{
  "domain": "com.microsoft",
  "name": "EmbedLayerNormalization",
  "sinceVersion": 1,
  "inputs": {
    "inputIdsT": { "onnx": "input_ids", "dtype": "T1", "rank": 2, "storage": "int32" },
    "segmentIdsT": { "onnx": "segment_ids", "dtype": "T1", "rank": 2, "optional": true, "storage": "int32" },
    "wordEmbeddingT": { "onnx": "word_embedding", "dtype": "T", "rank": 2 },
    "positionEmbeddingT": { "onnx": "position_embedding", "dtype": "T", "rank": 2 },
    "segmentEmbeddingT": { "onnx": "segment_embedding", "dtype": "T", "rank": 2, "optional": true },
    "gammaT": { "onnx": "gamma", "dtype": "T", "rank": 1 },
    "betaT": { "onnx": "beta", "dtype": "T", "rank": 1 },
    "maskT": { "onnx": "mask", "dtype": "T1", "rank": 2, "optional": true, "storage": "int32" },
    "positionIdsT": { "onnx": "position_ids", "dtype": "T1", "rank": 2, "optional": true, "storage": "int32" }
  },
  "outputs": {
    "outputT": {
      "onnx": "output",
      "dtype": "T",
      "rank": 3,
      "shape": "[dim(shapes.inputIdsT, 0), dim(shapes.inputIdsT, 1), hidden]"
    },
    "maskIndexT": {
      "onnx": "mask_index",
      "dtype": "T1",
      "rank": 1,
      "optional": true,
      "shape": "[dim(shapes.inputIdsT, 0)]",
      "storage": "int32"
    },
    "embeddingSumT": {
      "onnx": "embedding_sum",
      "dtype": "T",
      "rank": 3,
      "optional": true,
      "shape": "[dim(shapes.inputIdsT, 0), dim(shapes.inputIdsT, 1), hidden]"
    }
  },
  "attributes": { "epsilon": { "default": 9.999999960041972e-13 }, "mask_index_type": {} },
  "attributeConstraints": { "mask_index_type": { "values": [0, 1] } },
  "typeConstraints": { "T": ["float32", "float16"], "T1": ["int32"] },
  "tunables": { "WORKGROUP_SIZE": { "default": 128 }, "MASK_WORKGROUP_SIZE": { "default": 64 } },
  "derive": {
    "batchSize": "dim(shapes.inputIdsT, 0)",
    "sequenceLength": "dim(shapes.inputIdsT, 1)",
    "tokens": "batchSize * sequenceLength",
    "hidden": "dim(shapes.wordEmbeddingT, 1)",
    "epsilonValue": "attrs.epsilon",
    "epsilonOk": "epsilonValue >= 0",
    "tableShapeOk": "ranks.wordEmbeddingT == 2 and dim(shapes.wordEmbeddingT, 0) > 0 and ranks.positionEmbeddingT == 2 and dim(shapes.positionEmbeddingT, 0) > 0 and dim(shapes.positionEmbeddingT, 1) == hidden and ranks.gammaT == 1 and ranks.betaT == 1 and dim(shapes.gammaT, 0) == hidden and dim(shapes.betaT, 0) == hidden and hidden > 0",
    "segmentContract": "(not present.segmentIdsT or present.segmentEmbeddingT) and (ranks.segmentIdsT == 2 and sameShape(shapes.segmentIdsT, shapes.inputIdsT) if present.segmentIdsT else true) and (ranks.segmentEmbeddingT == 2 and dim(shapes.segmentEmbeddingT, 0) > 0 and dim(shapes.segmentEmbeddingT, 1) == hidden if present.segmentEmbeddingT else true)",
    "positionIdsContract": "(ranks.positionIdsT == 2 and dim(shapes.positionIdsT, 1) == sequenceLength and (dim(shapes.positionIdsT, 0) == batchSize or dim(shapes.positionIdsT, 0) == 1) if present.positionIdsT else dim(shapes.positionEmbeddingT, 0) >= sequenceLength)",
    "broadcastPositionIds": "dim(shapes.positionIdsT, 0) == 1 if present.positionIdsT else false",
    "maskContract": "ranks.maskT == 2 and sameShape(shapes.maskT, shapes.inputIdsT) if present.maskT else true",
    "maskIndexTypeOk": "not has(attrs, \"mask_index_type\") or attrs.mask_index_type == 0 or attrs.mask_index_type == 1",
    "ioShapeOk": "ranks.inputIdsT == 2 and ranks.outputT == 3 and dim(shapes.outputT, 0) == batchSize and dim(shapes.outputT, 1) == sequenceLength and dim(shapes.outputT, 2) == hidden and tensorDtypes.outputT == tensorDtypes.wordEmbeddingT and tensorDtypes.positionEmbeddingT == tensorDtypes.wordEmbeddingT and tensorDtypes.gammaT == tensorDtypes.wordEmbeddingT and tensorDtypes.betaT == tensorDtypes.wordEmbeddingT and f16Ok(tensorDtypes.wordEmbeddingT)",
    "embeddingSumContract": "ranks.embeddingSumT == 3 and sameShape(shapes.embeddingSumT, shapes.outputT) and tensorDtypes.embeddingSumT == tensorDtypes.wordEmbeddingT if present.embeddingSumT else true",
    "maskIndexShapeOk": "ranks.maskIndexT == 1 and dim(shapes.maskIndexT, 0) == batchSize if present.maskIndexT else true",
    "embedContractOk": "epsilonOk and tableShapeOk and segmentContract and positionIdsContract and maskContract and maskIndexTypeOk and ioShapeOk and embeddingSumContract and maskIndexShapeOk and batchSize > 0 and sequenceLength > 0",
    "dispatchFits": "tunables.WORKGROUP_SIZE <= device.limits.maxComputeInvocationsPerWorkgroup and tunables.MASK_WORKGROUP_SIZE <= device.limits.maxComputeInvocationsPerWorkgroup",
    "aScalar": "dtypes.T",
    "scalar": "dtypes.T",
    "epsilon": "epsilonValue",
    "workgroupSize": "tunables.WORKGROUP_SIZE",
    "maskWorkgroupSize": "tunables.MASK_WORKGROUP_SIZE",
    "wordRows": "dim(shapes.wordEmbeddingT, 0)",
    "positionRows": "dim(shapes.positionEmbeddingT, 0)",
    "segmentRows": "dim(shapes.segmentEmbeddingT, 0) if present.segmentEmbeddingT else 1",
    "hasSegment": "present.segmentEmbeddingT",
    "hasSegmentIds": "present.segmentIdsT",
    "hasPositionIds": "present.positionIdsT",
    "writeEmbeddingSum": "present.embeddingSumT",
    "hasMask": "present.maskT",
    "HIDDEN_LEN": "hidden"
  },
  "when": ["embedContractOk", "dispatchFits"],
  "bindings": {
    "input_ids": { "arg": "inputIdsT", "buffer": "read-only-storage", "elementType": "i32" },
    "word_embedding": { "arg": "wordEmbeddingT", "buffer": "read-only-storage", "elementType": "$aScalar" },
    "position_embedding": { "arg": "positionEmbeddingT", "buffer": "read-only-storage", "elementType": "$aScalar" },
    "output": { "arg": "outputT", "buffer": "storage", "elementType": "$aScalar" },
    "params": { "buffer": "uniform", "struct": [{ "name": "tokens", "type": "u32", "value": "tokens" }] },
    "embedding_sum": { "arg": "embeddingSumT", "buffer": "storage", "elementType": "$aScalar" },
    "position_ids": { "arg": "positionIdsT", "buffer": "read-only-storage", "elementType": "i32" },
    "segment_ids": { "arg": "segmentIdsT", "buffer": "read-only-storage", "elementType": "i32" },
    "segment_embedding": { "arg": "segmentEmbeddingT", "buffer": "read-only-storage", "elementType": "$aScalar" },
    "gamma": { "arg": "gammaT", "buffer": "read-only-storage", "elementType": "$aScalar", "length": "$HIDDEN_LEN" },
    "beta": { "arg": "betaT", "buffer": "read-only-storage", "elementType": "$aScalar", "length": "$HIDDEN_LEN" },
    "mask": { "arg": "maskT", "buffer": "read-only-storage", "elementType": "i32" },
    "mask_index": { "arg": "maskIndexT", "buffer": "storage", "elementType": "i32" },
    "params_2": {
      "name": "params",
      "buffer": "uniform",
      "struct": [{ "name": "batch", "type": "u32", "value": "batchSize" }]
    }
  },
  "variants": [
    {
      "id": "noseg_nopos_nosum_nomask",
      "when": ["not present.segmentEmbeddingT", "not present.positionIdsT", "not present.embeddingSumT", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "noseg_nopos_nosum_mask",
      "when": ["not present.segmentEmbeddingT", "not present.positionIdsT", "not present.embeddingSumT", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "noseg_nopos_sum_nomask",
      "when": ["not present.segmentEmbeddingT", "not present.positionIdsT", "present.embeddingSumT", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "noseg_nopos_sum_mask",
      "when": ["not present.segmentEmbeddingT", "not present.positionIdsT", "present.embeddingSumT", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "noseg_posids_nosum_nomask",
      "when": ["not present.segmentEmbeddingT", "present.positionIdsT", "not present.embeddingSumT", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "noseg_posids_nosum_mask",
      "when": ["not present.segmentEmbeddingT", "present.positionIdsT", "not present.embeddingSumT", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "noseg_posids_sum_nomask",
      "when": ["not present.segmentEmbeddingT", "present.positionIdsT", "present.embeddingSumT", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "noseg_posids_sum_mask",
      "when": ["not present.segmentEmbeddingT", "present.positionIdsT", "present.embeddingSumT", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "seg_nopos_nosum_nomask",
      "when": ["present.segmentEmbeddingT", "present.segmentIdsT", "not present.positionIdsT", "not present.embeddingSumT", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "seg_nopos_nosum_mask",
      "when": ["present.segmentEmbeddingT", "present.segmentIdsT", "not present.positionIdsT", "not present.embeddingSumT", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "seg_nopos_sum_nomask",
      "when": ["present.segmentEmbeddingT", "present.segmentIdsT", "not present.positionIdsT", "present.embeddingSumT", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "seg_nopos_sum_mask",
      "when": ["present.segmentEmbeddingT", "present.segmentIdsT", "not present.positionIdsT", "present.embeddingSumT", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "seg_posids_nosum_nomask",
      "when": ["present.segmentEmbeddingT", "present.segmentIdsT", "present.positionIdsT", "not present.embeddingSumT", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "seg_posids_nosum_mask",
      "when": ["present.segmentEmbeddingT", "present.segmentIdsT", "present.positionIdsT", "not present.embeddingSumT", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "seg_posids_sum_nomask",
      "when": ["present.segmentEmbeddingT", "present.segmentIdsT", "present.positionIdsT", "present.embeddingSumT", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "seg_posids_sum_mask",
      "when": ["present.segmentEmbeddingT", "present.segmentIdsT", "present.positionIdsT", "present.embeddingSumT", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "segdefault_nopos_nosum_nomask",
      "when": ["present.segmentEmbeddingT", "not present.segmentIdsT", "present.positionIdsT == (\"nopos\" == \"posids\")", "present.embeddingSumT == (\"nosum\" == \"sum\")", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "segdefault_nopos_nosum_mask",
      "when": ["present.segmentEmbeddingT", "not present.segmentIdsT", "present.positionIdsT == (\"nopos\" == \"posids\")", "present.embeddingSumT == (\"nosum\" == \"sum\")", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "segdefault_nopos_sum_nomask",
      "when": ["present.segmentEmbeddingT", "not present.segmentIdsT", "present.positionIdsT == (\"nopos\" == \"posids\")", "present.embeddingSumT == (\"sum\" == \"sum\")", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "segdefault_nopos_sum_mask",
      "when": ["present.segmentEmbeddingT", "not present.segmentIdsT", "present.positionIdsT == (\"nopos\" == \"posids\")", "present.embeddingSumT == (\"sum\" == \"sum\")", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "segdefault_posids_nosum_nomask",
      "when": ["present.segmentEmbeddingT", "not present.segmentIdsT", "present.positionIdsT == (\"posids\" == \"posids\")", "present.embeddingSumT == (\"nosum\" == \"sum\")", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "segdefault_posids_nosum_mask",
      "when": ["present.segmentEmbeddingT", "not present.segmentIdsT", "present.positionIdsT == (\"posids\" == \"posids\")", "present.embeddingSumT == (\"nosum\" == \"sum\")", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "segdefault_posids_sum_nomask",
      "when": ["present.segmentEmbeddingT", "not present.segmentIdsT", "present.positionIdsT == (\"posids\" == \"posids\")", "present.embeddingSumT == (\"sum\" == \"sum\")", "not present.maskIndexT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        }
      ]
    },
    {
      "id": "segdefault_posids_sum_mask",
      "when": ["present.segmentEmbeddingT", "not present.segmentIdsT", "present.positionIdsT == (\"posids\" == \"posids\")", "present.embeddingSumT == (\"sum\" == \"sum\")", "present.maskIndexT", "present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.MaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask", "mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "noseg_nopos_nosum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"noseg\" != \"noseg\")", "present.segmentIdsT == (\"noseg\" == \"seg\")", "present.positionIdsT == (\"nopos\" == \"posids\")", "present.embeddingSumT == (\"nosum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "noseg_nopos_sum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"noseg\" != \"noseg\")", "present.segmentIdsT == (\"noseg\" == \"seg\")", "present.positionIdsT == (\"nopos\" == \"posids\")", "present.embeddingSumT == (\"sum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "noseg_posids_nosum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"noseg\" != \"noseg\")", "present.segmentIdsT == (\"noseg\" == \"seg\")", "present.positionIdsT == (\"posids\" == \"posids\")", "present.embeddingSumT == (\"nosum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "noseg_posids_sum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"noseg\" != \"noseg\")", "present.segmentIdsT == (\"noseg\" == \"seg\")", "present.positionIdsT == (\"posids\" == \"posids\")", "present.embeddingSumT == (\"sum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "segdefault_nopos_nosum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"segdefault\" != \"noseg\")", "present.segmentIdsT == (\"segdefault\" == \"seg\")", "present.positionIdsT == (\"nopos\" == \"posids\")", "present.embeddingSumT == (\"nosum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "segdefault_nopos_sum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"segdefault\" != \"noseg\")", "present.segmentIdsT == (\"segdefault\" == \"seg\")", "present.positionIdsT == (\"nopos\" == \"posids\")", "present.embeddingSumT == (\"sum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "segdefault_posids_nosum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"segdefault\" != \"noseg\")", "present.segmentIdsT == (\"segdefault\" == \"seg\")", "present.positionIdsT == (\"posids\" == \"posids\")", "present.embeddingSumT == (\"nosum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "segdefault_posids_sum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"segdefault\" != \"noseg\")", "present.segmentIdsT == (\"segdefault\" == \"seg\")", "present.positionIdsT == (\"posids\" == \"posids\")", "present.embeddingSumT == (\"sum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "seg_nopos_nosum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"seg\" != \"noseg\")", "present.segmentIdsT == (\"seg\" == \"seg\")", "present.positionIdsT == (\"nopos\" == \"posids\")", "present.embeddingSumT == (\"nosum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "seg_nopos_sum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"seg\" != \"noseg\")", "present.segmentIdsT == (\"seg\" == \"seg\")", "present.positionIdsT == (\"nopos\" == \"posids\")", "present.embeddingSumT == (\"sum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "seg_posids_nosum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"seg\" != \"noseg\")", "present.segmentIdsT == (\"seg\" == \"seg\")", "present.positionIdsT == (\"posids\" == \"posids\")", "present.embeddingSumT == (\"nosum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    },
    {
      "id": "seg_posids_sum_mask_without_input",
      "when": ["present.segmentEmbeddingT == (\"seg\" != \"noseg\")", "present.segmentIdsT == (\"seg\" == \"seg\")", "present.positionIdsT == (\"posids\" == \"posids\")", "present.embeddingSumT == (\"sum\" == \"sum\")", "present.maskIndexT", "not present.maskT"],
      "passes": [
        {
          "id": "sum",
          "name": "EmbedLayerNormalization.EmbeddingSum",
          "shader": "embed-sum.wgsl.jinja",
          "bindings": ["input_ids", "segment_ids", "position_ids", "word_embedding", "position_embedding", "segment_embedding", "output", "embedding_sum", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "normalize",
          "name": "EmbedLayerNormalization.Normalize",
          "shader": "embed-normalize.wgsl.jinja",
          "bindings": ["output", "gamma", "beta", "params"],
          "dispatch": { "x": "min(tokens, 65535)", "y": "ceilDiv(tokens, 65535)", "z": 1 }
        },
        {
          "id": "maskIndex",
          "name": "EmbedLayerNormalization.ZeroMaskIndex",
          "shader": "embed-mask-index.wgsl.jinja",
          "bindings": ["mask_index", "params_2"],
          "dispatch": {
            "x": "min(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "y": "ceilDiv(ceilDiv((batchSize), (tunables.MASK_WORKGROUP_SIZE)), 65535)",
            "z": 1
          }
        }
      ]
    }
  ]
}