Mojo function

fp8_index_kernel

fp8_index_kernel[dtype: DType, output_layout: Layout, q_layout: Layout, qs_layout: Layout, k_operand_type: MHAOperand, ks_operand_type: MHAOperand, block_tile_shape: InlineArray[Int, 2], valid_length_layout: Layout, num_heads: Int, depth: Int, _is_cache_length_accurate: Bool = False](output: LayoutTensor[DType.float32, output_layout, MutAnyOrigin], q: LayoutTensor[dtype, q_layout, ImmutAnyOrigin], q_s: LayoutTensor[DType.float32, qs_layout, MutAnyOrigin], k_operand: k_operand_type, ks_operand: ks_operand_type, valid_length: LayoutTensor[DType.uint32, valid_length_layout, ImmutAnyOrigin])

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