Mojo function

kv_matmul_ragged_paged

kv_matmul_ragged_paged[dtype: DType, num_heads: Int, head_dim: Int, page_size: Int, //, target: StringSlice[StaticConstantOrigin]](hidden_state: NDBuffer[dtype, 2, origin, shape], input_row_offsets: NDBuffer[DType.uint32, 1, origin, shape, strides], weight: NDBuffer[dtype, 2, origin, shape], kv_collection: PagedKVCacheCollection[dtype, KVCacheStaticParams(UInt(num_heads), UInt(head_dim)), page_size], layer_idx: UInt32, ctx: DeviceContextPtr)

Performs a matmul, writing the output into a mutable ContinuousBatchingKVCacheCollection object.

Args:

hidden_state (NDBuffer): Tensor with shape (sum(seq_lens), num_heads * head_size).
input_row_offsets (NDBuffer): Tensor with shape (batch_size + 1,) denoting the start of each sequence along the seq_len dimension.
weight (NDBuffer): Tensor with shape (num_heads * head_size, num_kv_heads * head_size).
kv_collection (PagedKVCacheCollection): The historical KVCache for keys and values. The KVCache for this layer is retrieved via layer_idx.
layer_idx (UInt32): The index of the layer being executed. Used to retrieve the KVCache for the given layer from kv_collection.
ctx (DeviceContextPtr): The call context pointer, passed by the graph compiler.