diff options
Diffstat (limited to 'include/llama.h')
| -rw-r--r-- | include/llama.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/include/llama.h b/include/llama.h index 730c087a..39251d35 100644 --- a/include/llama.h +++ b/include/llama.h @@ -374,6 +374,7 @@ extern "C" { bool embeddings; // if true, extract embeddings (together with logits) bool offload_kqv; // whether to offload the KQV ops (including the KV cache) to GPU bool flash_attn; // whether to use flash attention [EXPERIMENTAL] + bool mla_attn; // whether to use MLA attention [EXPERIMENTAL] // Abort callback // if it returns true, execution of llama_decode() will be aborted |