{
  "domain": "com.microsoft",
  "name": "SkipSimplifiedLayerNormalization",
  "sinceVersion": 1,
  "description": "Adds `input` and `skip` (plus optional `bias`), then applies RMS normalization scaled by `gamma`. The optional second output exposes the pre-normalization sum. The schema's training-only mean and inverse-standard-deviation outputs are not implemented.",
  "inputs": [
    {
      "role": "input",
      "dtype": "T",
      "description": "Input tensor of shape `(token_count, hidden_size)` or `(batch, sequence, hidden_size)`, normalized over the last axis."
    },
    {
      "role": "skip",
      "dtype": "T",
      "description": "Residual tensor of the same shape as `input`, added before normalization."
    },
    {
      "role": "gamma",
      "dtype": "T",
      "rank": 1,
      "description": "1-D scale tensor with shape `(hidden_size)` applied after normalization."
    },
    {
      "role": "bias",
      "dtype": "T",
      "rank": 1,
      "optional": true,
      "description": "Optional 1-D bias tensor with shape `(hidden_size)` added to the `input + skip` sum."
    }
  ],
  "outputs": [
    {
      "role": "output",
      "dtype": "T",
      "rank": "ranks.inputT",
      "shape": "shapes.inputT",
      "description": "Normalized output tensor with the same shape as `input`."
    },
    {
      "role": "input_skip_bias_sum",
      "dtype": "T",
      "optional": true,
      "rank": "ranks.inputT",
      "shape": "shapes.inputT",
      "description": "Sum of `input`, `skip`, and optional `bias` before normalization, with the same shape as `input`."
    }
  ],
  "attributes": { "epsilon": 9.999999960041972e-13 },
  "attributeDescriptions": { "epsilon": "Non-negative epsilon added to the mean square before taking the square root." },
  "args": {
    "inputT": { "kind": "tensor", "semantic": "input", "role": "input" },
    "skipT": { "kind": "tensor", "semantic": "skip", "role": "input" },
    "gammaT": { "kind": "tensor", "semantic": "gamma", "role": "input" },
    "biasT": { "kind": "tensor", "semantic": "bias", "role": "input", "required": false },
    "outputT": { "kind": "tensor", "semantic": "output", "role": "output" },
    "residualT": { "kind": "tensor", "semantic": "input_skip_bias_sum", "role": "output", "required": false }
  },
  "typeConstraints": { "T": ["float32", "float16"] },
  "derive": {
    "rowCount": "numel(shapes.inputT) / max(1, dim(shapes.inputT, -1))",
    "hiddenSize": "dim(shapes.inputT, -1)",
    "skipWg": "max(1, min(tunables.MAX_WORKGROUP_SIZE, device.limits.maxComputeInvocationsPerWorkgroup, device.limits.maxComputeWorkgroupSizeX, pow2ceil(hiddenSize)))",
    "skipWgVec4": "max(1, min(tunables.MAX_WORKGROUP_SIZE, device.limits.maxComputeInvocationsPerWorkgroup, device.limits.maxComputeWorkgroupSizeX, pow2ceil(ceilDiv(hiddenSize, 4))))",
    "rowDispatchFits": "rowCount <= device.limits.maxComputeWorkgroupsPerDimension * device.limits.maxComputeWorkgroupsPerDimension",
    "normResourcesFit": "skipWg * 8 <= device.limits.maxComputeWorkgroupStorageSize and skipWgVec4 * 8 <= device.limits.maxComputeWorkgroupStorageSize",
    "epsilonOk": "attrs.epsilon >= 0",
    "coreContract": "epsilonOk and (ranks.inputT == 2 or ranks.inputT == 3) and ranks.skipT == ranks.inputT and ranks.gammaT == 1 and ranks.outputT == ranks.inputT and sameShape(shapes.inputT, shapes.skipT) and sameShape(shapes.outputT, shapes.inputT) and dim(shapes.inputT, -1) > 0 and dim(shapes.gammaT, 0) == dim(shapes.inputT, -1)",
    "residualOutputContract": "present.residualT and sameShape(shapes.residualT, shapes.inputT)",
    "outputOnlyContract": "not present.residualT",
    "f32MainDtypes": "tensorDtypes.inputT == \"float32\" and tensorDtypes.skipT == \"float32\" and tensorDtypes.gammaT == \"float32\" and tensorDtypes.outputT == \"float32\"",
    "f16MainDtypes": "tensorDtypes.inputT == \"float16\" and tensorDtypes.skipT == \"float16\" and tensorDtypes.gammaT == \"float16\" and tensorDtypes.outputT == \"float16\"",
    "f32ResidualDtypes": "f32MainDtypes and tensorDtypes.residualT == \"float32\" if present.residualT else false",
    "f16ResidualDtypes": "f16MainDtypes and tensorDtypes.residualT == \"float16\" if present.residualT else false",
    "vec4Aligned": "dim(shapes.inputT, -1) % 4 == 0",
    "hasSubgroups": "device.features.has(\"subgroups\") and device.wgslLanguageFeatures.has(\"subgroup_id\")",
    "hasF16": "device.features.has(\"shader-f16\")",
    "no_bias_contract": "not present.biasT",
    "f32_bias_contract": "false if not present.biasT else (ranks.biasT == 1 and tensorDtypes.biasT == \"float32\" and dim(shapes.biasT, 0) == hiddenSize)",
    "f16_bias_contract": "false if not present.biasT else (ranks.biasT == 1 and tensorDtypes.biasT == \"float16\" and dim(shapes.biasT, 0) == hiddenSize)",
    "f32_no_bias_residual_contract": "coreContract and residualOutputContract and f32ResidualDtypes and no_bias_contract",
    "f32_bias_residual_contract": "coreContract and residualOutputContract and f32ResidualDtypes and f32_bias_contract",
    "f16_no_bias_residual_contract": "hasF16 and coreContract and residualOutputContract and f16ResidualDtypes and no_bias_contract",
    "f16_bias_residual_contract": "hasF16 and coreContract and residualOutputContract and f16ResidualDtypes and f16_bias_contract",
    "f32_no_bias_output_contract": "coreContract and outputOnlyContract and f32MainDtypes and no_bias_contract",
    "f32_bias_output_contract": "coreContract and outputOnlyContract and f32MainDtypes and f32_bias_contract",
    "f16_no_bias_output_contract": "hasF16 and coreContract and outputOnlyContract and f16MainDtypes and no_bias_contract",
    "f16_bias_output_contract": "hasF16 and coreContract and outputOnlyContract and f16MainDtypes and f16_bias_contract"
  },
  "bindingSets": {
    "vec4_no_bias_residual": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "skip",
        "arg": "skipT",
        "semantic": "skip",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "gamma",
        "arg": "gammaT",
        "semantic": "gamma",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "input_skip_bias_sum",
        "arg": "residualT",
        "semantic": "input_skip_bias_sum",
        "buffer": { "type": "storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "name": "rows", "type": "u32", "value": "rowCount" },
            {
              "name": "rowStride",
              "type": "u32",
              "value": "max(1, min(rowCount, device.limits.maxComputeWorkgroupsPerDimension))"
            },
            { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" }
          ]
        }
      }
    ],
    "vec4_bias_residual": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "skip",
        "arg": "skipT",
        "semantic": "skip",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "gamma",
        "arg": "gammaT",
        "semantic": "gamma",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "input_skip_bias_sum",
        "arg": "residualT",
        "semantic": "input_skip_bias_sum",
        "buffer": { "type": "storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "name": "rows", "type": "u32", "value": "rowCount" },
            {
              "name": "rowStride",
              "type": "u32",
              "value": "max(1, min(rowCount, device.limits.maxComputeWorkgroupsPerDimension))"
            },
            { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" }
          ]
        }
      }
    ],
    "vec4_no_bias_output_only": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "skip",
        "arg": "skipT",
        "semantic": "skip",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "gamma",
        "arg": "gammaT",
        "semantic": "gamma",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "name": "rows", "type": "u32", "value": "rowCount" },
            {
              "name": "rowStride",
              "type": "u32",
              "value": "max(1, min(rowCount, device.limits.maxComputeWorkgroupsPerDimension))"
            },
            { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" }
          ]
        }
      }
    ],
    "vec4_bias_output_only": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "skip",
        "arg": "skipT",
        "semantic": "skip",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "gamma",
        "arg": "gammaT",
        "semantic": "gamma",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$vectorScalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$vectorScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "name": "rows", "type": "u32", "value": "rowCount" },
            {
              "name": "rowStride",
              "type": "u32",
              "value": "max(1, min(rowCount, device.limits.maxComputeWorkgroupsPerDimension))"
            },
            { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" }
          ]
        }
      }
    ],
    "scalar_no_bias_residual": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar"
      },
      {
        "name": "skip",
        "arg": "skipT",
        "semantic": "skip",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar"
      },
      {
        "name": "gamma",
        "arg": "gammaT",
        "semantic": "gamma",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$scalar"
      },
      {
        "name": "input_skip_bias_sum",
        "arg": "residualT",
        "semantic": "input_skip_bias_sum",
        "buffer": { "type": "storage" },
        "elementType": "$scalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "name": "rows", "type": "u32", "value": "rowCount" },
            { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" }
          ]
        }
      }
    ],
    "scalar_bias_residual": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar"
      },
      {
        "name": "skip",
        "arg": "skipT",
        "semantic": "skip",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar"
      },
      {
        "name": "gamma",
        "arg": "gammaT",
        "semantic": "gamma",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$scalar"
      },
      {
        "name": "input_skip_bias_sum",
        "arg": "residualT",
        "semantic": "input_skip_bias_sum",
        "buffer": { "type": "storage" },
        "elementType": "$scalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "name": "rows", "type": "u32", "value": "rowCount" },
            { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" }
          ]
        }
      }
    ],
    "scalar_no_bias_output_only": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar"
      },
      {
        "name": "skip",
        "arg": "skipT",
        "semantic": "skip",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar"
      },
      {
        "name": "gamma",
        "arg": "gammaT",
        "semantic": "gamma",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$scalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "name": "rows", "type": "u32", "value": "rowCount" },
            { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" }
          ]
        }
      }
    ],
    "scalar_bias_output_only": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar"
      },
      {
        "name": "skip",
        "arg": "skipT",
        "semantic": "skip",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar"
      },
      {
        "name": "gamma",
        "arg": "gammaT",
        "semantic": "gamma",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$scalar",
        "length": "$HIDDEN_LEN"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$scalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "name": "rows", "type": "u32", "value": "rowCount" },
            { "name": "epsilon", "type": "f32", "value": "attrs.epsilon" }
          ]
        }
      }
    ]
  },
  "tunables": { "MAX_WORKGROUP_SIZE": 256 },
  "variants": [
    {
      "id": "no_bias_vec4_f16",
      "priority": 21,
      "when": ["f16_no_bias_residual_contract", "vec4Aligned", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "scalar": "\"f16\"",
        "vectorScalar": "\"vec4<f16>\"",
        "hasBias": "\"no_bias\" == \"bias\"",
        "HIDDEN_LEN": "hiddenSize / 4"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.Vec4",
          "source": {
            "shader": "norm-skip-row-vec4.wgsl.jinja",
            "inputs": {
              "simplified": true,
              "hasBias": "\"no_bias\" == \"bias\"",
              "hasBeta": false,
              "writeResidualSum": true,
              "usesF16": true,
              "hidden": "hiddenSize",
              "hiddenVec": "hiddenSize / 4",
              "wg": "skipWgVec4",
              "vecType": "\"vec4<f16>\"",
              "useSubgroups": "hasSubgroups"
            }
          },
          "subgroupCollectivesWidth": "portable",
          "bindings": "vec4_no_bias_residual",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "no_bias_vec4",
      "priority": 20,
      "when": ["f32_no_bias_residual_contract", "vec4Aligned", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "scalar": "\"f32\"",
        "vectorScalar": "\"vec4<f32>\"",
        "hasBias": "\"no_bias\" == \"bias\"",
        "HIDDEN_LEN": "hiddenSize / 4"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.Vec4",
          "source": {
            "shader": "norm-skip-row-vec4.wgsl.jinja",
            "inputs": {
              "simplified": true,
              "hasBias": "\"no_bias\" == \"bias\"",
              "hasBeta": false,
              "writeResidualSum": true,
              "usesF16": false,
              "hidden": "hiddenSize",
              "hiddenVec": "hiddenSize / 4",
              "wg": "skipWgVec4",
              "vecType": "\"vec4<f32>\"",
              "useSubgroups": "hasSubgroups"
            }
          },
          "subgroupCollectivesWidth": "portable",
          "bindings": "vec4_no_bias_residual",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "no_bias_output_only_vec4",
      "priority": 20,
      "when": ["f32_no_bias_output_contract", "vec4Aligned", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "scalar": "\"f32\"",
        "vectorScalar": "\"vec4<f32>\"",
        "hasBias": "\"no_bias\" == \"bias\"",
        "HIDDEN_LEN": "hiddenSize / 4"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.Vec4OutputOnly",
          "source": {
            "shader": "norm-skip-row-vec4.wgsl.jinja",
            "inputs": {
              "simplified": true,
              "hasBias": "\"no_bias\" == \"bias\"",
              "hasBeta": false,
              "writeResidualSum": false,
              "usesF16": false,
              "hidden": "hiddenSize",
              "hiddenVec": "hiddenSize / 4",
              "wg": "skipWgVec4",
              "vecType": "\"vec4<f32>\"",
              "useSubgroups": "hasSubgroups"
            }
          },
          "subgroupCollectivesWidth": "portable",
          "bindings": "vec4_no_bias_output_only",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "no_bias_output_only_vec4_f16",
      "priority": 21,
      "when": ["f16_no_bias_output_contract", "vec4Aligned", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "scalar": "\"f16\"",
        "vectorScalar": "\"vec4<f16>\"",
        "hasBias": "\"no_bias\" == \"bias\"",
        "HIDDEN_LEN": "hiddenSize / 4"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.Vec4OutputOnly",
          "source": {
            "shader": "norm-skip-row-vec4.wgsl.jinja",
            "inputs": {
              "simplified": true,
              "hasBias": "\"no_bias\" == \"bias\"",
              "hasBeta": false,
              "writeResidualSum": false,
              "usesF16": true,
              "hidden": "hiddenSize",
              "hiddenVec": "hiddenSize / 4",
              "wg": "skipWgVec4",
              "vecType": "\"vec4<f16>\"",
              "useSubgroups": "hasSubgroups"
            }
          },
          "subgroupCollectivesWidth": "portable",
          "bindings": "vec4_no_bias_output_only",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "no_bias",
      "priority": 0,
      "when": ["f32_no_bias_residual_contract", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "simplified": true,
        "useSubgroups": false,
        "hasBeta": false,
        "writeResidualSum": true,
        "hasBias": "\"no_bias\" == \"bias\"",
        "scalar": "\"f32\"",
        "hiddenSize": "dim(shapes.inputT, -1)",
        "workgroupSize": "skipWg",
        "HIDDEN_LEN": "hiddenSize"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization",
          "shader": "norm-skip-row.wgsl.jinja",
          "bindings": "scalar_no_bias_residual",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "no_bias_f16",
      "requires": { "features": ["shader-f16"] },
      "priority": 0,
      "when": ["f16_no_bias_residual_contract", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "simplified": true,
        "useSubgroups": false,
        "hasBeta": false,
        "writeResidualSum": true,
        "hasBias": "\"no_bias\" == \"bias\"",
        "scalar": "\"f16\"",
        "usesF16": true,
        "hiddenSize": "dim(shapes.inputT, -1)",
        "workgroupSize": "skipWg",
        "HIDDEN_LEN": "hiddenSize"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization",
          "shader": "norm-skip-row.wgsl.jinja",
          "bindings": "scalar_no_bias_residual",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "no_bias_output_only_f16",
      "requires": { "features": ["shader-f16"] },
      "priority": 0,
      "when": ["f16_no_bias_output_contract", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "simplified": true,
        "useSubgroups": false,
        "hasBeta": false,
        "writeResidualSum": false,
        "hasBias": "\"no_bias\" == \"bias\"",
        "scalar": "\"f16\"",
        "usesF16": true,
        "hiddenSize": "dim(shapes.inputT, -1)",
        "workgroupSize": "skipWg",
        "HIDDEN_LEN": "hiddenSize"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.OutputOnly",
          "shader": "norm-skip-row.wgsl.jinja",
          "bindings": "scalar_no_bias_output_only",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "no_bias_output_only",
      "priority": 0,
      "when": ["f32_no_bias_output_contract", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "simplified": true,
        "useSubgroups": false,
        "hasBeta": false,
        "writeResidualSum": false,
        "hasBias": "\"no_bias\" == \"bias\"",
        "scalar": "\"f32\"",
        "hiddenSize": "dim(shapes.inputT, -1)",
        "workgroupSize": "skipWg",
        "HIDDEN_LEN": "hiddenSize"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.OutputOnly",
          "shader": "norm-skip-row.wgsl.jinja",
          "bindings": "scalar_no_bias_output_only",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "bias_vec4_f16",
      "priority": 21,
      "when": ["f16_bias_residual_contract", "vec4Aligned", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "scalar": "\"f16\"",
        "vectorScalar": "\"vec4<f16>\"",
        "hasBias": "\"bias\" == \"bias\"",
        "HIDDEN_LEN": "hiddenSize / 4"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.Vec4",
          "source": {
            "shader": "norm-skip-row-vec4.wgsl.jinja",
            "inputs": {
              "simplified": true,
              "hasBias": "\"bias\" == \"bias\"",
              "hasBeta": false,
              "writeResidualSum": true,
              "usesF16": true,
              "hidden": "hiddenSize",
              "hiddenVec": "hiddenSize / 4",
              "wg": "skipWgVec4",
              "vecType": "\"vec4<f16>\"",
              "useSubgroups": "hasSubgroups"
            }
          },
          "subgroupCollectivesWidth": "portable",
          "bindings": "vec4_bias_residual",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "bias_vec4",
      "priority": 20,
      "when": ["f32_bias_residual_contract", "vec4Aligned", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "scalar": "\"f32\"",
        "vectorScalar": "\"vec4<f32>\"",
        "hasBias": "\"bias\" == \"bias\"",
        "HIDDEN_LEN": "hiddenSize / 4"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.Vec4",
          "source": {
            "shader": "norm-skip-row-vec4.wgsl.jinja",
            "inputs": {
              "simplified": true,
              "hasBias": "\"bias\" == \"bias\"",
              "hasBeta": false,
              "writeResidualSum": true,
              "usesF16": false,
              "hidden": "hiddenSize",
              "hiddenVec": "hiddenSize / 4",
              "wg": "skipWgVec4",
              "vecType": "\"vec4<f32>\"",
              "useSubgroups": "hasSubgroups"
            }
          },
          "subgroupCollectivesWidth": "portable",
          "bindings": "vec4_bias_residual",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "bias_output_only_vec4",
      "priority": 20,
      "when": ["f32_bias_output_contract", "vec4Aligned", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "scalar": "\"f32\"",
        "vectorScalar": "\"vec4<f32>\"",
        "hasBias": "\"bias\" == \"bias\"",
        "HIDDEN_LEN": "hiddenSize / 4"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.Vec4OutputOnly",
          "source": {
            "shader": "norm-skip-row-vec4.wgsl.jinja",
            "inputs": {
              "simplified": true,
              "hasBias": "\"bias\" == \"bias\"",
              "hasBeta": false,
              "writeResidualSum": false,
              "usesF16": false,
              "hidden": "hiddenSize",
              "hiddenVec": "hiddenSize / 4",
              "wg": "skipWgVec4",
              "vecType": "\"vec4<f32>\"",
              "useSubgroups": "hasSubgroups"
            }
          },
          "subgroupCollectivesWidth": "portable",
          "bindings": "vec4_bias_output_only",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "bias_output_only_vec4_f16",
      "priority": 21,
      "when": ["f16_bias_output_contract", "vec4Aligned", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "scalar": "\"f16\"",
        "vectorScalar": "\"vec4<f16>\"",
        "hasBias": "\"bias\" == \"bias\"",
        "HIDDEN_LEN": "hiddenSize / 4"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.Vec4OutputOnly",
          "source": {
            "shader": "norm-skip-row-vec4.wgsl.jinja",
            "inputs": {
              "simplified": true,
              "hasBias": "\"bias\" == \"bias\"",
              "hasBeta": false,
              "writeResidualSum": false,
              "usesF16": true,
              "hidden": "hiddenSize",
              "hiddenVec": "hiddenSize / 4",
              "wg": "skipWgVec4",
              "vecType": "\"vec4<f16>\"",
              "useSubgroups": "hasSubgroups"
            }
          },
          "subgroupCollectivesWidth": "portable",
          "bindings": "vec4_bias_output_only",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "bias",
      "priority": 0,
      "when": ["f32_bias_residual_contract", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "simplified": true,
        "useSubgroups": false,
        "hasBeta": false,
        "writeResidualSum": true,
        "hasBias": "\"bias\" == \"bias\"",
        "scalar": "\"f32\"",
        "hiddenSize": "dim(shapes.inputT, -1)",
        "workgroupSize": "skipWg",
        "HIDDEN_LEN": "hiddenSize"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization",
          "shader": "norm-skip-row.wgsl.jinja",
          "bindings": "scalar_bias_residual",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "bias_f16",
      "requires": { "features": ["shader-f16"] },
      "priority": 0,
      "when": ["f16_bias_residual_contract", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "simplified": true,
        "useSubgroups": false,
        "hasBeta": false,
        "writeResidualSum": true,
        "hasBias": "\"bias\" == \"bias\"",
        "scalar": "\"f16\"",
        "usesF16": true,
        "hiddenSize": "dim(shapes.inputT, -1)",
        "workgroupSize": "skipWg",
        "HIDDEN_LEN": "hiddenSize"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization",
          "shader": "norm-skip-row.wgsl.jinja",
          "bindings": "scalar_bias_residual",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "bias_output_only_f16",
      "requires": { "features": ["shader-f16"] },
      "priority": 0,
      "when": ["f16_bias_output_contract", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "simplified": true,
        "useSubgroups": false,
        "hasBeta": false,
        "writeResidualSum": false,
        "hasBias": "\"bias\" == \"bias\"",
        "scalar": "\"f16\"",
        "usesF16": true,
        "hiddenSize": "dim(shapes.inputT, -1)",
        "workgroupSize": "skipWg",
        "HIDDEN_LEN": "hiddenSize"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.OutputOnly",
          "shader": "norm-skip-row.wgsl.jinja",
          "bindings": "scalar_bias_output_only",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    },
    {
      "id": "bias_output_only",
      "priority": 0,
      "when": ["f32_bias_output_contract", "normResourcesFit", "rowDispatchFits"],
      "constants": {
        "simplified": true,
        "useSubgroups": false,
        "hasBeta": false,
        "writeResidualSum": false,
        "hasBias": "\"bias\" == \"bias\"",
        "scalar": "\"f32\"",
        "hiddenSize": "dim(shapes.inputT, -1)",
        "workgroupSize": "skipWg",
        "HIDDEN_LEN": "hiddenSize"
      },
      "passes": [
        {
          "id": "main",
          "name": "SkipSimplifiedLayerNormalization.OutputOnly",
          "shader": "norm-skip-row.wgsl.jinja",
          "bindings": "scalar_bias_output_only",
          "dispatch": { "workgroups": "rowCount" }
        }
      ]
    }
  ]
}