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 struct
WithMaskFlashAttentionSplitKVCPU
struct WithMaskFlashAttentionSplitKVCPU
Registers the with_mask_flash_attention_split_kv_cpu graph op with the graph compiler.
Implemented traits
Methods
execute
static def execute[dtype: DType, rank: Int, target: StringSlice[ImmStaticOrigin]](output: ManagedTensorSlice[IOSpec[_, _].Output, static_spec=output.static_spec], q: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=q.static_spec], k: ManagedTensorSlice[IOSpec[_, _].FusedInput, static_spec=k.static_spec], v: ManagedTensorSlice[IOSpec[_, _].FusedInput, static_spec=v.static_spec], k_cache: ManagedTensorSlice[IOSpec[_, _].FusedInput, static_spec=k_cache.static_spec], v_cache: ManagedTensorSlice[IOSpec[_, _].FusedInput, static_spec=v_cache.static_spec], mask: ManagedTensorSlice[IOSpec[_, _].FusedInput, static_spec=mask.static_spec], scale: Float32, ctx: DeviceContext)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!