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

mla_sm100_prefill_generic

def mla_sm100_prefill_generic[output_dtype: DType, q_type: DType, KVType: MHAOperand, VType: MHAOperand, KRopeType: MHAOperand, MaskType: MHAMask, MaxPromptLenType: OptionallyStaticInt, //, config: MHAConfig[config.dtype], group: Int, q_depth: Int, cache_depth: Int, _ndbuffer_mha_operand: Bool, v_depth: Int = Int(-1)](output: TileTensor[output_dtype, Storage=output.Storage, linear_idx_type=output.linear_idx_type], q: TileTensor[q_type, Storage=q.Storage, linear_idx_type=q.linear_idx_type], k: KVType, v: VType, k_rope: KRopeType, mask_functor: MaskType, valid_length: TileTensor[DType.uint32, Storage=valid_length.Storage, linear_idx_type=valid_length.linear_idx_type], max_prompt_len: MaxPromptLenType, scale: Float32, batch_size: Int, ctx: DeviceContext)