ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-30 19:31:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fused mul + multi_add op (#858)

Browse Source 
* Adding fused mul+multi_add + CPU implementation

* fused mul+multi_add: CUDA

* fused mul+multi_add: command line argument to disable it

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-10-24 07:40:35 +03:00
committed by GitHub
parent 483cea527d
commit db3ba4999f
15 changed files with 211 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ggml/include/ggml.h
View File

@@ -619,6 +619,7 @@ extern "C" {
GGML_OP_OUT_PROD,
GGML_OP_FUSED_UP_GATE,
GGML_OP_MOE_FUSED_UP_GATE,
GGML_OP_MUL_MULTI_ADD,
GGML_OP_SCALE,
GGML_OP_SET,
@@ -1083,6 +1084,11 @@ extern "C" {
struct ggml_tensor * a,
int n_experts);
GGML_API struct ggml_tensor * ggml_mul_multi_add(
struct ggml_context * ctx,
struct ggml_tensor * a,
struct ggml_tensor * b);
// dst = a
// view(dst, nb1, nb2, nb3, offset) += b
// return dst