Mojo function

grouped_matmul_amd

grouped_matmul_amd[c_type: DType, a_type: DType, b_type: DType, *, transpose_b: Bool = True, block_tile_shape: IndexList[3] = Index[Int, Int, Int](128, 128, 64), elementwise_lambda_fn: Optional[elementwise_epilogue_type] = None](c: TileTensor[c_type, c.LayoutType, c.origin, linear_idx_type=c.linear_idx_type, element_size=c.element_size], a: TileTensor[a_type, a.LayoutType, a.origin, linear_idx_type=a.linear_idx_type, element_size=a.element_size], a_offsets: TileTensor[DType.uint32, a_offsets.LayoutType, a_offsets.origin, linear_idx_type=a_offsets.linear_idx_type, element_size=a_offsets.element_size], max_num_tokens_per_expert: Int, b: TileTensor[b_type, b.LayoutType, b.origin, linear_idx_type=b.linear_idx_type, element_size=b.element_size], expert_ids: TileTensor[DType.int32, expert_ids.LayoutType, expert_ids.origin, linear_idx_type=expert_ids.linear_idx_type, element_size=expert_ids.element_size], num_active_experts: Int, ctx: DeviceContext)

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit