diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-02-27 16:40:49 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-02-27 16:40:49 +0200 |
| commit | b762db7c9264199c2d0f66e7d63e3b4884f3fc0c (patch) | |
| tree | 01cc16988a4d21b4c1df367df23f4fd53e6b58a0 /common/common.h | |
| parent | 51029edfdf286df76f9268fc87b9514291b2fe42 (diff) | |
Option to use MLA without a transposed cache (#235)
The `-mla` command line option turns into an int from a bool.
mla = 0: use standard attention
mla = 1: use MLA with transposed cache
mla > 1: use MLA without transposed cache
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'common/common.h')
| -rw-r--r-- | common/common.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/common/common.h b/common/common.h index 152fd1cf..ef5175f3 100644 --- a/common/common.h +++ b/common/common.h @@ -175,7 +175,7 @@ struct gpt_params { bool simple_io = false; // improves compatibility with subprocesses and limited consoles bool cont_batching = true; // insert new sequences for decoding on-the-fly bool flash_attn = false; // flash attention - bool mla_attn = false; // MLA + int mla_attn = false; // MLA 0: standard attention, 1: MLA with K and transposed V cache, 2: MLA with just K cache bool fused_moe_up_gate = false; // fused up*unary(gate) op for MoE models bool input_prefix_bos = false; // prefix BOS to user inputs, preceding input_prefix |