Mojo function
block_scales_interleave_fp4_kernel
block_scales_interleave_fp4_kernel[scales_dtype: DType, input_scales_layout: Layout, output_scales_layout: Layout, *, SF_VECTOR_SIZE: Int = 16, num_max_threads: Int = 1024](input_scales: LayoutTensor[scales_dtype, input_scales_layout, MutAnyOrigin], output_scales: LayoutTensor[scales_dtype, output_scales_layout, MutAnyOrigin])
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!