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 2b33701c..bb43aebc 100644 --- a/include/llama.h +++ b/include/llama.h @@ -384,6 +384,7 @@ extern "C" { bool offload_kqv; // whether to offload the KQV ops (including the KV cache) to GPU bool flash_attn; // whether to use flash attention [EXPERIMENTAL] int mla_attn; // whether to use MLA attention [EXPERIMENTAL] + int attn_max_batch; // maximum batch size for attention computations [EXPERIMENTAL] bool fused_moe_up_gate; // whether to use fused MoE up/down op [EXPERIMENTAL] // Abort callback |