IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /max/get-started.md). For the complete documentation index, see llms.txt.
Skip to main content
For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Mojo function

with_mask_flash_attention_split_kv_cpu_shape

def with_mask_flash_attention_split_kv_cpu_shape[dtype: DType, rank: Int](q: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=q.static_spec], k: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=k.static_spec], v: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=v.static_spec], k_cache: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=k_cache.static_spec], v_cache: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=v_cache.static_spec], mask: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=mask.static_spec], scale: Float32) -> IndexList[rank]

Computes the output shape for the with_mask_flash_attention_split_kv_cpu graph op.

Returns:

IndexList[rank]