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
Struct_mla_compute_dispatch_args_scalar
struct Struct_mla_compute_dispatch_args_scalar
Implemented traitsโ
AnyType,
ImplicitlyDestructible
Methodsโ
executeโ
static def execute[num_heads: Int, is_fp8_kv: Bool, target: StringSlice[StaticConstantOrigin]](output: ManagedTensorSlice[Output, static_spec=output.static_spec], batch_size_tensor: ManagedTensorSlice[Input, static_spec=batch_size_tensor.static_spec], max_cache_valid_length_tensor: ManagedTensorSlice[Input, static_spec=max_cache_valid_length_tensor.static_spec], q_max_seq_len_tensor: ManagedTensorSlice[Input, static_spec=q_max_seq_len_tensor.static_spec], context: DeviceContext)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!