For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Mojo struct
Struct_kv_cache_pcp_pack_rows_paged_scaled
struct Struct_kv_cache_pcp_pack_rows_paged_scaled
Registers the kv_cache.pcp_pack_rows.paged.scaled graph op: the kv_cache.pcp_pack_rows.paged op over a cache with a scale pool, whose operands arrive in the order flatten_without_attention_dispatch_metadata emits for quantized cache params.
Implemented traitsโ
Methodsโ
executeโ
static def execute[col_offset: Int, dcp_size: Int, dcp_interleave: Int](output: T, row_offsets: T, kv_blocks: T, page_stride: T, cache_lengths: T, kv_lookup_table: T, max_prompt_length: T, max_cache_length: T, kv_scales: T, scales_page_stride: T, scales_lookup_table: T, layer_idx: UInt32, dcp_rank: Int32, context: DeviceContext)