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 module

mla

comptime values

AMD_MLA_DECODE_FOLD_M_MAX

comptime AMD_MLA_DECODE_FOLD_M_MAX = 128

AMD_MLA_DECODE_FOLD_MAX_NUM_HEADS

comptime AMD_MLA_DECODE_FOLD_MAX_NUM_HEADS = 16

MLA_DECODE_MAX_SEQ_LEN

comptime MLA_DECODE_MAX_SEQ_LEN = 8

Functions

• ​copy_fn_unified:
• ​flare_mla_decoding: MLA decoding kernel that would only be called in the optimized compute graph.
• ​flare_mla_decoding_dispatch:
• ​flare_mla_prefill: MLA prefill kernel that would only be called in the optimized compute graph. Only supports ragged Q/K/V inputs.
• ​flare_mla_prefill_dispatch:
• ​mla_decode_max_seq_len: Max query tokens (S) the MLA decode branch can fold for this config.
• ​mla_decoding:
• ​mla_decoding_single_batch: Flash attention v2 algorithm.
• ​mla_prefill:
• ​mla_prefill_plan: This calls a GPU kernel that plans how to process a batch of sequences with varying lengths using a fixed-size buffer.
• ​mla_prefill_plan_kernel:
• ​mla_prefill_single_batch: MLA for encoding where seqlen > 1.
• ​mla_splitk_reduce:
• ​q_block_idx:
• ​set_buffer_lengths_to_zero:

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit