 } }, { "name": "matrix_tunable_float16_q1_m128_k192_n256_128_8", "attrs": { "K": 192, "N": 256, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [128, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [24576], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [3072], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [128, 256], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 128, "SGMAT_TILE_K": 8 } }, { "name": "matrix_tunable_float32_q0_m15_k192_n128_64_24", "attrs": { "K": 192, "N": 128, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [15, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [12288], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [1536], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [15, 128], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 64, "SGMAT_TILE_K": 24 } }, { "name": "matrix_tunable_float32_q0_m128_k192_n128_64_24", "attrs": { "K": 192, "N": 128, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [128, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [12288], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [1536], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [128, 128], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 64, "SGMAT_TILE_K": 24 } }, { "name": "matrix_tunable_float16_q1_m15_k192_n192_96_16", "attrs": { "K": 192, "N": 192, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [15, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [18432], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [2304], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [15, 192], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 96, "SGMAT_TILE_K": 16 } }, { "name": "matrix_tunable_float16_q1_m128_k192_n192_96_16", "attrs": { "K": 192, "N": 192, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [128, 192], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [18432], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [2304], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [128, 192], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "SGMAT_TILE_COLS": 96, "SGMAT_TILE_K": 16 } }, { "name": "row_and_weight_tails_float32_q1_m9_k31_n65", "attrs": { "K": 31, "N": 65, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [9, 31], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [1008], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [126], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [9, 65], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "row_and_weight_tails_float32_q1_m33_k129_n127", "attrs": { "K": 129, "N": 127, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [33, 129], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [8192], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [1024], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [33, 127], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "row_and_weight_tails_float16_q1_m9_k31_n65", "attrs": { "K": 31, "N": 65, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [9, 31], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [1008], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [126], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [9, 65], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "row_and_weight_tails_float16_q1_m33_k129_n127", "attrs": { "K": 129, "N": 127, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [33, 129], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [8192], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [1024], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [33, 127], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "portable_f16_tunable_float16_q0_m17_k129_n65_32", "attrs": { "K": 129, "N": 65, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float16", "shape": [17, 129], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [4193], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [525], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [17, 65], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "PORTABLE_TILE_K": 32 } }, { "name": "portable_f16_tunable_float16_q0_m17_k129_n65_64", "attrs": { "K": 129, "N": 65, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float16", "shape": [17, 129], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [4193], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [525], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [17, 65], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." }, "tunables": { "PORTABLE_TILE_K": 64 } }, { "name": "empty_rows_float32_q1_m0_k32_n64", "attrs": { "K": 32, "N": 64, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float32", "shape": [0, 32], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [1024], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [128], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [0, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "empty_rows_float16_q1_m0_k32_n64", "attrs": { "K": 32, "N": 64, "block_size": 16, "quant_type": 1 }, "inputs": { "aT": { "dtype": "float16", "shape": [0, 32], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [1024], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [128], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [0, 64], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "Covers row-tile boundaries, f32 accumulation and position-varying NF4/FP4 weights on matrix and portable capability tiers." } }, { "name": "prefix_tail_float32_m95_k64_n64", "attrs": { "K": 64, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [95, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [95, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "The full-row prefix and a multi-fragment tail write disjoint rows, including the last output, with f32 accumulation." } }, { "name": "prefix_tail_float32_m191_k64_n64", "attrs": { "K": 64, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float32", "shape": [191, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float32", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float32", "shape": [191, 64], "tolerance": 0.00002, "relTolerance": 0.00001 } }, "provenance": { "notes": "The full-row prefix and a multi-fragment tail write disjoint rows, including the last output, with f32 accumulation." } }, { "name": "prefix_tail_float16_m95_k64_n64", "attrs": { "K": 64, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float16", "shape": [95, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [95, 64], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "The full-row prefix and a multi-fragment tail write disjoint rows, including the last output, with f32 accumulation." } }, { "name": "prefix_tail_float16_m191_k64_n64", "attrs": { "K": 64, "N": 64, "block_size": 16, "quant_type": 0 }, "inputs": { "aT": { "dtype": "float16", "shape": [191, 64], "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 } }, "bT": { "dtype": "uint8", "shape": [2048], "data": { "kind": "cycle", "values": { "$ref": "#/fixtureArrays/bnb4_weight_cycle_b_t" } } }, "absmaxT": { "dtype": "float16", "shape": [256], "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.07, "scale": 0.02, "offset": 0.06 } } }, "outputs": { "yT": { "dtype": "float16", "shape": [191, 64], "tolerance": 0.001, "relTolerance": 0.001 } }, "provenance": { "notes": "The full-row prefix and a multi-fragment tail write disjoint rows, including the last output, with f32 accumulation." } } ] }