| { |
| "op": "com.microsoft.MoE", |
| "cases": [ |
| { |
| "name": "relu_top1_no_bias", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "default activation_type (relu), one expert per token", |
| "notes": "The schema's default activation and nothing optional: no biases, no FC3. Every other case is a delta from this one." |
| }, |
| "attrs": { "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.19, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "gelu_top1_fc1_bias", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "activation_type gelu with an FC1 bias", |
| "notes": "The tanh-approximate GELU used by ONNX Runtime's MoE kernel, over an FC1 that carries its own per-expert bias. The bias joins the projection before the activation, which is what separates it from a bias on the output side." |
| }, |
| "attrs": { "k": 1, "activation_type": "gelu", "normalize_routing_weights": 0 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.19, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.13, "scale": 0.25 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "silu_topk2_fc2_bias", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "activation_type silu at k = 2 with an FC2 bias", |
| "notes": "The FC2 bias belongs to the expert, so at k = 2 each selected expert contributes its own bias scaled by its own routing weight. Adding it once to the routed sum instead would be wrong by the difference of the two experts' biases." |
| }, |
| "attrs": { "k": 2, "activation_type": "silu", "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.19, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.43, "cosStep": 0.17, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "silu_gate_fc3_no_bias", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "activation_type silu with FC3 as a multiplicative linear projection", |
| "notes": "The pinned CUDA provider's separate FC3 gated-MLP form computes the FC3 projection times SiLU of the FC1 projection." |
| }, |
| "attrs": { "k": 1, "activation_type": "silu", "normalize_routing_weights": 0 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.19, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.29, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "silu_gate_fc3_every_bias", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "all three optional biases present at once", |
| "notes": "FC1, FC2 and FC3 biases together on the provider-defined SiLU gated path." |
| }, |
| "attrs": { "k": 2, "activation_type": "silu", "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.19, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.13, "scale": 0.25 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.43, "cosStep": 0.17, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.29, "scale": 0.15 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.31, "cosStep": 0.23, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "swiglu_fusion2_top1", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "swiglu_fusion 2 (fused, concatenated halves)", |
| "notes": "One fused FC1 whose row block holds the gate half then the linear half. inter_size is the FC1 row count halved, which is what fusion_size 2 means in the schema's shape formula." |
| }, |
| "attrs": { |
| "k": 1, |
| "activation_type": "swiglu", |
| "swiglu_fusion": 2, |
| "normalize_routing_weights": 1, |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.33, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.41, "cosStep": 0.23, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 6, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "swiglu_fusion1_interleaved_topk2", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "swiglu_fusion 1 (fused, interleaved rows)", |
| "notes": "The same fused FC1 as fusion 2 but with the two operands interleaved: lane i reads rows 2i and 2i+1 rather than i and inter+i. Reading the concatenated layout here still lands on the right gate row for lane 0 and on the wrong linear row for it, and on the wrong row for both operands of every later lane." |
| }, |
| "attrs": { |
| "k": 2, |
| "activation_type": "swiglu", |
| "swiglu_fusion": 1, |
| "normalize_routing_weights": 1, |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [4, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.33, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [4, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.41, "cosStep": 0.23, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 6, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 6], |
| "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.13, "scale": 0.25 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [4, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "swiglu_fusion0_separate_fc3", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "swiglu_fusion 0 (two unfused GEMMs)", |
| "notes": "With the GEMMs unfused the SwiGLU operands come from separate FC1 and FC3 tensors, so fusion_size is 1 and inter_size is the full FC1 row count. FC3 is required in this form and rejected in the fused ones." |
| }, |
| "attrs": { |
| "k": 1, |
| "activation_type": "swiglu", |
| "swiglu_fusion": 0, |
| "normalize_routing_weights": 0, |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.19, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.29, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "swiglu_fusion2_limit_clamped", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "swiglu_limit clamping both operands", |
| "notes": "swiglu_limit clamps the gate operand from above and the linear operand into [-limit, limit] before the product. The limit is small enough here that it actually binds; when the attribute is absent no clamp is applied at all." |
| }, |
| "attrs": { |
| "k": 1, |
| "activation_type": "swiglu", |
| "swiglu_fusion": 2, |
| "normalize_routing_weights": 1, |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05, |
| "swiglu_limit": 0.35 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.33, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.41, "cosStep": 0.23, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 6, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.43, "cosStep": 0.17, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "rank3_batched_relu", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "3D input (batch, sequence, hidden)", |
| "notes": "num_tokens is the product of every leading dimension, so a [1, 3, 4] input routes exactly like the [3, 4] case while the output keeps the 3D shape." |
| }, |
| "attrs": { "k": 1, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [1, 3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.19, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [1, 3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "topk_equals_expert_count", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "k equal to the expert count", |
| "notes": "Every expert is selected for every token, which is the upper bound the contract allows and the case where the router's taken-exclusion has to visit every index without repeating one." |
| }, |
| "attrs": { "k": 3, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.17, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.19, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "empty_tokens_zero_dim", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "zero-token input", |
| "notes": "A zero-length token axis: every stage dispatches nothing and the output is empty. The route scratch is still allocated at one element so the binding stays well-formed." |
| }, |
| "attrs": { "k": 1, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { "dtype": "float32", "shape": [0, 4], "data": { "kind": "values", "values": [] } }, |
| "routerT": { "dtype": "float32", "shape": [0, 3], "data": { "kind": "values", "values": [] } }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [0, 4], "tolerance": 0 } } |
| }, |
| { |
| "name": "gelu_fc1_bias_fc2_bias", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "com.microsoft.MoE optional-input combination", |
| "notes": "Each optional input changes the binding layout, so every combination of FC1 bias, FC3 (with or without its own bias) and FC2 bias is a distinct variant. This case is the one that selects fc1bias / no FC3 / fc2bias; without it that variant would ship unexercised." |
| }, |
| "attrs": { "k": 1, "activation_type": "gelu", "normalize_routing_weights": 0 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.19, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.21, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.13, "scale": 0.25 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.43, "cosStep": 0.17, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_silu_gate_fc3_fc2_bias", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "com.microsoft.MoE optional-input combination", |
| "notes": "This optional-input layout uses a 128-wide reduction so the cooperative GEMV schedule exercises SiLU with a separate, unbiased FC3 projection and FC2 bias." |
| }, |
| "attrs": { "k": 2, "activation_type": "silu", "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.21, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.23, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.43, "cosStep": 0.17, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.29, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_silu_gate_fc3_bias_only", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "com.microsoft.MoE optional-input combination", |
| "notes": "This optional-input layout supplies enough routed slots for the expert-grouped schedule to exercise SiLU with a separately biased FC3 projection and no FC2 bias." |
| }, |
| "attrs": { "k": 1, "activation_type": "silu", "normalize_routing_weights": 0 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [96, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.23, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [96, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.25, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.29, "scale": 0.15 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.31, "cosStep": 0.23, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [96, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "silu_gate_fc3_bias_fc2_bias", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "com.microsoft.MoE optional-input combination", |
| "notes": "Each optional input changes the binding layout, so every combination of FC1 bias, FC3 (with or without its own bias) and FC2 bias is a distinct variant. This case is the one that selects no FC1 bias / FC3 with bias / fc2bias; without it that variant would ship unexercised." |
| }, |
| "attrs": { "k": 2, "activation_type": "silu", "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.25, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.27, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.43, "cosStep": 0.17, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.29, "scale": 0.15 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.31, "cosStep": 0.23, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "silu_fc1_bias_gate_fc3", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "com.microsoft.MoE optional-input combination", |
| "notes": "Each optional input changes the binding layout, so every combination of FC1 bias, FC3 (with or without its own bias) and FC2 bias is a distinct variant. This case is the one that selects fc1bias / FC3 without bias / no FC2 bias; without it that variant would ship unexercised." |
| }, |
| "attrs": { "k": 1, "activation_type": "silu", "normalize_routing_weights": 0 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.27, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.29, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.13, "scale": 0.25 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.29, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "silu_fc1_bias_gate_fc3_fc2_bias", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "com.microsoft.MoE optional-input combination", |
| "notes": "Each optional input changes the binding layout, so every combination of FC1 bias, FC3 (with or without its own bias) and FC2 bias is a distinct variant. This case is the one that selects fc1bias / FC3 without bias / fc2bias; without it that variant would ship unexercised." |
| }, |
| "attrs": { "k": 2, "activation_type": "silu", "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.31, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.13, "scale": 0.25 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.43, "cosStep": 0.17, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.29, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "ort_softmax_tie_break_top1", |
| "provenance": { |
| "source": "onnxruntime/contrib_ops/cpu/moe/moe_cpu.cc", |
| "test": "full-softmax routing and equal-probability pair ordering", |
| "notes": "Equal zero logits become probabilities [0.5, 0.5]. ONNX Runtime selects the higher expert index on the tie; that expert emits 6, and the non-normalized route probability scales the result to exactly 3. This also exercises the schema defaults k=1, activation_type=relu, and normalize_routing_weights=0." |
| }, |
| "inputs": { |
| "inputT": { "dtype": "float32", "shape": [1, 1], "data": { "kind": "values", "values": [1.0] } }, |
| "routerT": { "dtype": "float32", "shape": [1, 2], "data": { "kind": "values", "values": [0.0, 0.0] } }, |
| "fc1T": { "dtype": "float32", "shape": [2, 1, 1], "data": { "kind": "values", "values": [1.0, 2.0] } }, |
| "fc2T": { "dtype": "float32", "shape": [2, 1, 1], "data": { "kind": "values", "values": [1.0, 3.0] } } |
| }, |
| "outputs": { |
| "outputT": { |
| "dtype": "float32", |
| "shape": [1, 1], |
| "tolerance": 0, |
| "data": { "kind": "values", "values": [3.0] } |
| } |
| } |
| }, |
| { |
| "name": "silu_fc1_bias_gate_fc3_bias", |
| "provenance": { |
| "source": "onnxruntime/docs/ContribOperators.md#com.microsoft.MoE", |
| "test": "com.microsoft.MoE optional-input combination", |
| "notes": "Each optional input changes the binding layout, so every combination of FC1 bias, FC3 (with or without its own bias) and FC2 bias is a distinct variant. This case is the one that selects fc1bias / FC3 with bias / no FC2 bias; without it that variant would ship unexercised." |
| }, |
| "attrs": { "k": 1, "activation_type": "silu", "normalize_routing_weights": 0 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.31, "cosStep": 0.31, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.33, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.13, "scale": 0.25 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.16 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.29, "scale": 0.15 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.31, "cosStep": 0.23, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1plain_fc3none_fc2plain_identity", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { "activation_type": "identity", "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.31, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.26, "cosStep": 0.24, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.36, "scale": 0.12 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.09, "cosStep": 0.28, "scale": 0.12 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1plain_fc3none_fc2bias_swiglu2", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { |
| "k": 2, |
| "activation_type": "swiglu", |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05, |
| "swiglu_fusion": 2, |
| "normalize_routing_weights": 1 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.083, "cosStep": 0.299, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.273, "cosStep": 0.229, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 256, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.123, "cosStep": 0.349, "scale": 0.12 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.103, "cosStep": 0.269, "scale": 0.12 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.233, "cosStep": 0.319, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1bias_fc3none_fc2plain_swiglu1", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { "k": 2, "activation_type": "swiglu", "swiglu_fusion": 1, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.096, "cosStep": 0.288, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.286, "cosStep": 0.218, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 256, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.136, "cosStep": 0.338, "scale": 0.12 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 256], |
| "data": { "kind": "fillFloat32", "sinStep": 0.186, "cosStep": 0.418, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.116, "cosStep": 0.258, "scale": 0.12 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1bias_fc3none_fc2bias_swiglu2", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { "activation_type": "swiglu", "swiglu_fusion": 2, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.109, "cosStep": 0.277, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.299, "cosStep": 0.207, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 256, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.149, "cosStep": 0.327, "scale": 0.12 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 256], |
| "data": { "kind": "fillFloat32", "sinStep": 0.199, "cosStep": 0.407, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.129, "cosStep": 0.247, "scale": 0.12 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.259, "cosStep": 0.297, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1plain_fc3plain_fc2plain_swiglu0", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { "activation_type": "swiglu", "swiglu_fusion": 0, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.122, "cosStep": 0.266, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.312, "cosStep": 0.196, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.162, "cosStep": 0.316, "scale": 0.12 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.142, "cosStep": 0.236, "scale": 0.12 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.182, "cosStep": 0.356, "scale": 0.12 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1plain_fc3plain_fc2bias_swiglu0", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { |
| "k": 2, |
| "activation_type": "swiglu", |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05, |
| "swiglu_fusion": 0, |
| "normalize_routing_weights": 1 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.135, "cosStep": 0.255, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.325, "cosStep": 0.185, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.175, "cosStep": 0.305, "scale": 0.12 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.155, "cosStep": 0.225, "scale": 0.12 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.285, "cosStep": 0.275, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.195, "cosStep": 0.345, "scale": 0.12 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1plain_fc3biased_fc2plain_swiglu0", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { |
| "activation_type": "swiglu", |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05, |
| "swiglu_fusion": 0, |
| "normalize_routing_weights": 1 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.148, "cosStep": 0.244, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.338, "cosStep": 0.174, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.188, "cosStep": 0.294, "scale": 0.12 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.168, "cosStep": 0.214, "scale": 0.12 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.208, "cosStep": 0.334, "scale": 0.12 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.258, "cosStep": 0.194, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1plain_fc3biased_fc2bias_swiglu0", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { "k": 2, "activation_type": "swiglu", "swiglu_fusion": 0, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.161, "cosStep": 0.233, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.351, "cosStep": 0.163, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.201, "cosStep": 0.283, "scale": 0.12 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.181, "cosStep": 0.203, "scale": 0.12 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.311, "cosStep": 0.253, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.221, "cosStep": 0.323, "scale": 0.12 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.271, "cosStep": 0.183, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1bias_fc3plain_fc2plain_swiglu0", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { |
| "k": 2, |
| "activation_type": "swiglu", |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05, |
| "swiglu_fusion": 0, |
| "normalize_routing_weights": 1 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.174, "cosStep": 0.222, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.364, "cosStep": 0.152, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.214, "cosStep": 0.272, "scale": 0.12 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.264, "cosStep": 0.352, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.194, "cosStep": 0.192, "scale": 0.12 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.234, "cosStep": 0.312, "scale": 0.12 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1bias_fc3plain_fc2bias_swiglu0", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { "activation_type": "swiglu", "swiglu_fusion": 0, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.187, "cosStep": 0.211, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.377, "cosStep": 0.141, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.227, "cosStep": 0.261, "scale": 0.12 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.277, "cosStep": 0.341, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.207, "cosStep": 0.181, "scale": 0.12 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.337, "cosStep": 0.231, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.247, "cosStep": 0.301, "scale": 0.12 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1bias_fc3biased_fc2plain_swiglu0", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { "k": 2, "activation_type": "swiglu", "swiglu_fusion": 0, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.2, "cosStep": 0.2, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.39, "cosStep": 0.13, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.24, "cosStep": 0.25, "scale": 0.12 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.33, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.22, "cosStep": 0.17, "scale": 0.12 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.26, "cosStep": 0.29, "scale": 0.12 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.31, "cosStep": 0.15, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_fc1bias_fc3biased_fc2bias_swiglu0", |
| "provenance": { |
| "notes": "A 128-long reduction on both projections, deep enough for the cooperative schedule; the 4-wide cases above stay on the one-thread-per-column schedule." |
| }, |
| "attrs": { |
| "activation_type": "swiglu", |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05, |
| "swiglu_fusion": 0, |
| "normalize_routing_weights": 1 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.213, "cosStep": 0.189, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.403, "cosStep": 0.119, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.253, "cosStep": 0.239, "scale": 0.12 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.303, "cosStep": 0.319, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.233, "cosStep": 0.159, "scale": 0.12 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.363, "cosStep": 0.209, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.273, "cosStep": 0.279, "scale": 0.12 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.323, "cosStep": 0.139, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "identity_activation_top1", |
| "provenance": { |
| "notes": "activation_type identity passes the FC1 projection through unchanged, which is the only declared activation with no other case." |
| }, |
| "attrs": { "activation_type": "identity" }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [3, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.13, "cosStep": 0.29, "scale": 0.5 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [3, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.17, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 5, 4], |
| "data": { "kind": "fillFloat32", "sinStep": 0.11, "cosStep": 0.23, "scale": 0.18 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 4, 5], |
| "data": { "kind": "fillFloat32", "sinStep": 0.07, "cosStep": 0.41, "scale": 0.18 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [3, 4], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "deep_reduction_gelu_fc2bias", |
| "provenance": { |
| "notes": "GELU over a 128-long reduction makes the cooperative schedule exercise its tanh-approximation activation path." |
| }, |
| "attrs": { "k": 2, "activation_type": "gelu", "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [2, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.23, "cosStep": 0.17, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [2, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.43, "cosStep": 0.11, "scale": 0.6 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.27, "cosStep": 0.19, "scale": 0.12 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 128, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.25, "cosStep": 0.33, "scale": 0.12 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 128], |
| "data": { "kind": "fillFloat32", "sinStep": 0.38, "cosStep": 0.21, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [2, 128], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1plain_fc3none_fc2plain_relu", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { "k": 2, "activation_type": "relu", "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [48, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.09, "cosStep": 0.29, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [48, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.3, "cosStep": 0.24, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.12, "cosStep": 0.36, "scale": 0.15 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.14, "cosStep": 0.26, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [48, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1plain_fc3none_fc2bias_swiglu2", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { |
| "activation_type": "swiglu", |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05, |
| "swiglu_fusion": 2, |
| "normalize_routing_weights": 1 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [96, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.107, "cosStep": 0.281, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [96, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.317, "cosStep": 0.231, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 64, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.137, "cosStep": 0.351, "scale": 0.15 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.157, "cosStep": 0.251, "scale": 0.15 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.277, "cosStep": 0.321, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [96, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1bias_fc3none_fc2plain_swiglu1", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { "k": 2, "activation_type": "swiglu", "swiglu_fusion": 1, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [48, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.124, "cosStep": 0.272, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [48, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.334, "cosStep": 0.222, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 64, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.154, "cosStep": 0.342, "scale": 0.15 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 64], |
| "data": { "kind": "fillFloat32", "sinStep": 0.234, "cosStep": 0.422, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.174, "cosStep": 0.242, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [48, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1bias_fc3none_fc2bias_swiglu2", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { "activation_type": "swiglu", "swiglu_fusion": 2, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [96, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.141, "cosStep": 0.263, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [96, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.351, "cosStep": 0.213, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 64, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.171, "cosStep": 0.333, "scale": 0.15 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 64], |
| "data": { "kind": "fillFloat32", "sinStep": 0.251, "cosStep": 0.413, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.191, "cosStep": 0.233, "scale": 0.15 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.311, "cosStep": 0.303, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [96, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_partial_tiles_gelu", |
| "provenance": { |
| "notes": "Half the routed slots the grouped schedule used to demand, so most of every expert's tile is padding: the tiles are 32 rows and 3 experts share only 64 slots. Covers the band the slot threshold opened, where the store guard drops more rows than it keeps." |
| }, |
| "attrs": { "activation_type": "gelu", "normalize_routing_weights": 1, "k": 2 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.173, "cosStep": 0.229, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [32, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.347, "cosStep": 0.163, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.199, "cosStep": 0.271, "scale": 0.15 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.251, "cosStep": 0.413, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.241, "cosStep": 0.179, "scale": 0.15 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.311, "cosStep": 0.303, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [32, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1plain_fc3plain_fc2plain_swiglu0", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { "activation_type": "swiglu", "swiglu_fusion": 0, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [96, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.158, "cosStep": 0.254, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [96, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.368, "cosStep": 0.204, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.188, "cosStep": 0.324, "scale": 0.15 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.208, "cosStep": 0.224, "scale": 0.15 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.228, "cosStep": 0.364, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [96, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1plain_fc3plain_fc2bias_swiglu0", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { |
| "k": 2, |
| "activation_type": "swiglu", |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05, |
| "swiglu_fusion": 0, |
| "normalize_routing_weights": 1 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [48, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.175, "cosStep": 0.245, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [48, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.385, "cosStep": 0.195, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.205, "cosStep": 0.315, "scale": 0.15 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.225, "cosStep": 0.215, "scale": 0.15 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.345, "cosStep": 0.285, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.245, "cosStep": 0.355, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [48, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1plain_fc3biased_fc2plain_swiglu0", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { |
| "activation_type": "swiglu", |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05, |
| "swiglu_fusion": 0, |
| "normalize_routing_weights": 1 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [96, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.192, "cosStep": 0.236, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [96, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.402, "cosStep": 0.186, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.222, "cosStep": 0.306, "scale": 0.15 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.242, "cosStep": 0.206, "scale": 0.15 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.262, "cosStep": 0.346, "scale": 0.15 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.322, "cosStep": 0.176, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [96, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1plain_fc3biased_fc2bias_swiglu0", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { "k": 2, "activation_type": "swiglu", "swiglu_fusion": 0, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [48, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.209, "cosStep": 0.227, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [48, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.419, "cosStep": 0.177, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.239, "cosStep": 0.297, "scale": 0.15 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.259, "cosStep": 0.197, "scale": 0.15 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.379, "cosStep": 0.267, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.279, "cosStep": 0.337, "scale": 0.15 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.339, "cosStep": 0.167, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [48, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1bias_fc3plain_fc2plain_swiglu0", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { |
| "k": 2, |
| "activation_type": "swiglu", |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05, |
| "swiglu_fusion": 0, |
| "normalize_routing_weights": 1 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [48, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.226, "cosStep": 0.218, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [48, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.436, "cosStep": 0.168, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.256, "cosStep": 0.288, "scale": 0.15 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.336, "cosStep": 0.368, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.276, "cosStep": 0.188, "scale": 0.15 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.296, "cosStep": 0.328, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [48, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1bias_fc3plain_fc2bias_swiglu0", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { "activation_type": "swiglu", "swiglu_fusion": 0, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [96, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.243, "cosStep": 0.209, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [96, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.453, "cosStep": 0.159, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.273, "cosStep": 0.279, "scale": 0.15 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.353, "cosStep": 0.359, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.293, "cosStep": 0.179, "scale": 0.15 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.413, "cosStep": 0.249, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.313, "cosStep": 0.319, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [96, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1bias_fc3biased_fc2plain_swiglu0", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { "k": 2, "activation_type": "swiglu", "swiglu_fusion": 0, "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [48, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.26, "cosStep": 0.2, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [48, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.47, "cosStep": 0.15, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.29, "cosStep": 0.27, "scale": 0.15 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.37, "cosStep": 0.35, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.31, "cosStep": 0.17, "scale": 0.15 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.33, "cosStep": 0.31, "scale": 0.15 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.39, "cosStep": 0.14, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [48, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_fc1bias_fc3biased_fc2bias_swiglu0", |
| "provenance": { |
| "notes": "Enough routed slots per expert to fill grouped tiles, so the expert-grouped schedule reuses one staged weight tile across a tile of slots." |
| }, |
| "attrs": { |
| "activation_type": "swiglu", |
| "activation_alpha": 1.702, |
| "activation_beta": 0.05, |
| "swiglu_fusion": 0, |
| "normalize_routing_weights": 1 |
| }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [96, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.277, "cosStep": 0.191, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [96, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.487, "cosStep": 0.141, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.307, "cosStep": 0.261, "scale": 0.15 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.387, "cosStep": 0.341, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.327, "cosStep": 0.161, "scale": 0.15 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.447, "cosStep": 0.231, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 32, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.347, "cosStep": 0.301, "scale": 0.15 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 32], |
| "data": { "kind": "fillFloat32", "sinStep": 0.407, "cosStep": 0.131, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [96, 32], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_identity_no_fc3", |
| "provenance": { |
| "notes": "The smallest default-tile prefill that meets the grouped schedule's routed-slot threshold, and exercises identity activation without FC3 after expert grouping." |
| }, |
| "attrs": { "k": 2, "activation_type": "identity", "normalize_routing_weights": 1 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [48, 16], |
| "data": { "kind": "fillFloat32", "sinStep": 0.181, "cosStep": 0.217, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [48, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.391, "cosStep": 0.127, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 16, 16], |
| "data": { "kind": "fillFloat32", "sinStep": 0.211, "cosStep": 0.287, "scale": 0.15 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 16, 16], |
| "data": { "kind": "fillFloat32", "sinStep": 0.231, "cosStep": 0.187, "scale": 0.15 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [48, 16], "tolerance": 0.00002 } } |
| }, |
| { |
| "name": "grouped_prefill_unaligned_hidden_inter", |
| "provenance": { |
| "notes": "Hidden 34 and intermediate 30 are not divisible by four, so grouped staging uses scalar activation and weight reads. The gated FC3 stream adds a second scalar weight stream, and every K tile is partial against the 16-wide tile." |
| }, |
| "attrs": { "activation_type": "silu", "normalize_routing_weights": 1, "k": 2 }, |
| "inputs": { |
| "inputT": { |
| "dtype": "float32", |
| "shape": [96, 34], |
| "data": { "kind": "fillFloat32", "sinStep": 0.163, "cosStep": 0.239, "scale": 0.4 } |
| }, |
| "routerT": { |
| "dtype": "float32", |
| "shape": [96, 3], |
| "data": { "kind": "fillFloat32", "sinStep": 0.337, "cosStep": 0.173, "scale": 0.7 } |
| }, |
| "fc1T": { |
| "dtype": "float32", |
| "shape": [3, 30, 34], |
| "data": { "kind": "fillFloat32", "sinStep": 0.209, "cosStep": 0.281, "scale": 0.15 } |
| }, |
| "fc1BiasT": { |
| "dtype": "float32", |
| "shape": [3, 30], |
| "data": { "kind": "fillFloat32", "sinStep": 0.261, "cosStep": 0.423, "scale": 0.2 } |
| }, |
| "fc2T": { |
| "dtype": "float32", |
| "shape": [3, 34, 30], |
| "data": { "kind": "fillFloat32", "sinStep": 0.251, "cosStep": 0.189, "scale": 0.15 } |
| }, |
| "fc2BiasT": { |
| "dtype": "float32", |
| "shape": [3, 34], |
| "data": { "kind": "fillFloat32", "sinStep": 0.321, "cosStep": 0.313, "scale": 0.2 } |
| }, |
| "fc3T": { |
| "dtype": "float32", |
| "shape": [3, 30, 34], |
| "data": { "kind": "fillFloat32", "sinStep": 0.227, "cosStep": 0.197, "scale": 0.15 } |
| }, |
| "fc3BiasT": { |
| "dtype": "float32", |
| "shape": [3, 30], |
| "data": { "kind": "fillFloat32", "sinStep": 0.283, "cosStep": 0.359, "scale": 0.2 } |
| } |
| }, |
| "outputs": { "outputT": { "dtype": "float32", "shape": [96, 34], "tolerance": 0.00002 } } |
| } |
| ] |
| } |
|
|
