{ "domain": "com.microsoft", "name": "QMoE", "sinceVersion": 1, "description": "Quantized mixture of experts over float32 activations and raw uint8-packed integer expert weights. The package implements 4- and 8-bit symmetric dequantization, ReLU, and interleaved SwiGLU for rank-2 or rank-3 input. Routing uses the softmax over the selected top-k logits, matching ONNX Runtime QMoE when the omitted `router_weights` input is absent. Biases, explicit zero points, FC3, sparse mixing, provider-prepacked layouts, and FP4/FP8 modes are not implemented.", "inputs": [ { "role": "input", "dtype": "T", "description": "Token activations of shape `(num_tokens, hidden_size)` or `(batch_size, sequence_length, hidden_size)`." }, { "role": "router_probs", "dtype": "T", "rank": 2, "description": "Routing logits of shape `(num_tokens, num_experts)`, where `num_tokens` is the product of the leading input dimensions." }, { "role": "fc1_experts_weights", "dtype": "T1", "rank": 3, "description": "Raw packed FC1 weights of shape `(num_experts, fusion_size * inter_size, hidden_size / pack_size)`, where `fusion_size` is 2 only for interleaved SwiGLU and `pack_size` is 2 for 4-bit or 1 for 8-bit weights." }, { "role": "fc1_scales", "dtype": "T2", "description": "Required FC1 dequantization scales: rank 2 `(num_experts, fusion_size * inter_size)` for column-wise quantization, or rank 3 with a trailing `hidden_size / block_size` axis." }, { "role": "fc2_experts_weights", "dtype": "T1", "rank": 3, "description": "Raw packed FC2 weights of shape `(num_experts, hidden_size, inter_size / pack_size)`." }, { "role": "fc2_scales", "dtype": "T2", "description": "Required FC2 dequantization scales: rank 2 `(num_experts, hidden_size)` for column-wise quantization, or rank 3 with a trailing `inter_size / block_size` axis." } ], "outputs": [ { "role": "output", "dtype": "T", "shape": "shapes.input", "description": "Routed expert output with the same shape as `input`." } ], "attributes": { "activation_alpha": 1, "activation_beta": 0, "activation_type": "relu", "expert_weight_bits": 4, "k": 1, "normalize_routing_weights": 0, "quant_type": "int", "swiglu_fusion": 0, "use_sparse_mixer": 0, "weights_prepacked": -1 }, "attributeDescriptions": { "activation_alpha": "Alpha used by SwiGLU; the exact standard default is 1.", "activation_beta": "Beta added to the SwiGLU linear branch; the exact standard default is 0.", "activation_type": "Activation applied after FC1. This package supports `relu` and `swiglu`; the exact standard default is `relu`.", "block_size": "Optional quantization block size along the reduction dimension. Omission selects column-wise scaling; a supplied value must be a power of two of at least 16 and divide both `hidden_size` and `inter_size`.", "expert_weight_bits": "Integer expert-weight bit width. This package supports 4 and 8; the exact standard default is 4.", "k": "Number of experts selected per token; the exact standard default is 1.", "normalize_routing_weights": "Accepted values are 0 and 1. With the separate `router_weights` input omitted, ONNX Runtime QMoE applies a softmax over the selected top-k logits for either value; the attribute only distinguishes the unsupported separate-weight path.", "quant_type": "Quantization family. This package supports only the exact standard default `int`.", "swiglu_fusion": "SwiGLU packing mode. ReLU uses the exact standard default 0; supported SwiGLU interleaves gate/up FC1 rows with value 1.", "swiglu_limit": "Optional SwiGLU clamp limit. Omission means no finite clamp.", "use_sparse_mixer": "Whether to use sparse-mixer routing. The exact standard default and only supported value is 0.", "weights_prepacked": "Provider weight-layout selector. Values -1 and 0 both consume the public raw packed tensor layout; provider-specific prepacked value 1 is not portable and is rejected." }, "attributeConstraints": { "activation_type": { "values": ["relu", "swiglu"] }, "expert_weight_bits": { "values": [4, 8] }, "normalize_routing_weights": { "values": [0, 1] }, "quant_type": { "values": ["int"] }, "swiglu_fusion": { "values": [0, 1] }, "use_sparse_mixer": { "values": [0] }, "weights_prepacked": { "values": [-1, 0] } }, "typeConstraints": { "T": ["float32"], "T1": ["uint8"], "T2": ["float32"] }, "args": { "inputT": { "kind": "tensor", "semantic": "input", "role": "input" }, "routerT": { "kind": "tensor", "semantic": "router_probs", "role": "input" }, "fc1T": { "kind": "tensor", "semantic": "fc1_experts_weights", "role": "input" }, "fc1ScalesT": { "kind": "tensor", "semantic": "fc1_scales", "role": "input" }, "fc2T": { "kind": "tensor", "semantic": "fc2_experts_weights", "role": "input" }, "fc2ScalesT": { "kind": "tensor", "semantic": "fc2_scales", "role": "input" }, "outputT": { "kind": "tensor", "semantic": "output", "role": "output" } }, "tunables": { "workgroupSize": 64, "decodeLanes": 32, "decodeBlockTarget": 1024, "decodeMinLaneTrips": 4, "groupThreads": 8, "groupRegM": 4, "groupRegN": 4, "groupTileK": 16, "groupRouteWorkgroup": 256 }, "derive": { "deviceWorkgroupCap": "min(device.limits.maxComputeInvocationsPerWorkgroup, device.limits.maxComputeWorkgroupSizeX)", "wave32Adapter": "has(device.adapterInfo, \"subgroupMinSize\") and has(device.adapterInfo, \"subgroupMaxSize\") and device.adapterInfo.subgroupMinSize == 32 and device.adapterInfo.subgroupMaxSize == 32", "canPinSubgroupSize32": "device.features.has(\"subgroups\") and device.features.has(\"subgroup-size-control\") and has(device.adapterInfo, \"subgroupMinSize\") and has(device.adapterInfo, \"subgroupMaxSize\") and device.adapterInfo.subgroupMinSize <= 32 and device.adapterInfo.subgroupMaxSize >= 32", "pinSubgroupSize32": "canPinSubgroupSize32 and not wave32Adapter", "wave32Effective": "wave32Adapter or pinSubgroupSize32", "hiddenSize": "dim(shapes.input, ranks.input - 1)", "numTokens": "numel(shapes.input) / max(1, hiddenSize)", "topK": "attrs.k", "weightBits": "attrs.expert_weight_bits", "quantBlockSize": "attrs.block_size if has(attrs, \"block_size\") else 0", "packSize": "2 if weightBits == 4 else 1", "quantMidpoint": "8 if weightBits == 4 else 128", "fusionSize": "2 if attrs.activation_type == \"swiglu\" and attrs.swiglu_fusion == 1 else 1", "interSize": "dim(shapes.fc1_experts_weights, 1) / fusionSize", "fc1PackedCols": "dim(shapes.fc1_experts_weights, 2)", "fc2PackedCols": "dim(shapes.fc2_experts_weights, 2)", "colWiseScales": "quantBlockSize == 0", "fc1ScaleBlocks": "1 if colWiseScales else hiddenSize / max(1, quantBlockSize)", "fc2ScaleBlocks": "1 if colWiseScales else interSize / max(1, quantBlockSize)", "activationSupported": "(attrs.activation_type == \"relu\" and attrs.swiglu_fusion == 0) or (attrs.activation_type == \"swiglu\" and attrs.swiglu_fusion == 1)", "routingModeSupported": "attrs.normalize_routing_weights == 0 or attrs.normalize_routing_weights == 1", "rawWeightLayout": "attrs.weights_prepacked == -1 or attrs.weights_prepacked == 0", "inputOutputShapeOk": "((ranks.input == 2 and ranks.output == 2 and dim(shapes.output, 0) == dim(shapes.input, 0) and dim(shapes.output, 1) == dim(shapes.input, 1)) or (ranks.input == 3 and ranks.output == 3 and dim(shapes.output, 0) == dim(shapes.input, 0) and dim(shapes.output, 1) == dim(shapes.input, 1) and dim(shapes.output, 2) == dim(shapes.input, 2))) and hiddenSize > 0", "quantBlockSizeOk": "colWiseScales or (quantBlockSize >= 16 and pow2ceil(quantBlockSize) == quantBlockSize and hiddenSize % quantBlockSize == 0 and interSize % quantBlockSize == 0)", "quantScalesOk": "tensorDtypes.fc1_scales == \"float32\" and tensorDtypes.fc2_scales == \"float32\" and dim(shapes.fc1_scales, 0) == dim(shapes.router_probs, 1) and dim(shapes.fc2_scales, 0) == dim(shapes.router_probs, 1) and dim(shapes.fc1_scales, 1) == dim(shapes.fc1_experts_weights, 1) and dim(shapes.fc2_scales, 1) == hiddenSize and ((ranks.fc1_scales == 2 and ranks.fc2_scales == 2) if colWiseScales else (ranks.fc1_scales == 3 and ranks.fc2_scales == 3 and dim(shapes.fc1_scales, 2) == fc1ScaleBlocks and dim(shapes.fc2_scales, 2) == fc2ScaleBlocks))", "quantShapeOk": "inputOutputShapeOk and ranks.router_probs == 2 and ranks.fc1_experts_weights == 3 and ranks.fc2_experts_weights == 3 and dim(shapes.router_probs, 0) == numTokens and dim(shapes.fc1_experts_weights, 0) == dim(shapes.router_probs, 1) and dim(shapes.fc2_experts_weights, 0) == dim(shapes.router_probs, 1) and dim(shapes.fc1_experts_weights, 1) % fusionSize == 0 and dim(shapes.fc2_experts_weights, 1) == hiddenSize and dim(shapes.fc1_experts_weights, 2) * packSize == hiddenSize and dim(shapes.fc2_experts_weights, 2) * packSize == interSize and quantBlockSizeOk and quantScalesOk", "quantContract": "activationSupported and routingModeSupported and rawWeightLayout and quantShapeOk and topK >= 1 and topK <= dim(shapes.router_probs, 1)", "workgroupSizeOk": "tunables.workgroupSize >= 1 and tunables.workgroupSize <= deviceWorkgroupCap", "hiddenChunkFits": "topK * interSize * 4 <= device.limits.maxStorageBufferBindingSize and topK * interSize * 4 <= device.limits.maxBufferSize", "hiddenChunkTokens": "numTokens if interSize == 0 else min(numTokens, max(1, floor(min(device.limits.maxStorageBufferBindingSize, device.limits.maxBufferSize) / (topK * interSize * 4))))", "hiddenChunkCount": "max(1, ceilDiv(numTokens, max(1, hiddenChunkTokens)))", "routeScratchBytes": "numTokens * topK * 4", "routedScratchFits": "routeScratchBytes <= device.limits.maxStorageBufferBindingSize and routeScratchBytes <= device.limits.maxBufferSize", "groupTileM": "tunables.groupThreads * tunables.groupRegM", "groupTileN": "tunables.groupThreads * tunables.groupRegN", "groupTileKVec": "ceilDiv(tunables.groupTileK, 4)", "groupThreadCount": "tunables.groupThreads * tunables.groupThreads", "groupSlots": "hiddenChunkTokens * topK", "groupMaxTiles": "ceilDiv(groupSlots, max(1, groupTileM)) + dim(shapes.router_probs, 1)", "groupSharedBytes": "(groupTileM * tunables.groupTileK + 2 * groupTileN * tunables.groupTileK + groupTileM) * 4", "groupSlotOutBytes": "hiddenChunkTokens * topK * hiddenSize * 4", "groupedDeviceOk": "groupThreadCount <= device.limits.maxComputeInvocationsPerWorkgroup and tunables.groupThreads <= device.limits.maxComputeWorkgroupSizeX and tunables.groupThreads <= device.limits.maxComputeWorkgroupSizeY and tunables.groupRouteWorkgroup <= deviceWorkgroupCap and groupSharedBytes <= device.limits.maxComputeWorkgroupStorageSize and dim(shapes.router_probs, 1) * 8 <= device.limits.maxComputeWorkgroupStorageSize and tunables.groupTileK % 4 == 0", "groupedDispatchOk": "groupMaxTiles <= device.limits.maxComputeWorkgroupsPerDimension and ceilDiv(interSize, max(1, groupTileN)) <= device.limits.maxComputeWorkgroupsPerDimension and ceilDiv(hiddenSize, max(1, groupTileN)) <= device.limits.maxComputeWorkgroupsPerDimension", "groupSlotOutFits": "groupSlotOutBytes <= device.limits.maxStorageBufferBindingSize and groupSlotOutBytes <= device.limits.maxBufferSize", "groupedShapeOk": "numTokens * topK * 4 >= groupTileM * dim(shapes.router_probs, 1)", "groupedContract": "quantContract and workgroupSizeOk and hiddenChunkFits and routedScratchFits and interSize > 0 and groupedDeviceOk and groupedDispatchOk and groupSlotOutFits and groupedShapeOk", "sgmatWorkgroup": "128", "sgmatSubgroups": "4", "sgmatRowSubtiles": "2", "groupedSgmatSharedBytes": "groupTileM * 4 + groupTileM * 32 * 4 + 64 * 32 * 4 + sgmatSubgroups * 4 * 64 * 4", "groupedSgmatOk": "groupedContract and groupTileM == 32 and interSize % 32 == 0 and groupedSgmatSharedBytes <= device.limits.maxComputeWorkgroupStorageSize and ceilDiv(hiddenSize, 64) <= device.limits.maxComputeWorkgroupsPerDimension and hiddenSize % 32 == 0", "decodeLanesOk": "tunables.decodeLanes >= 1 and tunables.decodeLanes <= tunables.workgroupSize and tunables.workgroupSize % tunables.decodeLanes == 0", "decodeRows": "max(1, tunables.workgroupSize / max(1, tunables.decodeLanes))", "decodeDeviceOk": "workgroupSizeOk and decodeLanesOk and tunables.decodeLanes <= device.limits.maxComputeWorkgroupSizeX and decodeRows <= device.limits.maxComputeWorkgroupSizeY and tunables.workgroupSize * 8 <= device.limits.maxComputeWorkgroupStorageSize", "decodeDispatchOk": "ceilDiv(interSize, decodeRows) <= device.limits.maxComputeWorkgroupsPerDimension and ceilDiv(hiddenSize, decodeRows) <= device.limits.maxComputeWorkgroupsPerDimension and hiddenChunkTokens * topK <= device.limits.maxComputeWorkgroupsPerDimension", "decodeLaneDepth": "min(hiddenSize, interSize) / max(1, tunables.decodeLanes)", "decodeDepthOk": "decodeLaneDepth >= tunables.decodeMinLaneTrips", "splitFc1Blocks": "ceilDiv(numTokens * topK * interSize, max(1, tunables.workgroupSize))", "decodeOccupancyOk": "splitFc1Blocks <= tunables.decodeBlockTarget", "decodeContract": "quantContract and decodeDeviceOk and decodeDispatchOk and hiddenChunkFits and routedScratchFits and interSize > 0 and decodeDepthOk and (decodeOccupancyOk or not groupedContract)" }, "constants": { "tokens": "numTokens", "hidden": "hiddenSize", "experts": "dim(shapes.router_probs, 1)", "fc1Rows": "dim(shapes.fc1_experts_weights, 1)", "inter": "interSize", "topK": "topK", "workgroupSize": "tunables.workgroupSize", "activationType": "attrs.activation_type", "hasSwigluLimit": "has(attrs, \"swiglu_limit\")", "swigluLimit": "attrs.swiglu_limit if has(attrs, \"swiglu_limit\") else 0", "quantMidpoint": "quantMidpoint", "quantBlockSize": "quantBlockSize", "packSize": "packSize", "fc1PackedCols": "fc1PackedCols", "fc2PackedCols": "fc2PackedCols", "colWiseScales": "colWiseScales", "fc1ScaleBlocks": "fc1ScaleBlocks", "fc2ScaleBlocks": "fc2ScaleBlocks" }, "bindingSets": { "route": [ { "name": "router_probs", "arg": "routerT", "semantic": "router_probs", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "route_expert", "semantic": "routeExpert", "buffer": { "type": "storage" }, "elementType": "u32" }, { "name": "route_mix", "semantic": "routeMix", "buffer": { "type": "storage" }, "elementType": "f32" } ], "fc1Activation": [ { "name": "input", "arg": "inputT", "semantic": "input", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "route_expert", "semantic": "routeExpert", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc1_experts_weights", "arg": "fc1T", "semantic": "fc1_experts_weights", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc1_scales", "arg": "fc1ScalesT", "semantic": "fc1_scales", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "hidden_act", "semantic": "hiddenAct", "buffer": { "type": "storage" }, "elementType": "f32" }, { "name": "params", "semantic": "kernel.params", "buffer": { "type": "uniform" }, "struct": { "name": "Params", "fields": [ { "name": "activationAlpha", "type": "f32", "value": "attrs.activation_alpha" }, { "name": "activationBeta", "type": "f32", "value": "attrs.activation_beta" }, { "name": "tokenOffset", "type": "u32", "value": "repeat.chunk * hiddenChunkTokens" }, { "name": "tokenCount", "type": "u32", "value": "min(hiddenChunkTokens, numTokens - repeat.chunk * hiddenChunkTokens)" } ] } } ], "output": [ { "name": "hidden_act", "semantic": "hiddenAct", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "route_expert", "semantic": "routeExpert", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "route_mix", "semantic": "routeMix", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "fc2_experts_weights", "arg": "fc2T", "semantic": "fc2_experts_weights", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc2_scales", "arg": "fc2ScalesT", "semantic": "fc2_scales", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "output", "arg": "outputT", "semantic": "output", "buffer": { "type": "storage" }, "elementType": "f32" }, { "name": "params", "semantic": "kernel.params", "buffer": { "type": "uniform" }, "struct": { "name": "Params", "fields": [ { "name": "tokenOffset", "type": "u32", "value": "repeat.chunk * hiddenChunkTokens" }, { "name": "tokenCount", "type": "u32", "value": "min(hiddenChunkTokens, numTokens - repeat.chunk * hiddenChunkTokens)" } ] } } ], "zeroInterOutput": [ { "name": "output", "arg": "outputT", "semantic": "output", "buffer": { "type": "storage" }, "elementType": "f32" } ], "group": [ { "name": "route_expert", "semantic": "routeExpert", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "slot_list", "semantic": "slotList", "buffer": { "type": "storage" }, "elementType": "u32" }, { "name": "tile_meta", "semantic": "tileMeta", "buffer": { "type": "storage" }, "elementType": "u32" }, { "name": "params", "semantic": "kernel.params", "buffer": { "type": "uniform" }, "struct": { "name": "Params", "fields": [ { "name": "tokenOffset", "type": "u32", "value": "repeat.chunk * hiddenChunkTokens" }, { "name": "tokenCount", "type": "u32", "value": "min(hiddenChunkTokens, numTokens - repeat.chunk * hiddenChunkTokens)" } ] } } ], "fc1Grouped": [ { "name": "input", "arg": "inputT", "semantic": "input", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "slot_list", "semantic": "slotList", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "tile_meta", "semantic": "tileMeta", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc1_experts_weights", "arg": "fc1T", "semantic": "fc1_experts_weights", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc1_scales", "arg": "fc1ScalesT", "semantic": "fc1_scales", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "hidden_act", "semantic": "hiddenAct", "buffer": { "type": "storage" }, "elementType": "f32" }, { "name": "params", "semantic": "kernel.params", "buffer": { "type": "uniform" }, "struct": { "name": "Params", "fields": [ { "name": "activationAlpha", "type": "f32", "value": "attrs.activation_alpha" }, { "name": "activationBeta", "type": "f32", "value": "attrs.activation_beta" }, { "name": "tokenOffset", "type": "u32", "value": "repeat.chunk * hiddenChunkTokens" } ] } } ], "outputGrouped": [ { "name": "hidden_act", "semantic": "hiddenAct", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "slot_list", "semantic": "slotList", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "tile_meta", "semantic": "tileMeta", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc2_experts_weights", "arg": "fc2T", "semantic": "fc2_experts_weights", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc2_scales", "arg": "fc2ScalesT", "semantic": "fc2_scales", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "slot_out", "semantic": "slotOut", "buffer": { "type": "storage" }, "elementType": "f32" } ], "mix": [ { "name": "slot_out", "semantic": "slotOut", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "route_mix", "semantic": "routeMix", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "output", "arg": "outputT", "semantic": "output", "buffer": { "type": "storage" }, "elementType": "f32" }, { "name": "params", "semantic": "kernel.params", "buffer": { "type": "uniform" }, "struct": { "name": "Params", "fields": [ { "name": "tokenOffset", "type": "u32", "value": "repeat.chunk * hiddenChunkTokens" }, { "name": "tokenCount", "type": "u32", "value": "min(hiddenChunkTokens, numTokens - repeat.chunk * hiddenChunkTokens)" } ] } } ], "fc1ActivationIo": [ { "name": "input", "arg": "inputT", "semantic": "input", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "route_expert", "semantic": "routeExpert", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc1_experts_weights", "arg": "fc1T", "semantic": "fc1_experts_weights", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc1_scales", "arg": "fc1ScalesT", "semantic": "fc1_scales", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "hidden_act", "semantic": "hiddenAct", "buffer": { "type": "storage" }, "elementType": "f32" } ], "fc1ActivationScheduled": [ { "name": "input", "arg": "inputT", "semantic": "input", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "route_expert", "semantic": "routeExpert", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc1_experts_weights", "arg": "fc1T", "semantic": "fc1_experts_weights", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc1_scales", "arg": "fc1ScalesT", "semantic": "fc1_scales", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "hidden_act", "semantic": "hiddenAct", "buffer": { "type": "storage" }, "elementType": "f32" }, { "name": "params", "semantic": "kernel.params", "buffer": { "type": "uniform" }, "struct": { "name": "Params", "fields": [ { "name": "activationAlpha", "type": "f32", "value": "attrs.activation_alpha" }, { "name": "activationBeta", "type": "f32", "value": "attrs.activation_beta" }, { "name": "tokenOffset", "type": "u32", "value": "repeat.chunk * hiddenChunkTokens" } ] } } ], "outputIo": [ { "name": "hidden_act", "semantic": "hiddenAct", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "route_expert", "semantic": "routeExpert", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "route_mix", "semantic": "routeMix", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "fc2_experts_weights", "arg": "fc2T", "semantic": "fc2_experts_weights", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc2_scales", "arg": "fc2ScalesT", "semantic": "fc2_scales", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "output", "arg": "outputT", "semantic": "output", "buffer": { "type": "storage" }, "elementType": "f32" } ], "outputScheduled": [ { "name": "hidden_act", "semantic": "hiddenAct", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "route_expert", "semantic": "routeExpert", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "route_mix", "semantic": "routeMix", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "fc2_experts_weights", "arg": "fc2T", "semantic": "fc2_experts_weights", "buffer": { "type": "read-only-storage" }, "elementType": "u32" }, { "name": "fc2_scales", "arg": "fc2ScalesT", "semantic": "fc2_scales", "buffer": { "type": "read-only-storage" }, "elementType": "f32" }, { "name": "output", "arg": "outputT", "semantic": "output", "buffer": { "type": "storage" }, "elementType": "f32" }, { "name": "params", "semantic": "kernel.params", "buffer": { "type": "uniform" }, "struct": { "name": "Params", "fields": [{ "name": "tokenOffset", "type": "u32", "value": "repeat.chunk * hiddenChunkTokens" }] } } ] }, "variants": [ { "id": "quant_zero_inter", "priority": 20, "when": ["quantContract", "workgroupSizeOk", "interSize == 0"], "passes": [ { "id": "output_stage", "name": "QMoE.OutputStageZeroInter", "source": { "shader": "qmoe-output-zero-inter.wgsl.jinja", "inputs": { "outputElementCount": "numel(shapes.output)" } }, "bindings": "zeroInterOutput", "dispatch": { "threads": "numel(shapes.output)", "workgroupSize": "constants.workgroupSize" } } ] }, { "id": "quant_grouped_sgmat_routed", "priority": 32, "when": ["groupedSgmatOk", "wave32Effective"], "constants": { "groupTileM": "groupTileM", "groupRouteWorkgroup": "tunables.groupRouteWorkgroup", "sgmatWorkgroup": "sgmatWorkgroup", "sgmatSubgroups": "sgmatSubgroups", "sgmatRowSubtiles": "sgmatRowSubtiles" }, "intermediates": [ { "id": "routeExpert", "dtype": "uint32", "shape": "[numTokens * topK]" }, { "id": "routeMix", "dtype": "float32", "shape": "[numTokens * topK]" }, { "id": "hiddenAct", "dtype": "float32", "shape": "[hiddenChunkTokens * topK * interSize]" }, { "id": "slotList", "dtype": "uint32", "shape": "[max(1, groupSlots)]" }, { "id": "tileMeta", "dtype": "uint32", "shape": "[1 + 3 * groupMaxTiles]" }, { "id": "slotOut", "dtype": "float32", "shape": "[max(1, hiddenChunkTokens * topK * hiddenSize)]" } ], "passes": [ { "id": "route_stage", "name": "QMoE.RouteStage", "shader": "qmoe-route-stage.wgsl.jinja", "bindings": "route", "dispatch": { "threads": "numTokens", "workgroupSize": "constants.workgroupSize" } }, { "id": "token_chunks", "repeat": { "count": "hiddenChunkCount", "index": "chunk" }, "passes": [ { "id": "group_stage", "name": "QMoE.GroupStage", "shader": "expert-group-slots.wgsl.jinja", "bindings": "group", "dispatch": { "threads": "constants.groupRouteWorkgroup", "workgroupSize": "constants.groupRouteWorkgroup" } }, { "id": "fc1_activation_stage", "name": "QMoE.FC1ActivationStageGroupedSgmat", "shader": "qmoe-fc1-activation-grouped-sgmat.wgsl.jinja", "bindings": "fc1Grouped", "dispatch": { "x": "groupMaxTiles", "y": "ceilDiv(interSize * fusionSize, 64)" } }, { "id": "output_stage", "name": "QMoE.OutputStageGroupedSgmat", "shader": "qmoe-output-grouped-sgmat.wgsl.jinja", "bindings": "outputGrouped", "dispatch": { "x": "groupMaxTiles", "y": "ceilDiv(hiddenSize, 64)" } }, { "id": "mix_stage", "name": "QMoE.MixStage", "shader": "qmoe-mix-stage.wgsl.jinja", "bindings": "mix", "dispatch": { "threads": "min(hiddenChunkTokens, numTokens - repeat.chunk * hiddenChunkTokens) * hiddenSize", "workgroupSize": "constants.workgroupSize" } } ] } ], "requires": { "features": ["subgroups", "chromium-experimental-subgroup-matrix"], "limits": { "maxComputeWorkgroupStorageSize": 16512 }, "subgroupMatrixConfigs": [{ "componentType": "f32", "resultComponentType": "f32", "M": 8, "N": 8, "K": 8 }] } }, { "id": "quant_grouped_routed", "priority": 30, "when": ["groupedContract"], "constants": { "groupTileM": "groupTileM", "groupTileN": "groupTileN", "groupTileK": "tunables.groupTileK", "groupTileKVec": "groupTileKVec", "groupThreads": "tunables.groupThreads", "regM": "tunables.groupRegM", "regN": "tunables.groupRegN", "groupRouteWorkgroup": "tunables.groupRouteWorkgroup" }, "intermediates": [ { "id": "routeExpert", "dtype": "uint32", "shape": "[numTokens * topK]" }, { "id": "routeMix", "dtype": "float32", "shape": "[numTokens * topK]" }, { "id": "hiddenAct", "dtype": "float32", "shape": "[hiddenChunkTokens * topK * interSize]" }, { "id": "slotList", "dtype": "uint32", "shape": "[max(1, groupSlots)]" }, { "id": "tileMeta", "dtype": "uint32", "shape": "[1 + 3 * groupMaxTiles]" }, { "id": "slotOut", "dtype": "float32", "shape": "[max(1, hiddenChunkTokens * topK * hiddenSize)]" } ], "passes": [ { "id": "route_stage", "name": "QMoE.RouteStage", "shader": "qmoe-route-stage.wgsl.jinja", "bindings": "route", "dispatch": { "threads": "numTokens", "workgroupSize": "constants.workgroupSize" } }, { "id": "token_chunks", "repeat": { "count": "hiddenChunkCount", "index": "chunk" }, "passes": [ { "id": "group_stage", "name": "QMoE.GroupStage", "shader": "expert-group-slots.wgsl.jinja", "bindings": "group", "dispatch": { "threads": "constants.groupRouteWorkgroup", "workgroupSize": "constants.groupRouteWorkgroup" } }, { "id": "fc1_activation_stage", "name": "QMoE.FC1ActivationStageGrouped", "shader": "qmoe-fc1-activation-grouped.wgsl.jinja", "bindings": "fc1Grouped", "dispatch": { "x": "groupMaxTiles", "y": "ceilDiv(interSize, groupTileN)" } }, { "id": "output_stage", "name": "QMoE.OutputStageGrouped", "shader": "qmoe-output-grouped.wgsl.jinja", "bindings": "outputGrouped", "dispatch": { "x": "groupMaxTiles", "y": "ceilDiv(hiddenSize, groupTileN)" } }, { "id": "mix_stage", "name": "QMoE.MixStage", "shader": "qmoe-mix-stage.wgsl.jinja", "bindings": "mix", "dispatch": { "threads": "min(hiddenChunkTokens, numTokens - repeat.chunk * hiddenChunkTokens) * hiddenSize", "workgroupSize": "constants.workgroupSize" } } ] } ] }, { "id": "quant_gemv_routed", "priority": 20, "when": ["decodeContract"], "constants": { "decodeLanes": "tunables.decodeLanes", "decodeRows": "decodeRows" }, "intermediates": [ { "id": "routeExpert", "dtype": "uint32", "shape": "[numTokens * topK]" }, { "id": "routeMix", "dtype": "float32", "shape": "[numTokens * topK]" }, { "id": "hiddenAct", "dtype": "float32", "shape": "[hiddenChunkTokens * topK * interSize]" } ], "passes": [ { "id": "route_stage", "name": "QMoE.RouteStage", "shader": "qmoe-route-stage.wgsl.jinja", "bindings": "route", "dispatch": { "threads": "numTokens", "workgroupSize": "constants.workgroupSize" } }, { "id": "token_chunks", "repeat": { "count": "hiddenChunkCount", "index": "chunk" }, "passes": [ { "id": "fc1_activation_stage", "name": "QMoE.FC1ActivationStageGemv", "shader": "qmoe-fc1-activation-gemv.wgsl.jinja", "bindings": "fc1ActivationScheduled", "dispatch": { "x": "ceilDiv(interSize, decodeRows)", "y": "min(hiddenChunkTokens, numTokens - repeat.chunk * hiddenChunkTokens) * topK" } }, { "id": "output_stage", "name": "QMoE.OutputStageGemv", "shader": "qmoe-output-gemv.wgsl.jinja", "bindings": "outputScheduled", "dispatch": { "x": "ceilDiv(hiddenSize, decodeRows)", "y": "min(hiddenChunkTokens, numTokens - repeat.chunk * hiddenChunkTokens)" } } ] } ] }, { "id": "quant_split_routed", "priority": 10, "when": ["quantContract", "workgroupSizeOk", "hiddenChunkFits", "routedScratchFits", "interSize > 0"], "intermediates": [ { "id": "routeExpert", "dtype": "uint32", "shape": "[numTokens * topK]" }, { "id": "routeMix", "dtype": "float32", "shape": "[numTokens * topK]" }, { "id": "hiddenAct", "dtype": "float32", "shape": "[hiddenChunkTokens * topK * interSize]" } ], "passes": [ { "id": "route_stage", "name": "QMoE.RouteStage", "shader": "qmoe-route-stage.wgsl.jinja", "bindings": "route", "dispatch": { "threads": "numTokens", "workgroupSize": "constants.workgroupSize" } }, { "id": "token_chunks", "repeat": { "count": "hiddenChunkCount", "index": "chunk" }, "passes": [ { "id": "fc1_activation_stage", "name": "QMoE.FC1ActivationStage", "shader": "qmoe-fc1-activation-stage.wgsl.jinja", "bindings": "fc1Activation", "dispatch": { "threads": "min(hiddenChunkTokens, numTokens - repeat.chunk * hiddenChunkTokens) * topK * interSize", "workgroupSize": "constants.workgroupSize" } }, { "id": "output_stage", "name": "QMoE.OutputStage", "shader": "qmoe-output-stage.wgsl.jinja", "bindings": "output", "dispatch": { "threads": "min(hiddenChunkTokens, numTokens - repeat.chunk * hiddenChunkTokens) * hiddenSize", "workgroupSize": "constants.workgroupSize" } } ] } ] } ] }