{
  "cases": [
    {
      "name": "cross_plain_b1_h4_kv16_d16",
      "provenance": {
        "notes": "Cross attention with no mask and no diagnostic row: the minimum contract, where every encoder key contributes."
      },
      "attrs": { "num_heads": 4 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 64], "tolerance": 0.00002 } }
    },
    {
      "name": "cross_plain_b2_h6_kv40_d32",
      "provenance": {
        "notes": "Cross attention over a key count that is not a multiple of the split tile, so the last partition absorbs the remainder."
      },
      "attrs": { "num_heads": 6 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [2, 1, 192],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [2, 6, 40, 32],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [2, 6, 40, 32],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [2, 1, 192], "tolerance": 0.00002 } }
    },
    {
      "name": "cross_mask_b1_h4_kv16_d16",
      "provenance": {
        "notes": "Cross attention with an alternating key-padding mask. A zero entry adds the filter value, so a masked key keeps a tiny but non-zero weight."
      },
      "attrs": { "num_heads": 4 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 16], "data": { "kind": "cycle", "values": [1, 0] } }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 64], "tolerance": 0.00002 } }
    },
    {
      "name": "cross_mask_all_padded_b1_h2_kv8_d16",
      "provenance": {
        "notes": "Every mask entry is zero. The additive filter leaves the row uniform, where a knockout mask would return zeros; this case separates the two readings."
      },
      "attrs": { "num_heads": 2 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 32],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 2, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 2, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 8], "data": { "kind": "constant", "value": 0 } }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 32], "tolerance": 0.00002 } }
    },
    {
      "name": "cross_mask_filter_value_b1_h4_kv12_d16",
      "provenance": {
        "notes": "A non-default mask filter value, small enough that masked keys still carry visible weight."
      },
      "attrs": { "num_heads": 4, "mask_filter_value": -4 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 4, 12, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 4, 12, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 12], "data": { "kind": "cycle", "values": [1, 1, 0] } }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 64], "tolerance": 0.00002 } }
    },
    {
      "name": "cross_qk_b1_h4_kv16_d16",
      "provenance": {
        "notes": "Cross attention emitting the pre-softmax score row. The values are the scaled dot products, so a post-softmax reading would show every row summing to one."
      },
      "attrs": { "num_heads": 4, "output_qk": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 64], "tolerance": 0.00002 },
        "qkT": { "dtype": "float32", "shape": [1, 4, 1, 16], "tolerance": 0.00002 }
      }
    },
    {
      "name": "cross_mask_qk_b1_h4_kv20_d16",
      "provenance": {
        "notes": "The score row is emitted after the mask is added, so the masked columns sit a filter value below their neighbours."
      },
      "attrs": { "num_heads": 4, "output_qk": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 4, 20, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 4, 20, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 20], "data": { "kind": "cycle", "values": [1, 0, 1] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 64], "tolerance": 0.00002 },
        "qkT": { "dtype": "float32", "shape": [1, 4, 1, 20], "tolerance": 0.00002 }
      }
    },
    {
      "name": "cross_qk_scale_b2_h3_kv24_d32",
      "provenance": {
        "notes": "An explicit scale overrides the default reciprocal square root, and the emitted score row shows it directly."
      },
      "attrs": { "num_heads": 3, "scale": 0.125, "output_qk": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [2, 1, 96],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [2, 3, 24, 32],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [2, 3, 24, 32],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [2, 1, 96], "tolerance": 0.00002 },
        "qkT": { "dtype": "float32", "shape": [2, 3, 1, 24], "tolerance": 0.00002 }
      }
    },
    {
      "name": "cross_plain_b1_h2_kv1_d16",
      "provenance": {
        "notes": "A single encoder key: the softmax is degenerate and the output is that key's value row."
      },
      "attrs": { "num_heads": 2 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 32],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 2, 1, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 2, 1, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 32], "tolerance": 0.00002 } }
    },
    {
      "name": "cross_plain_b1_h1_kv1500_d64",
      "provenance": {
        "notes": "Whisper-scale cross attention geometry at one head, where the key count is far larger than the head dimension."
      },
      "attrs": { "num_heads": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 1, 1500, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 1, 1500, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 64], "tolerance": 0.00005 } }
    },
    {
      "name": "cross_head_size_four_b1_h4_kv8_d4",
      "provenance": {
        "notes": "Cross-attention with 4 heads and head width 4, the minimum that fills one four-element vector, over an 8-token key/value cache."
      },
      "attrs": { "num_heads": 4 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 4, 8, 4],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 4, 8, 4],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 16], "tolerance": 0.00002 } }
    },
    {
      "name": "cross_plain_f16_b1_h4_kv16_d16",
      "provenance": {
        "notes": "The float16 twin of the plain cross route: operands and output narrow, while the score and online softmax stay float32."
      },
      "attrs": { "num_heads": 4 },
      "inputs": {
        "queryT": {
          "dtype": "float16",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float16",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float16",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float16", "shape": [1, 1, 64], "tolerance": 0.003 } }
    },
    {
      "name": "cross_mask_qk_f16_b1_h4_kv20_d16",
      "provenance": {
        "notes": "Float16 operands with a float32 score row, the combination the schema allows by typing the diagnostic output independently."
      },
      "attrs": { "num_heads": 4, "output_qk": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float16",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float16",
          "shape": [1, 4, 20, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float16",
          "shape": [1, 4, 20, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 20], "data": { "kind": "cycle", "values": [1, 0, 1] } }
      },
      "outputs": {
        "outputT": { "dtype": "float16", "shape": [1, 1, 64], "tolerance": 0.003 },
        "qkT": { "dtype": "float32", "shape": [1, 4, 1, 20], "tolerance": 0.003 }
      }
    },
    {
      "name": "cross_qk_f16_row_b1_h4_kv16_d16",
      "provenance": { "notes": "A float16 score row, so the diagnostic output narrows with the operands." },
      "attrs": { "num_heads": 4, "output_qk": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float16",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float16",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float16",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": {
        "outputT": { "dtype": "float16", "shape": [1, 1, 64], "tolerance": 0.003 },
        "qkT": { "dtype": "float16", "shape": [1, 4, 1, 16], "tolerance": 0.002 }
      }
    },
    {
      "name": "self_plain_b1_h4_cap8_d16_past3",
      "provenance": {
        "notes": "Self attention appending token four into a cache of capacity eight. Only the first four rows are attended; the rest keep their past values."
      },
      "attrs": { "num_heads": 4, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [1, 4, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [1, 4, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [3] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 64], "tolerance": 0.00002 },
        "presentKeyT": { "dtype": "float32", "shape": [1, 4, 8, 16], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [1, 4, 8, 16], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_plain_b1_h4_cap8_d16_past0",
      "provenance": {
        "notes": "An empty cache: the appended token is the only key, so the output is its own value row."
      },
      "attrs": { "num_heads": 4, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [1, 4, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [1, 4, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [0] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 64], "tolerance": 0.00002 },
        "presentKeyT": { "dtype": "float32", "shape": [1, 4, 8, 16], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [1, 4, 8, 16], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_plain_b1_h4_cap8_d16_past6",
      "provenance": {
        "notes": "Self-attention with a shared past/present buffer sized for 8 tokens; 6 past tokens plus the appended token leave one row unused. 4 heads, head width 16."
      },
      "attrs": { "num_heads": 4, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [1, 4, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [1, 4, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [6] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 64], "tolerance": 0.00002 },
        "presentKeyT": { "dtype": "float32", "shape": [1, 4, 8, 16], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [1, 4, 8, 16], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_mask_b2_h4_cap16_d16_past9",
      "provenance": {
        "notes": "A key-padding mask over the live length only; the cache rows past it are outside the mask and outside the softmax."
      },
      "attrs": { "num_heads": 4, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [2, 10], "data": { "kind": "cycle", "values": [1, 1, 0] } },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [2, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [2, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [9] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [2, 1, 64], "tolerance": 0.00002 },
        "presentKeyT": { "dtype": "float32", "shape": [2, 4, 16, 16], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [2, 4, 16, 16], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_bias_b1_h4_cap16_d16_past5",
      "provenance": {
        "notes": "An additive score bias broadcast across batch and heads, the shape upstream's own self-attention test uses."
      },
      "attrs": { "num_heads": 4, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "attentionBiasT": {
          "dtype": "float32",
          "shape": [1, 1, 1, 6],
          "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.19, "scale": 0.3 }
        },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [1, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [5] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 64], "tolerance": 0.00002 },
        "presentKeyT": { "dtype": "float32", "shape": [1, 4, 16, 16], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [1, 4, 16, 16], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_bias_per_head_b2_h4_cap12_d16_past7",
      "provenance": {
        "notes": "A score bias with a real head dimension, so the head stride is non-zero and a broadcast reading would mix heads."
      },
      "attrs": { "num_heads": 4, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "attentionBiasT": {
          "dtype": "float32",
          "shape": [1, 4, 1, 8],
          "data": { "kind": "fillFloat32", "sinStep": 0.23, "cosStep": 0.41, "scale": 0.3 }
        },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [2, 4, 12, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [2, 4, 12, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [7] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [2, 1, 64], "tolerance": 0.00002 },
        "presentKeyT": { "dtype": "float32", "shape": [2, 4, 12, 16], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [2, 4, 12, 16], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_mask_bias_b2_h4_cap16_d16_past9",
      "provenance": {
        "notes": "Both additive terms at once. The bias is added before the mask, matching the reference's term order."
      },
      "attrs": { "num_heads": 4, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [2, 10], "data": { "kind": "cycle", "values": [1, 0] } },
        "attentionBiasT": {
          "dtype": "float32",
          "shape": [2, 4, 1, 10],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.53, "scale": 0.3 }
        },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [2, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [2, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [9] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [2, 1, 64], "tolerance": 0.00002 },
        "presentKeyT": { "dtype": "float32", "shape": [2, 4, 16, 16], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [2, 4, 16, 16], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_bias_batch_only_b2_h4_cap12_d16_past5",
      "provenance": {
        "notes": "A score bias with a batch dimension but a broadcast head dimension, the mixed stride pair."
      },
      "attrs": { "num_heads": 4, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "attentionBiasT": {
          "dtype": "float32",
          "shape": [2, 1, 1, 6],
          "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.31, "scale": 0.3 }
        },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [2, 4, 12, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [2, 4, 12, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [5] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [2, 1, 64], "tolerance": 0.00002 },
        "presentKeyT": { "dtype": "float32", "shape": [2, 4, 12, 16], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [2, 4, 12, 16], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_scale_b1_h4_cap8_d16_past3",
      "provenance": {
        "notes": "An explicit scale on the self route, overriding the reciprocal square root of the head size."
      },
      "attrs": { "num_heads": 4, "past_present_share_buffer": 1, "scale": 0.2 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [1, 4, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [1, 4, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [3] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 64], "tolerance": 0.00002 },
        "presentKeyT": { "dtype": "float32", "shape": [1, 4, 8, 16], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [1, 4, 8, 16], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_plain_b1_h8_cap448_d64_past223",
      "provenance": { "notes": "Whisper-base decoder self-attention geometry, with the cache half filled." },
      "attrs": { "num_heads": 8, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 512],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 1, 512],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 1, 512],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [1, 8, 448, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [1, 8, 448, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [223] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 512], "tolerance": 0.00005 },
        "presentKeyT": { "dtype": "float32", "shape": [1, 8, 448, 64], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [1, 8, 448, 64], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_mask_all_padded_b1_h2_cap8_d16_past3",
      "provenance": {
        "notes": "Every live key is masked. The additive filter keeps the row a uniform average rather than collapsing it to zeros."
      },
      "attrs": { "num_heads": 2, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 32],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 1, 32],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 1, 32],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 4], "data": { "kind": "constant", "value": 0 } },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [1, 2, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [1, 2, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [3] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 32], "tolerance": 0.00002 },
        "presentKeyT": { "dtype": "float32", "shape": [1, 2, 8, 16], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [1, 2, 8, 16], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_retain_stage4_b2_h8_cap448_d64_past31",
      "provenance": {
        "notes": "Self-attention with a shared past/present buffer sized for 448 tokens across 2 batches; 31 past tokens are extended by the appended token. 8 heads, head width 64."
      },
      "attrs": { "num_heads": 8, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [2, 1, 512],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [2, 1, 512],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [2, 1, 512],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "pastKeyT": {
          "dtype": "float32",
          "shape": [2, 8, 448, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float32",
          "shape": [2, 8, 448, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [31] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [2, 1, 512], "tolerance": 0.00005 },
        "presentKeyT": { "dtype": "float32", "shape": [2, 8, 448, 64], "tolerance": 0.000001 },
        "presentValueT": { "dtype": "float32", "shape": [2, 8, 448, 64], "tolerance": 0.000001 }
      }
    },
    {
      "name": "self_retain_stage8_f16_b4_h8_cap448_d64_past223",
      "provenance": {
        "notes": "A cache large enough for the retain copy to stage the full eight words per lane, the deepest rung, in float16."
      },
      "attrs": { "num_heads": 8, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float16",
          "shape": [4, 1, 512],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float16",
          "shape": [4, 1, 512],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float16",
          "shape": [4, 1, 512],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "pastKeyT": {
          "dtype": "float16",
          "shape": [4, 8, 448, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float16",
          "shape": [4, 8, 448, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [223] } }
      },
      "outputs": {
        "outputT": { "dtype": "float16", "shape": [4, 1, 512], "tolerance": 0.003 },
        "presentKeyT": { "dtype": "float16", "shape": [4, 8, 448, 64], "tolerance": 0.001 },
        "presentValueT": { "dtype": "float16", "shape": [4, 8, 448, 64], "tolerance": 0.001 }
      }
    },
    {
      "name": "self_plain_f16_b1_h4_cap8_d16_past3",
      "provenance": {
        "notes": "The float16 twin of the plain self route, including the float16 cache the append pass writes."
      },
      "attrs": { "num_heads": 4, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float16",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float16",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float16",
          "shape": [1, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "pastKeyT": {
          "dtype": "float16",
          "shape": [1, 4, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float16",
          "shape": [1, 4, 8, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [3] } }
      },
      "outputs": {
        "outputT": { "dtype": "float16", "shape": [1, 1, 64], "tolerance": 0.003 },
        "presentKeyT": { "dtype": "float16", "shape": [1, 4, 8, 16], "tolerance": 0.001 },
        "presentValueT": { "dtype": "float16", "shape": [1, 4, 8, 16], "tolerance": 0.001 }
      }
    },
    {
      "name": "self_mask_bias_f16_b2_h4_cap16_d16_past9",
      "provenance": {
        "notes": "Float16 operands with both additive terms, so the bias narrows with the tensor type while the score stays float32."
      },
      "attrs": { "num_heads": 4, "past_present_share_buffer": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float16",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float16",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float16",
          "shape": [2, 1, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [2, 10], "data": { "kind": "cycle", "values": [1, 0] } },
        "attentionBiasT": {
          "dtype": "float16",
          "shape": [2, 4, 1, 10],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.53, "scale": 0.3 }
        },
        "pastKeyT": {
          "dtype": "float16",
          "shape": [2, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.05, "cosStep": 0.13 }
        },
        "pastValueT": {
          "dtype": "float16",
          "shape": [2, 4, 16, 16],
          "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.29, "offset": 0.7 }
        },
        "pastSequenceLengthT": { "dtype": "int32", "shape": [1], "data": { "kind": "values", "values": [9] } }
      },
      "outputs": {
        "outputT": { "dtype": "float16", "shape": [2, 1, 64], "tolerance": 0.003 },
        "presentKeyT": { "dtype": "float16", "shape": [2, 4, 16, 16], "tolerance": 0.001 },
        "presentValueT": { "dtype": "float16", "shape": [2, 4, 16, 16], "tolerance": 0.001 }
      }
    },
    {
      "name": "cross_single_split_boundary_kv255_d64_float32",
      "provenance": {
        "notes": "Adjacent key lengths straddle the default computed split count; direct and split/merge must preserve the same full attention row."
      },
      "attrs": { "num_heads": 6 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 6, 255, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 6, 255, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 384], "tolerance": 0.00002 } }
    },
    {
      "name": "cross_single_split_boundary_kv255_d64_float16",
      "provenance": {
        "notes": "Adjacent key lengths straddle the default computed split count; direct and split/merge must preserve the same full attention row."
      },
      "attrs": { "num_heads": 6 },
      "inputs": {
        "queryT": {
          "dtype": "float16",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float16",
          "shape": [1, 6, 255, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float16",
          "shape": [1, 6, 255, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float16", "shape": [1, 1, 384], "tolerance": 0.003 } }
    },
    {
      "name": "cross_single_split_boundary_kv256_d64_float32",
      "provenance": {
        "notes": "Adjacent key lengths straddle the default computed split count; direct and split/merge must preserve the same full attention row."
      },
      "attrs": { "num_heads": 6 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 6, 256, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 6, 256, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 384], "tolerance": 0.00002 } }
    },
    {
      "name": "cross_single_split_boundary_kv256_d64_float16",
      "provenance": {
        "notes": "Adjacent key lengths straddle the default computed split count; direct and split/merge must preserve the same full attention row."
      },
      "attrs": { "num_heads": 6 },
      "inputs": {
        "queryT": {
          "dtype": "float16",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float16",
          "shape": [1, 6, 256, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float16",
          "shape": [1, 6, 256, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float16", "shape": [1, 1, 384], "tolerance": 0.003 } }
    },
    {
      "name": "cross_single_split_boundary_kv257_d64_float32",
      "provenance": {
        "notes": "Adjacent key lengths straddle the default computed split count; direct and split/merge must preserve the same full attention row."
      },
      "attrs": { "num_heads": 6 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 6, 257, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 6, 257, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 384], "tolerance": 0.00002 } }
    },
    {
      "name": "cross_single_split_boundary_kv257_d64_float16",
      "provenance": {
        "notes": "Adjacent key lengths straddle the default computed split count; direct and split/merge must preserve the same full attention row."
      },
      "attrs": { "num_heads": 6 },
      "inputs": {
        "queryT": {
          "dtype": "float16",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float16",
          "shape": [1, 6, 257, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float16",
          "shape": [1, 6, 257, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float16", "shape": [1, 1, 384], "tolerance": 0.003 } }
    },
    {
      "name": "cross_single_split_mask_qk_kv64_d64_float32",
      "provenance": {
        "notes": "Single-partition cross attention emits the scaled, finitely masked pre-softmax QK row while directly normalizing its output."
      },
      "attrs": { "num_heads": 6, "output_qk": 1, "mask_filter_value": -4 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 6, 64, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 6, 64, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 64], "data": { "kind": "cycle", "values": [1, 0, 1] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 384], "tolerance": 0.00002 },
        "qkT": { "dtype": "float32", "shape": [1, 6, 1, 64], "tolerance": 0.00002 }
      }
    },
    {
      "name": "cross_single_split_mask_qk_kv64_d64_float16",
      "provenance": {
        "notes": "Single-partition cross attention emits the scaled, finitely masked pre-softmax QK row while directly normalizing its output."
      },
      "attrs": { "num_heads": 6, "output_qk": 1, "mask_filter_value": -4 },
      "inputs": {
        "queryT": {
          "dtype": "float16",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float16",
          "shape": [1, 6, 64, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float16",
          "shape": [1, 6, 64, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 64], "data": { "kind": "cycle", "values": [1, 0, 1] } }
      },
      "outputs": {
        "outputT": { "dtype": "float16", "shape": [1, 1, 384], "tolerance": 0.003 },
        "qkT": { "dtype": "float16", "shape": [1, 6, 1, 64], "tolerance": 0.003 }
      }
    },
    {
      "name": "cross_multi_split_mask_qk_kv257_d64_float32",
      "provenance": {
        "notes": "Cross-attention with 6 heads and head width 64, a 257-length key/value cache (256 plus one), a padding mask, and a custom mask_filter_value of -4. The diagnostic qkT output is requested alongside outputT."
      },
      "attrs": { "num_heads": 6, "output_qk": 1, "mask_filter_value": -4 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 6, 257, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 6, 257, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 257], "data": { "kind": "cycle", "values": [1, 0, 1] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 384], "tolerance": 0.00002 },
        "qkT": { "dtype": "float32", "shape": [1, 6, 1, 257], "tolerance": 0.00002 }
      }
    },
    {
      "name": "cross_multi_split_mask_qk_kv257_d64_float16",
      "provenance": {
        "notes": "Cross-attention with 6 heads and head width 64, a 257-length key/value cache (256 plus one), a padding mask, and a custom mask_filter_value of -4, with float16 query/key/value/output. The diagnostic qkT output is requested alongside outputT."
      },
      "attrs": { "num_heads": 6, "output_qk": 1, "mask_filter_value": -4 },
      "inputs": {
        "queryT": {
          "dtype": "float16",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float16",
          "shape": [1, 6, 257, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float16",
          "shape": [1, 6, 257, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 257], "data": { "kind": "cycle", "values": [1, 0, 1] } }
      },
      "outputs": {
        "outputT": { "dtype": "float16", "shape": [1, 1, 384], "tolerance": 0.003 },
        "qkT": { "dtype": "float16", "shape": [1, 6, 1, 257], "tolerance": 0.003 }
      }
    },
    {
      "name": "qk_policy_b1_h4_kv256_d512_f32",
      "provenance": {
        "notes": "QK policy boundary or head-width fixture, checked against the CPU reference at the f32 attention tolerance."
      },
      "attrs": { "num_heads": 4 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 2048],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 4, 256, 512],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 4, 256, 512],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 2048], "tolerance": 0.00002 } }
    },
    {
      "name": "qk_policy_b1_h2_kv256_d1024_f32",
      "provenance": {
        "notes": "QK policy boundary or head-width fixture, checked against the CPU reference at the f32 attention tolerance."
      },
      "attrs": { "num_heads": 2 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 2048],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 2, 256, 1024],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 2, 256, 1024],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 2048], "tolerance": 0.00002 } }
    },
    {
      "name": "qk_policy_b1_h1_kv256_d2048_f32",
      "provenance": {
        "notes": "QK policy boundary or head-width fixture, checked against the CPU reference at the f32 attention tolerance."
      },
      "attrs": { "num_heads": 1 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 2048],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 1, 256, 2048],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 1, 256, 2048],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 2048], "tolerance": 0.00002 } },
      "requires": {
        "limits": {
          "maxComputeInvocationsPerWorkgroup": 512,
          "maxComputeWorkgroupSizeX": 512,
          "maxComputeWorkgroupStorageSize": 22528
        }
      }
    },
    {
      "name": "qk_policy_b1_h15_kv257_d128_f32",
      "provenance": {
        "notes": "QK policy boundary or head-width fixture, checked against the CPU reference at the f32 attention tolerance."
      },
      "attrs": { "num_heads": 15 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 1920],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 15, 257, 128],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 15, 257, 128],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 1920], "tolerance": 0.00002 } }
    },
    {
      "name": "qk_policy_b1_h16_kv257_d128_f32",
      "provenance": {
        "notes": "QK policy boundary or head-width fixture, checked against the CPU reference at the f32 attention tolerance."
      },
      "attrs": { "num_heads": 16 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 2048],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 16, 257, 128],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 16, 257, 128],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 2048], "tolerance": 0.00002 } }
    },
    {
      "name": "qk_policy_b1_h17_kv257_d128_f32",
      "provenance": {
        "notes": "QK policy boundary or head-width fixture, checked against the CPU reference at the f32 attention tolerance."
      },
      "attrs": { "num_heads": 17 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 2176],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 17, 257, 128],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 17, 257, 128],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 2176], "tolerance": 0.00002 } }
    },
    {
      "name": "qk_policy_b1_h6_kv256_d32_f32",
      "provenance": {
        "notes": "QK policy boundary or head-width fixture, checked against the CPU reference at the f32 attention tolerance."
      },
      "attrs": { "num_heads": 6 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 192],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 6, 256, 32],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 6, 256, 32],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 192], "tolerance": 0.00002 } }
    },
    {
      "name": "qk_policy_b1_h6_kv256_d256_f32",
      "provenance": {
        "notes": "QK policy boundary or head-width fixture, checked against the CPU reference at the f32 attention tolerance."
      },
      "attrs": { "num_heads": 6 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 1536],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 6, 256, 256],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 6, 256, 256],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 1536], "tolerance": 0.00002 } }
    },
    {
      "name": "qk_policy_b1_h6_kv1500_d64_f32",
      "provenance": {
        "notes": "QK policy boundary or head-width fixture, checked against the CPU reference at the f32 attention tolerance."
      },
      "attrs": { "num_heads": 6 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 6, 1500, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 6, 1500, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [1, 1, 384], "tolerance": 0.00002 } }
    },
    {
      "name": "qk_policy_b4_h6_kv1500_d128_f32",
      "provenance": {
        "notes": "QK policy boundary or head-width fixture, checked against the CPU reference at the f32 attention tolerance."
      },
      "attrs": { "num_heads": 6 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [4, 1, 768],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [4, 6, 1500, 128],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [4, 6, 1500, 128],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        }
      },
      "outputs": { "outputT": { "dtype": "float32", "shape": [4, 1, 768], "tolerance": 0.00002 } }
    },
    {
      "name": "qk_policy_f32_query_f16_scores_kv64_d64",
      "provenance": {
        "notes": "Mixed-dtype diagnostic scores exercise the f32 QK reduction at the mixed-QK half-output tolerance, on both sides of the split boundary."
      },
      "attrs": { "num_heads": 6, "output_qk": 1, "mask_filter_value": -4 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 6, 64, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 6, 64, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 64], "data": { "kind": "cycle", "values": [1, 0, 1] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 384], "tolerance": 0.00002 },
        "qkT": { "dtype": "float16", "shape": [1, 6, 1, 64], "tolerance": 0.002 }
      }
    },
    {
      "name": "qk_policy_f32_query_f16_scores_kv257_d64",
      "provenance": {
        "notes": "Mixed-dtype diagnostic scores exercise the f32 QK reduction at the mixed-QK half-output tolerance, on both sides of the split boundary."
      },
      "attrs": { "num_heads": 6, "output_qk": 1, "mask_filter_value": -4 },
      "inputs": {
        "queryT": {
          "dtype": "float32",
          "shape": [1, 1, 384],
          "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31 }
        },
        "keyT": {
          "dtype": "float32",
          "shape": [1, 6, 257, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23 }
        },
        "valueT": {
          "dtype": "float32",
          "shape": [1, 6, 257, 64],
          "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "offset": 0.7 }
        },
        "maskIndexT": { "dtype": "int32", "shape": [1, 257], "data": { "kind": "cycle", "values": [1, 0, 1] } }
      },
      "outputs": {
        "outputT": { "dtype": "float32", "shape": [1, 1, 384], "tolerance": 0.00002 },
        "qkT": { "dtype": "float16", "shape": [1, 6, 1, 257], "tolerance": 0.002 }
      }
    }
  ]
}