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
generic_get_continuous_cache
def generic_get_continuous_cache[dtype: DType, kv_params: KVCacheStaticParams](blocks: LayoutTensor[dtype, Layout.row_major[Int(6)]()], cache_lengths: LayoutTensor[DType.uint32, Layout(IntTuple(Int(-1)))], lookup_table: LayoutTensor[DType.uint32, Layout(IntTuple(Int(-1)))], max_lengths: LayoutTensor[DType.uint32, Layout.row_major[Int(2)]()]) -> ContinuousBatchingKVCacheCollection[dtype, kv_params, blocks.origin, cache_lengths.origin, lookup_table.origin]
Returns:
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!