{
  "domain": "com.microsoft",
  "name": "CausalConvWithState",
  "sinceVersion": 1,
  "inputs": {
    "inputT": { "onnx": "input", "dtype": "T", "rank": 3 },
    "weightT": { "onnx": "weight", "dtype": "T", "rank": 3 },
    "biasT": { "onnx": "bias", "dtype": "T", "rank": 1, "optional": true },
    "pastStateT": {
      "onnx": "past_state",
      "dtype": "T",
      "rank": "3 if attrs.state_window == 0 else 4",
      "optional": true
    }
  },
  "outputs": {
    "outputT": { "onnx": "output", "dtype": "T", "rank": 3, "shape": "shapes.inputT" },
    "presentStateT": {
      "onnx": "present_state",
      "dtype": "T",
      "rank": "3 if attrs.state_window == 0 else 4",
      "shape": "[dim(shapes.inputT, 0), dim(shapes.inputT, 1), dim(shapes.weightT, 2) - 1] if attrs.state_window == 0 else [attrs.state_window, dim(shapes.inputT, 0), dim(shapes.inputT, 1), dim(shapes.weightT, 2) - 1]"
    }
  },
  "attributes": { "activation": { "default": "none" }, "ndim": { "default": 1 }, "state_window": { "default": 0 } },
  "attributeConstraints": { "activation": { "values": ["none", "silu", "swish"] }, "ndim": { "values": [1] } },
  "typeConstraints": { "T": ["float32", "float16"] },
  "tunables": { "workgroupSize": { "default": 256 }, "tiledWorkgroupSize": { "default": 128 } },
  "derive": {
    "stateWindow": "attrs.state_window",
    "windowed": "stateWindow > 0",
    "stateWindowOk": "stateWindow >= 0 and stateWindow <= 8",
    "kernelSize": "dim(shapes.weightT, ranks.weightT - 1)",
    "kernelSizePadded": "ceilDiv(kernelSize, 4) * 4",
    "weightRankOk": "ranks.weightT == 3 and dim(shapes.weightT, 1) == 1",
    "stateLength": "kernelSize - 1",
    "stateSlotStride": "dim(shapes.inputT, 0) * dim(shapes.inputT, 1) * stateLength",
    "windowedLengthOk": "not windowed or dim(shapes.inputT, 2) > 0",
    "presentStateOk": "(ranks.presentStateT == 3 and dim(shapes.presentStateT, 0) == dim(shapes.inputT, 0) and dim(shapes.presentStateT, 1) == dim(shapes.inputT, 1) and dim(shapes.presentStateT, 2) == stateLength) if not windowed else (ranks.presentStateT == 4 and dim(shapes.presentStateT, 0) == stateWindow and dim(shapes.presentStateT, 1) == dim(shapes.inputT, 0) and dim(shapes.presentStateT, 2) == dim(shapes.inputT, 1) and dim(shapes.presentStateT, 3) == stateLength)",
    "pastStateShapeOk": "present.pastStateT and ((ranks.pastStateT == 3 and dim(shapes.pastStateT, 0) == dim(shapes.inputT, 0) and dim(shapes.pastStateT, 1) == dim(shapes.inputT, 1) and dim(shapes.pastStateT, 2) == stateLength) if not windowed else (ranks.pastStateT == 4 and dim(shapes.pastStateT, 0) == stateWindow and dim(shapes.pastStateT, 1) == dim(shapes.inputT, 0) and dim(shapes.pastStateT, 2) == dim(shapes.inputT, 1) and dim(shapes.pastStateT, 3) == stateLength))",
    "commonContract": "ranks.inputT == 3 and weightRankOk and ranks.outputT == 3 and (tensorDtypes.inputT == \"float32\" or tensorDtypes.inputT == \"float16\") and tensorDtypes.weightT == tensorDtypes.inputT and tensorDtypes.outputT == tensorDtypes.inputT and tensorDtypes.presentStateT == tensorDtypes.inputT and f16Ok(dtypes.T) and dim(shapes.inputT, 1) == dim(shapes.weightT, 0) and dim(shapes.outputT, 0) == dim(shapes.inputT, 0) and dim(shapes.outputT, 1) == dim(shapes.inputT, 1) and dim(shapes.outputT, 2) == dim(shapes.inputT, 2) and stateWindowOk and windowedLengthOk and presentStateOk",
    "zeroStateContract": "commonContract and not present.pastStateT and not present.biasT",
    "biasNoStateContract": "commonContract and not present.pastStateT and present.biasT and ranks.biasT == 1 and tensorDtypes.biasT == tensorDtypes.inputT and dim(shapes.biasT, 0) == dim(shapes.inputT, 1)",
    "stateNoBiasContract": "commonContract and present.pastStateT and not present.biasT and tensorDtypes.pastStateT == tensorDtypes.inputT and pastStateShapeOk",
    "stateBiasContract": "commonContract and present.pastStateT and present.biasT and ranks.biasT == 1 and tensorDtypes.pastStateT == tensorDtypes.inputT and tensorDtypes.biasT == tensorDtypes.inputT and pastStateShapeOk and dim(shapes.biasT, 0) == dim(shapes.inputT, 1)"
  },
  "bindings": {
    "input": { "arg": "inputT", "buffer": "read-only-storage", "elementType": "$inputVec4" },
    "weight": { "arg": "weightT", "buffer": "read-only-storage", "elementType": "$weightElem" },
    "output": { "arg": "outputT", "buffer": "storage", "elementType": "$outputVec4" },
    "present_state": { "arg": "presentStateT", "buffer": "storage", "elementType": "$outputScalar" },
    "params": {
      "buffer": "uniform",
      "struct": [
        { "name": "batchSize", "type": "u32", "value": "dim(shapes.inputT, 0)" },
        { "name": "channels", "type": "u32", "value": "dim(shapes.inputT, 1)" },
        { "name": "length", "type": "u32", "value": "dim(shapes.inputT, 2)" },
        { "name": "stateWindow", "type": "u32", "value": "stateWindow" },
        { "name": "stateSlotStride", "type": "u32", "value": "stateSlotStride" }
      ]
    },
    "bias": { "arg": "biasT", "buffer": "read-only-storage", "elementType": "$inputScalar" },
    "past_state": { "arg": "pastStateT", "buffer": "read-only-storage", "elementType": "$inputScalar" },
    "input_2": { "arg": "inputT", "name": "input", "buffer": "read-only-storage", "elementType": "$inputScalar" },
    "weight_2": { "arg": "weightT", "name": "weight", "buffer": "read-only-storage", "elementType": "$inputScalar" },
    "output_2": { "arg": "outputT", "name": "output", "buffer": "storage", "elementType": "$outputScalar" },
    "params_2": {
      "name": "params",
      "buffer": "uniform",
      "struct": [
        { "name": "batchSize", "type": "u32", "value": "dim(shapes.inputT, 0)" },
        { "name": "channels", "type": "u32", "value": "dim(shapes.inputT, 1)" },
        { "name": "length", "type": "u32", "value": "dim(shapes.inputT, 2)" },
        { "name": "kernelSize", "type": "u32", "value": "kernelSize" },
        { "name": "stateWindow", "type": "u32", "value": "stateWindow" },
        { "name": "stateSlotStride", "type": "u32", "value": "stateSlotStride" }
      ]
    }
  },
  "variants": [
    {
      "id": "zero_state_vec4",
      "priority": 20,
      "when": ["zeroStateContract", "kernelSize >= 2", "kernelSize <= 4", "dim(shapes.inputT, 2) >= 4", "dim(shapes.inputT, 2) % 4 == 0"],
      "derive": {
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "workgroupSize": 256,
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "inputVec4": "\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\"",
        "outputVec4": "\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\"",
        "hasBias": false,
        "hasState": false,
        "weightElem": "(\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\") if kernelSize == 4 else dtypes.T"
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.Vec4",
          "shader": "causal-conv-with-state-vec4.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input", "weight", "output", "present_state", "params"],
          "dispatch": {
            "x": "min(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)), (workgroupSize)), 65535)",
            "y": "ceilDiv(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)), (workgroupSize)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "state_bias_vec4",
      "priority": 20,
      "when": ["stateBiasContract", "kernelSize >= 2", "kernelSize <= 4", "dim(shapes.inputT, 2) >= 4", "dim(shapes.inputT, 2) % 4 == 0"],
      "derive": {
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "workgroupSize": 256,
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "inputVec4": "\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\"",
        "outputVec4": "\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\"",
        "hasBias": true,
        "hasState": true,
        "weightElem": "(\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\") if kernelSize == 4 else dtypes.T"
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.Vec4",
          "shader": "causal-conv-with-state-vec4.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input", "weight", "bias", "past_state", "output", "present_state", "params"],
          "dispatch": {
            "x": "min(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)), (workgroupSize)), 65535)",
            "y": "ceilDiv(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)), (workgroupSize)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "bias_no_state_vec4",
      "priority": 20,
      "when": ["biasNoStateContract", "kernelSize >= 2", "kernelSize <= 4", "dim(shapes.inputT, 2) >= 4", "dim(shapes.inputT, 2) % 4 == 0"],
      "derive": {
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "workgroupSize": 256,
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "inputVec4": "\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\"",
        "outputVec4": "\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\"",
        "hasBias": true,
        "hasState": false,
        "weightElem": "(\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\") if kernelSize == 4 else dtypes.T"
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.Vec4",
          "shader": "causal-conv-with-state-vec4.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input", "weight", "bias", "output", "present_state", "params"],
          "dispatch": {
            "x": "min(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)), (workgroupSize)), 65535)",
            "y": "ceilDiv(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)), (workgroupSize)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "state_no_bias_vec4",
      "priority": 20,
      "when": ["stateNoBiasContract", "kernelSize >= 2", "kernelSize <= 4", "dim(shapes.inputT, 2) >= 4", "dim(shapes.inputT, 2) % 4 == 0"],
      "derive": {
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "workgroupSize": 256,
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "inputVec4": "\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\"",
        "outputVec4": "\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\"",
        "hasBias": false,
        "hasState": true,
        "weightElem": "(\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\") if kernelSize == 4 else dtypes.T"
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.Vec4",
          "shader": "causal-conv-with-state-vec4.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input", "weight", "past_state", "output", "present_state", "params"],
          "dispatch": {
            "x": "min(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)), (workgroupSize)), 65535)",
            "y": "ceilDiv(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)), (workgroupSize)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "zero_state_tiled_large_kernel",
      "priority": 10,
      "when": ["zeroStateContract", "kernelSize >= 32", "dim(shapes.inputT, 2) >= 256", "dim(shapes.inputT, 2) % 8 == 0", "tunables.tiledWorkgroupSize >= 1", "floor(tunables.tiledWorkgroupSize) == tunables.tiledWorkgroupSize", "tunables.tiledWorkgroupSize <= device.limits.maxComputeInvocationsPerWorkgroup", "tunables.tiledWorkgroupSize <= device.limits.maxComputeWorkgroupSizeX", "(tunables.tiledWorkgroupSize * 8 + 2 * kernelSizePadded - 1) * 4 <= device.limits.maxComputeWorkgroupStorageSize"],
      "derive": {
        "hasBias": false,
        "hasState": false,
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "workgroupSize": "tunables.tiledWorkgroupSize",
        "tileSize": "tunables.tiledWorkgroupSize * 8",
        "inputTileSize": "tunables.tiledWorkgroupSize * 8 + kernelSizePadded - 1",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.TiledLargeKernel",
          "shader": "causal-conv-with-state-tiled.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input_2", "weight_2", "output_2", "present_state", "params"],
          "dispatch": {
            "x": "min(dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), tileSize), 65535)",
            "y": "ceilDiv(dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), tileSize), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "state_bias_tiled_large_kernel",
      "priority": 10,
      "when": ["stateBiasContract", "kernelSize >= 32", "dim(shapes.inputT, 2) >= 256", "dim(shapes.inputT, 2) % 8 == 0", "tunables.tiledWorkgroupSize >= 1", "floor(tunables.tiledWorkgroupSize) == tunables.tiledWorkgroupSize", "tunables.tiledWorkgroupSize <= device.limits.maxComputeInvocationsPerWorkgroup", "tunables.tiledWorkgroupSize <= device.limits.maxComputeWorkgroupSizeX", "(tunables.tiledWorkgroupSize * 8 + 2 * kernelSizePadded - 1) * 4 <= device.limits.maxComputeWorkgroupStorageSize"],
      "derive": {
        "hasBias": true,
        "hasState": true,
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "workgroupSize": "tunables.tiledWorkgroupSize",
        "tileSize": "tunables.tiledWorkgroupSize * 8",
        "inputTileSize": "tunables.tiledWorkgroupSize * 8 + kernelSizePadded - 1",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.TiledLargeKernel",
          "shader": "causal-conv-with-state-tiled.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input_2", "weight_2", "bias", "past_state", "output_2", "present_state", "params"],
          "dispatch": {
            "x": "min(dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), tileSize), 65535)",
            "y": "ceilDiv(dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), tileSize), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "bias_no_state_tiled_large_kernel",
      "priority": 10,
      "when": ["biasNoStateContract", "kernelSize >= 32", "dim(shapes.inputT, 2) >= 256", "dim(shapes.inputT, 2) % 8 == 0", "tunables.tiledWorkgroupSize >= 1", "floor(tunables.tiledWorkgroupSize) == tunables.tiledWorkgroupSize", "tunables.tiledWorkgroupSize <= device.limits.maxComputeInvocationsPerWorkgroup", "tunables.tiledWorkgroupSize <= device.limits.maxComputeWorkgroupSizeX", "(tunables.tiledWorkgroupSize * 8 + 2 * kernelSizePadded - 1) * 4 <= device.limits.maxComputeWorkgroupStorageSize"],
      "derive": {
        "hasBias": true,
        "hasState": false,
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "workgroupSize": "tunables.tiledWorkgroupSize",
        "tileSize": "tunables.tiledWorkgroupSize * 8",
        "inputTileSize": "tunables.tiledWorkgroupSize * 8 + kernelSizePadded - 1",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.TiledLargeKernel",
          "shader": "causal-conv-with-state-tiled.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input_2", "weight_2", "bias", "output_2", "present_state", "params"],
          "dispatch": {
            "x": "min(dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), tileSize), 65535)",
            "y": "ceilDiv(dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), tileSize), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "state_no_bias_tiled_large_kernel",
      "priority": 10,
      "when": ["stateNoBiasContract", "kernelSize >= 32", "dim(shapes.inputT, 2) >= 256", "dim(shapes.inputT, 2) % 8 == 0", "tunables.tiledWorkgroupSize >= 1", "floor(tunables.tiledWorkgroupSize) == tunables.tiledWorkgroupSize", "tunables.tiledWorkgroupSize <= device.limits.maxComputeInvocationsPerWorkgroup", "tunables.tiledWorkgroupSize <= device.limits.maxComputeWorkgroupSizeX", "(tunables.tiledWorkgroupSize * 8 + 2 * kernelSizePadded - 1) * 4 <= device.limits.maxComputeWorkgroupStorageSize"],
      "derive": {
        "hasBias": false,
        "hasState": true,
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "workgroupSize": "tunables.tiledWorkgroupSize",
        "tileSize": "tunables.tiledWorkgroupSize * 8",
        "inputTileSize": "tunables.tiledWorkgroupSize * 8 + kernelSizePadded - 1",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.TiledLargeKernel",
          "shader": "causal-conv-with-state-tiled.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input_2", "weight_2", "past_state", "output_2", "present_state", "params"],
          "dispatch": {
            "x": "min(dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), tileSize), 65535)",
            "y": "ceilDiv(dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), tileSize), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "zero_state",
      "priority": 0,
      "when": ["zeroStateContract"],
      "derive": {
        "hasBias": false,
        "hasState": false,
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "workgroupSize": "tunables.workgroupSize",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState",
          "shader": "causal-conv-with-state.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input_2", "weight_2", "output_2", "present_state", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))), (workgroupSize)), 65535)",
            "y": "ceilDiv(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))), (workgroupSize)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "state_bias",
      "priority": 0,
      "when": ["stateBiasContract"],
      "derive": {
        "hasBias": true,
        "hasState": true,
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "workgroupSize": "tunables.workgroupSize",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState",
          "shader": "causal-conv-with-state.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input_2", "weight_2", "bias", "past_state", "output_2", "present_state", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))), (workgroupSize)), 65535)",
            "y": "ceilDiv(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))), (workgroupSize)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "bias_no_state",
      "priority": 0,
      "when": ["biasNoStateContract"],
      "derive": {
        "hasBias": true,
        "hasState": false,
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "workgroupSize": "tunables.workgroupSize",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState",
          "shader": "causal-conv-with-state.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input_2", "weight_2", "bias", "output_2", "present_state", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))), (workgroupSize)), 65535)",
            "y": "ceilDiv(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))), (workgroupSize)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "state_no_bias",
      "priority": 0,
      "when": ["stateNoBiasContract"],
      "derive": {
        "hasBias": false,
        "hasState": true,
        "useSilu": "attrs.activation == \"silu\" or attrs.activation == \"swish\"",
        "inputScalar": "dtypes.T",
        "outputScalar": "dtypes.T",
        "workgroupSize": "tunables.workgroupSize",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState",
          "shader": "causal-conv-with-state.wgsl.jinja",
          "derive": { "materializeConvBeforeActivation": false },
          "bindings": ["input_2", "weight_2", "past_state", "output_2", "present_state", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))), (workgroupSize)), 65535)",
            "y": "ceilDiv(ceilDiv((dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))), (workgroupSize)), 65535)",
            "z": 1
          }
        }
      ]
    }
  ]
}