CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-09 10:17:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : change ggml_scale to take a float instead of tensor (#4573)

Browse Source 
* ggml : change ggml_scale to take a float instead of tensor

* ggml : fix CPU implementation

* tests : fix test-grad0

ggml-ci
This commit is contained in:
Georgi Gerganov
2023-12-21 23:20:49 +02:00
committed by GitHub
parent 769a7bc85e
commit afefa319f1
12 changed files with 82 additions and 205 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml.h
View File

@@ -1094,13 +1094,13 @@ extern "C" {
GGML_API struct ggml_tensor * ggml_scale(
struct ggml_context * ctx,
struct ggml_tensor * a,
struct ggml_tensor * b);
float s);
// in-place, returns view(a)
GGML_API struct ggml_tensor * ggml_scale_inplace(
struct ggml_context * ctx,
struct ggml_tensor * a,
struct ggml_tensor * b);
float s);
// b -> view(a,offset,nb1,nb2,3), return modified a
GGML_API struct ggml_tensor * ggml_set(