CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml: add GGML_SET Metal kernel + i32 CPU kernel (ggml/1037)

Browse Source 
* implemented cpu kernel

* add i32 test cases in test-backend-ops

* typedef `ggml_metal_kargs_set`

* implemented `kernel_set`

* memcpy
This commit is contained in:
PAB
2024-12-04 09:19:30 +01:00
committed by Georgi Gerganov
parent c2082d93a8
commit a8cbab201d
5 changed files with 206 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
ggml/src/ggml-metal/ggml-metal-impl.h
View File

@@ -102,6 +102,21 @@ typedef struct {
uint64_t nb3;
} ggml_metal_kargs_cpy;
typedef struct {
int64_t ne10;
int64_t ne11;
int64_t ne12;
uint64_t nb10;
uint64_t nb11;
uint64_t nb12;
uint64_t nb13;
uint64_t nb1;
uint64_t nb2;
uint64_t nb3;
uint64_t offs;
bool inplace;
} ggml_metal_kargs_set;
typedef struct {
int32_t ne00;
int32_t ne01;