Skip to main content

Mojo function

generic_get_continuous_cache

generic_get_continuous_cache[dtype: DType, kv_params: KVCacheStaticParams](blocks: LayoutTensor[dtype, Layout.row_major[6](), blocks.origin], cache_lengths: LayoutTensor[DType.uint32, Layout(IntTuple(-1)), cache_lengths.origin], lookup_table: LayoutTensor[DType.uint32, Layout(IntTuple(-1)), lookup_table.origin], max_lengths: LayoutTensor[DType.uint32, Layout.row_major[2](), max_lengths.origin]) -> ContinuousBatchingKVCacheCollection[dtype, kv_params]

Returns:

ContinuousBatchingKVCacheCollection

Was this page helpful?