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

MHAAttentionConfigRDNA

struct MHAAttentionConfigRDNA[token_gen: Bool, config: MHAConfig[config.dtype], group: Int]

Implemented traits

AnyType, Copyable, ImplicitlyCopyable, ImplicitlyDeletable, Movable

comptime members

depth_padded

comptime depth_padded = True

double_buffer

comptime double_buffer = False

double_buffer_k_only

comptime double_buffer_k_only = False

full_kv

comptime full_kv = False

shared_kv

comptime shared_kv = False

Methods

q_head_idx

static def q_head_idx() -> Int

Returns:

Int

q_tile_idx

static def q_tile_idx() -> Int

Returns:

Int

kv_head_idx

static def kv_head_idx() -> Int

Returns:

Int

get_mma_shape

static def get_mma_shape() -> IndexList[3]

Returns:

IndexList[3]

get_q_offset

static def get_q_offset[q_depth: Int]() -> UInt32

Returns:

UInt32

get_output_offset

static def get_output_offset[output_depth: Int]() -> UInt32

Returns:

UInt32