WeightQuantBatchMatmulV2TransposeFusionPass
Description
Offloads information about the Transpose nodes connected to WeightQuantBatchMatmulV2 to the transpose_x and transpose_weight attributes.
Constraints
- The Transpose nodes connected to antiquant_scale and antiquant_offset can be processed only when the weight node is connected to the Transpose node.
- This fusion pattern is mandatory. Disabling it will result in functional errors.
Applicable Products
Parent topic: Graph Fusion Patterns