tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-20 06:36:48 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: backwards pass for misc. ops, add tests (#11257)

Browse Source 
* CUDA: backwards pass for misc. ops, add tests

* remove restrict from pointers
This commit is contained in:
Johannes Gäßler
2025-01-16 16:43:38 +01:00
committed by GitHub
parent 681149ced2
commit 9c8dcefe17
18 changed files with 930 additions and 332 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
ggml/include/ggml.h
View File

@@ -1384,16 +1384,20 @@ extern "C" {
float scale,
float max_bias);
GGML_API struct ggml_tensor * ggml_soft_max_back(
GGML_API struct ggml_tensor * ggml_soft_max_ext_back(
struct ggml_context * ctx,
struct ggml_tensor * a,
struct ggml_tensor * b);
struct ggml_tensor * b,
float scale,
float max_bias);
// in-place, returns view(a)
GGML_API struct ggml_tensor * ggml_soft_max_back_inplace(
GGML_API struct ggml_tensor * ggml_soft_max_ext_back_inplace(
struct ggml_context * ctx,
struct ggml_tensor * a,
struct ggml_tensor * b);
struct ggml_tensor * b,
float scale,
float max_bias);
// rotary position embedding
// if (mode & 1) - skip n_past elements (NOT SUPPORTED)