Mojo function

generic_get_continuous_cache

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

Returns:

ContinuousBatchingKVCacheCollection

View source

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!