Mojo struct

MLAAttentionConfig

struct MLAAttentionConfig[token_gen: Bool, config: MHAConfig]

Implemented traits

AnyType, AttentionConfig, Copyable, ImplicitlyCopyable, UnknownDestructibility

Aliases

__copyinit__is_trivial

alias __copyinit__is_trivial = True

__del__is_trivial

alias __del__is_trivial = True

depth_padded

alias depth_padded = True

double_buffer

alias double_buffer = False

full_kv

alias full_kv = False

shared_kv

alias shared_kv = True

Methods

q_head_idx

static q_head_idx() -> UInt

Returns:

UInt

q_tile_idx

static q_tile_idx() -> UInt

Returns:

UInt

kv_head_idx

static kv_head_idx() -> UInt

Returns:

UInt

get_mma_shape

static get_mma_shape() -> IndexList[3]

Returns:

IndexList

get_q_offset

static get_q_offset[q_depth: UInt]() -> UInt32

Returns:

UInt32

get_output_offset

static get_output_offset[output_depth: UInt]() -> UInt32

Returns:

UInt32

Was this page helpful?

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

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit