Mojo function
generic_fused_qk_rope_bshd_continuous_batch_ragged
generic_fused_qk_rope_bshd_continuous_batch_ragged[dtype: DType, freq_dtype: DType, //, *, interleaved: Bool, has_position_ids: Bool, target: StringSlice[StaticConstantOrigin], mrope_section: Optional[IntTuple] = None](q_proj: LayoutTensor[dtype, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], input_row_offsets: LayoutTensor[DType.uint32, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], kv_collection: ContinuousBatchingKVCacheCollection[dtype_, kv_params_], freqs_cis: LayoutTensor[freq_dtype, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], position_ids: LayoutTensor[DType.uint32, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], layer_idx: UInt32, output: LayoutTensor[dtype, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], context: DeviceContextPtr)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!