diff options
Diffstat (limited to 'ggml/include/ggml.h')
| -rw-r--r-- | ggml/include/ggml.h | 23 |
1 files changed, 22 insertions, 1 deletions
diff --git a/ggml/include/ggml.h b/ggml/include/ggml.h index 17d3cb1a..1a4a516c 100644 --- a/ggml/include/ggml.h +++ b/ggml/include/ggml.h @@ -515,6 +515,7 @@ extern "C" { GGML_OP_ARGSORT, GGML_OP_LEAKY_RELU, GGML_OP_SOFTCAP, + GGML_OP_SOFT_CAP_MAX, GGML_OP_FLASH_ATTN_EXT, GGML_OP_FLASH_ATTN_BACK, @@ -1237,6 +1238,25 @@ extern "C" { float s_before, float s_after); + GGML_API struct ggml_tensor * ggml_softcap_max( + struct ggml_context * ctx, + struct ggml_tensor * a, + struct ggml_tensor * mask, + float scale, + float max_bias, + float s_before, + float s_after); + + // in-place, returns view(a) + GGML_API struct ggml_tensor * ggml_softcap_max_inplace( + struct ggml_context * ctx, + struct ggml_tensor * a, + struct ggml_tensor * mask, + float scale, + float max_bias, + float s_before, + float s_after); + // b -> view(a,offset,nb1,nb2,3), return modified a GGML_API struct ggml_tensor * ggml_set( struct ggml_context * ctx, @@ -1791,7 +1811,8 @@ extern "C" { struct ggml_tensor * v, struct ggml_tensor * mask, float scale, - float max_bias); + float max_bias, + float softcap); GGML_API void ggml_flash_attn_ext_set_prec( struct ggml_tensor * a, |