{
  "domain": "com.microsoft",
  "name": "CausalConvWithState",
  "sinceVersion": 1,
  "description": "Legacy Microsoft contrib form of stateful 1-D causal depthwise convolution. Each channel uses its own `(channels, 1, kernel)` weight over current and past positions, with optional activation and `past_state`/`present_state` tensors for incremental decoding. The contrib-only `state_window` attribute may retain several rollback states. This inference implementation preserves the existing contrib ABI with `ndim = 1`, float16 or float32 tensors, and float32 accumulation; spatial ranks 2 and 3 and bfloat16 are not implemented.",
  "inputs": [
    {
      "role": "input",
      "dtype": "T",
      "rank": 3,
      "description": "Channels-first input tensor with shape `(batch_size, channels, sequence_length)` for the supported 1-D mode."
    },
    {
      "role": "weight",
      "dtype": "T",
      "rank": 3,
      "description": "Depthwise convolution kernel with shape `(channels, 1, kernel_size)` for the supported 1-D mode."
    },
    {
      "role": "bias",
      "dtype": "T",
      "rank": 1,
      "optional": true,
      "description": "Optional per-channel bias with shape `(channels,)`."
    },
    {
      "role": "past_state",
      "dtype": "T",
      "rank": "3 if attrs.state_window == 0 else 4",
      "optional": true,
      "description": "Carry state from the previous step; shape `(batch_size, channels, k_1 - 1)`, or `(W, batch_size, channels, k_1 - 1)` when `state_window = W > 0`, in which case only slot `W - 1` is read. If absent, the left-side padding is zero."
    }
  ],
  "outputs": [
    {
      "role": "output",
      "dtype": "T",
      "rank": 3,
      "shape": "shapes.input",
      "description": "Convolution output with the same shape as `input`."
    },
    {
      "role": "present_state",
      "dtype": "T",
      "rank": "3 if attrs.state_window == 0 else 4",
      "shape": "[dim(shapes.input, 0), dim(shapes.input, 1), dim(shapes.weight, 2) - 1] if attrs.state_window == 0 else [attrs.state_window, dim(shapes.input, 0), dim(shapes.input, 1), dim(shapes.weight, 2) - 1]",
      "description": "Updated carry state; shape `(batch_size, channels, k_1 - 1)`, or `(W, batch_size, channels, k_1 - 1)` when `state_window = W > 0`. Slot `W - 1` holds the last `k - 1` values along the causal axis; slot `j` holds the same for the prefix ending at position `seq_len - W + j`."
    }
  ],
  "attributes": { "activation": "none", "ndim": 1, "state_window": 0 },
  "attributeConstraints": { "activation": { "values": ["none", "silu", "swish"] }, "ndim": { "values": [1] } },
  "attributeDescriptions": {
    "activation": "Activation applied after convolution and bias. Defaults to `none`; `swish` is an alias of SiLU.",
    "ndim": "Number of spatial dimensions. This implementation supports the contrib 1D mode (`ndim = 1`).",
    "state_window": "Contrib extension selecting the number of rollback state slots to retain, in the range 0 through 8. Defaults to 0."
  },
  "typeConstraints": { "T": ["float32", "float16"] },
  "args": {
    "inputT": { "kind": "tensor", "semantic": "input", "role": "input" },
    "weightT": { "kind": "tensor", "semantic": "weight", "role": "input" },
    "biasT": { "kind": "tensor", "semantic": "bias", "role": "input", "required": false },
    "pastStateT": { "kind": "tensor", "semantic": "past_state", "role": "input", "required": false },
    "outputT": { "kind": "tensor", "semantic": "output", "role": "output" },
    "presentStateT": { "kind": "tensor", "semantic": "present_state", "role": "output" }
  },
  "tunables": { "workgroupSize": 256, "tiledWorkgroupSize": 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)"
  },
  "bindingSets": {
    "zeroScalar": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "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" }
          ]
        }
      }
    ],
    "zeroVec4": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputVec4"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$weightElem"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputVec4"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "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" }
          ]
        }
      }
    ],
    "biasNoState": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "name": "batchSize", "type": "u32", "value": "dim(shapes.inputT, 0)" },
            { "name": "channels", "type": "u32", "value": "dim(shapes.inputT, 1)" },
            { "name": "length", "type": "u32", "value": "dim(shapes.inputT, 2)" },
            { "name": "kernelSize", "type": "u32", "value": "kernelSize" },
            { "name": "stateWindow", "type": "u32", "value": "stateWindow" },
            { "name": "stateSlotStride", "type": "u32", "value": "stateSlotStride" }
          ]
        }
      }
    ],
    "stateNoBias": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "past_state",
        "arg": "pastStateT",
        "semantic": "past_state",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "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" }
          ]
        }
      }
    ],
    "stateBias": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "past_state",
        "arg": "pastStateT",
        "semantic": "past_state",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "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" }
          ]
        }
      }
    ],
    "zeroScalarIo": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      }
    ],
    "biasNoStateIo": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      }
    ],
    "stateNoBiasIo": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "past_state",
        "arg": "pastStateT",
        "semantic": "past_state",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      }
    ],
    "stateBiasIo": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "past_state",
        "arg": "pastStateT",
        "semantic": "past_state",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      }
    ],
    "zeroTiled": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "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" }
          ]
        }
      }
    ],
    "biasNoStateTiled": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "name": "batchSize", "type": "u32", "value": "dim(shapes.inputT, 0)" },
            { "name": "channels", "type": "u32", "value": "dim(shapes.inputT, 1)" },
            { "name": "length", "type": "u32", "value": "dim(shapes.inputT, 2)" },
            { "name": "stateWindow", "type": "u32", "value": "stateWindow" },
            { "name": "stateSlotStride", "type": "u32", "value": "stateSlotStride" }
          ]
        }
      }
    ],
    "stateNoBiasTiled": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "past_state",
        "arg": "pastStateT",
        "semantic": "past_state",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "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" }
          ]
        }
      }
    ],
    "stateBiasTiled": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "past_state",
        "arg": "pastStateT",
        "semantic": "past_state",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "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" }
          ]
        }
      }
    ],
    "biasNoStateVec4": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputVec4"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$weightElem"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputVec4"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "name": "batchSize", "type": "u32", "value": "dim(shapes.inputT, 0)" },
            { "name": "channels", "type": "u32", "value": "dim(shapes.inputT, 1)" },
            { "name": "length", "type": "u32", "value": "dim(shapes.inputT, 2)" },
            { "name": "stateWindow", "type": "u32", "value": "stateWindow" },
            { "name": "stateSlotStride", "type": "u32", "value": "stateSlotStride" }
          ]
        }
      }
    ],
    "stateNoBiasVec4": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputVec4"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$weightElem"
      },
      {
        "name": "past_state",
        "arg": "pastStateT",
        "semantic": "past_state",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputVec4"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "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" }
          ]
        }
      }
    ],
    "stateBiasVec4": [
      {
        "name": "input",
        "arg": "inputT",
        "semantic": "input",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputVec4"
      },
      {
        "name": "weight",
        "arg": "weightT",
        "semantic": "weight",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$weightElem"
      },
      {
        "name": "bias",
        "arg": "biasT",
        "semantic": "bias",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "past_state",
        "arg": "pastStateT",
        "semantic": "past_state",
        "buffer": { "type": "read-only-storage" },
        "elementType": "$inputScalar"
      },
      {
        "name": "output",
        "arg": "outputT",
        "semantic": "output",
        "buffer": { "type": "storage" },
        "elementType": "$outputVec4"
      },
      {
        "name": "present_state",
        "arg": "presentStateT",
        "semantic": "present_state",
        "buffer": { "type": "storage" },
        "elementType": "$outputScalar"
      },
      {
        "name": "params",
        "semantic": "kernel.params",
        "buffer": { "type": "uniform" },
        "struct": {
          "name": "Params",
          "fields": [
            { "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" }
          ]
        }
      }
    ]
  },
  "variants": [
    {
      "id": "zero_state_vec4",
      "priority": 20,
      "when": ["zeroStateContract", "kernelSize >= 2", "kernelSize <= 4", "dim(shapes.inputT, 2) >= 4", "dim(shapes.inputT, 2) % 4 == 0"],
      "constants": {
        "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,
        "kernelSize": "kernelSize",
        "kernelSizePadded": "kernelSizePadded",
        "weightElem": "(\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\") if kernelSize == 4 else dtypes.T"
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.Vec4",
          "source": {
            "shader": "causal-conv-with-state-vec4.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "zeroVec4",
          "dispatch": {
            "threads": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)",
            "workgroupSize": "constants.workgroupSize"
          }
        }
      ]
    },
    {
      "id": "state_bias_vec4",
      "priority": 20,
      "when": ["stateBiasContract", "kernelSize >= 2", "kernelSize <= 4", "dim(shapes.inputT, 2) >= 4", "dim(shapes.inputT, 2) % 4 == 0"],
      "constants": {
        "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,
        "kernelSize": "kernelSize",
        "kernelSizePadded": "kernelSizePadded",
        "weightElem": "(\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\") if kernelSize == 4 else dtypes.T"
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.Vec4",
          "source": {
            "shader": "causal-conv-with-state-vec4.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "stateBiasVec4",
          "dispatch": {
            "threads": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)",
            "workgroupSize": "constants.workgroupSize"
          }
        }
      ]
    },
    {
      "id": "bias_no_state_vec4",
      "priority": 20,
      "when": ["biasNoStateContract", "kernelSize >= 2", "kernelSize <= 4", "dim(shapes.inputT, 2) >= 4", "dim(shapes.inputT, 2) % 4 == 0"],
      "constants": {
        "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,
        "kernelSize": "kernelSize",
        "kernelSizePadded": "kernelSizePadded",
        "weightElem": "(\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\") if kernelSize == 4 else dtypes.T"
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.Vec4",
          "source": {
            "shader": "causal-conv-with-state-vec4.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "biasNoStateVec4",
          "dispatch": {
            "threads": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)",
            "workgroupSize": "constants.workgroupSize"
          }
        }
      ]
    },
    {
      "id": "state_no_bias_vec4",
      "priority": 20,
      "when": ["stateNoBiasContract", "kernelSize >= 2", "kernelSize <= 4", "dim(shapes.inputT, 2) >= 4", "dim(shapes.inputT, 2) % 4 == 0"],
      "constants": {
        "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,
        "kernelSize": "kernelSize",
        "kernelSizePadded": "kernelSizePadded",
        "weightElem": "(\"vec4<f16>\" if tensorDtypes.inputT == \"float16\" else \"vec4<f32>\") if kernelSize == 4 else dtypes.T"
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.Vec4",
          "source": {
            "shader": "causal-conv-with-state-vec4.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "stateNoBiasVec4",
          "dispatch": {
            "threads": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * (dim(shapes.outputT, 2) / 4)",
            "workgroupSize": "constants.workgroupSize"
          }
        }
      ]
    },
    {
      "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"],
      "constants": {
        "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",
        "kernelSize": "kernelSize",
        "kernelSizePadded": "kernelSizePadded",
        "inputTileSize": "tunables.tiledWorkgroupSize * 8 + kernelSizePadded - 1",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.TiledLargeKernel",
          "source": {
            "shader": "causal-conv-with-state-tiled.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "zeroTiled",
          "dispatch": {
            "workgroups": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), constants.tileSize)"
          }
        }
      ]
    },
    {
      "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"],
      "constants": {
        "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",
        "kernelSize": "kernelSize",
        "kernelSizePadded": "kernelSizePadded",
        "inputTileSize": "tunables.tiledWorkgroupSize * 8 + kernelSizePadded - 1",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.TiledLargeKernel",
          "source": {
            "shader": "causal-conv-with-state-tiled.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "stateBiasTiled",
          "dispatch": {
            "workgroups": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), constants.tileSize)"
          }
        }
      ]
    },
    {
      "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"],
      "constants": {
        "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",
        "kernelSize": "kernelSize",
        "kernelSizePadded": "kernelSizePadded",
        "inputTileSize": "tunables.tiledWorkgroupSize * 8 + kernelSizePadded - 1",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.TiledLargeKernel",
          "source": {
            "shader": "causal-conv-with-state-tiled.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "biasNoStateTiled",
          "dispatch": {
            "workgroups": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), constants.tileSize)"
          }
        }
      ]
    },
    {
      "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"],
      "constants": {
        "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",
        "kernelSize": "kernelSize",
        "kernelSizePadded": "kernelSizePadded",
        "inputTileSize": "tunables.tiledWorkgroupSize * 8 + kernelSizePadded - 1",
        "hasStateWindow": "windowed",
        "usesF16": "tensorDtypes.inputT == \"float16\""
      },
      "passes": [
        {
          "id": "main",
          "name": "CausalConvWithState.TiledLargeKernel",
          "source": {
            "shader": "causal-conv-with-state-tiled.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "stateNoBiasTiled",
          "dispatch": {
            "workgroups": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * ceilDiv(dim(shapes.outputT, 2), constants.tileSize)"
          }
        }
      ]
    },
    {
      "id": "zero_state",
      "priority": 0,
      "when": ["zeroStateContract"],
      "constants": {
        "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",
          "source": {
            "shader": "causal-conv-with-state.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "zeroScalar",
          "dispatch": {
            "threads": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))",
            "workgroupSize": "constants.workgroupSize"
          }
        }
      ]
    },
    {
      "id": "state_bias",
      "priority": 0,
      "when": ["stateBiasContract"],
      "constants": {
        "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",
          "source": {
            "shader": "causal-conv-with-state.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "stateBias",
          "dispatch": {
            "threads": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))",
            "workgroupSize": "constants.workgroupSize"
          }
        }
      ]
    },
    {
      "id": "bias_no_state",
      "priority": 0,
      "when": ["biasNoStateContract"],
      "constants": {
        "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",
          "source": {
            "shader": "causal-conv-with-state.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "biasNoState",
          "dispatch": {
            "threads": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))",
            "workgroupSize": "constants.workgroupSize"
          }
        }
      ]
    },
    {
      "id": "state_no_bias",
      "priority": 0,
      "when": ["stateNoBiasContract"],
      "constants": {
        "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",
          "source": {
            "shader": "causal-conv-with-state.wgsl.jinja",
            "inputs": { "materializeConvBeforeActivation": false }
          },
          "bindings": "stateNoBias",
          "dispatch": {
            "threads": "dim(shapes.outputT, 0) * dim(shapes.outputT, 1) * max(1, dim(shapes.outputT, 2))",
            "workgroupSize": "constants.workgroupSize"
          }
        }
      ]
    }
  ]
}