For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Mojo function

kv_cache_row_offsets_ragged_paged

def kv_cache_row_offsets_ragged_paged[target: StringSlice[StaticConstantOrigin]](cache_row_offsets: TileTensor[DType.uint32, Storage=cache_row_offsets.Storage, linear_idx_type=cache_row_offsets.linear_idx_type, element_size=cache_row_offsets.element_size], input_row_offsets: TileTensor[DType.uint32, Storage=input_row_offsets.Storage, linear_idx_type=input_row_offsets.linear_idx_type, element_size=input_row_offsets.element_size], cache_lengths: TileTensor[DType.uint32, Storage=cache_lengths.Storage, linear_idx_type=cache_lengths.linear_idx_type, element_size=cache_lengths.element_size], ctx: DeviceContext)

Builds cumulative valid-cache row offsets for a ragged prefill batch.

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