CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-16 11:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : implement soft_max_ext

Browse Source
This commit is contained in:
Georgi Gerganov
2023-11-29 12:44:47 +02:00
parent 1f5cd83275
commit e89597c062
5 changed files with 75 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
ggml.h
View File

@@ -1282,6 +1282,14 @@ extern "C" {
struct ggml_context * ctx,
struct ggml_tensor * a);
// fused soft_max(a*scale + mask)
// mask is optional
GGML_API struct ggml_tensor * ggml_soft_max_ext(
struct ggml_context * ctx,
struct ggml_tensor * a,
struct ggml_tensor * mask,
float scale);
GGML_API struct ggml_tensor * ggml_soft_max_back(
struct ggml_context * ctx,
struct ggml_tensor * a,