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]
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!