CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-12 10:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : small-batch mat-mul kernels (#10581)

Browse Source 
* metal : small-batch mat-mul kernels

ggml-ci

* metal : add rest of types

ggml-ci

* metal : final adjustments

ggml-ci

* metal : add comments

ggml-ci
This commit is contained in:
Georgi Gerganov
2024-12-03 11:52:33 +02:00
committed by GitHub
parent 515d4e5372
commit 0115df2f65
4 changed files with 709 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
ggml/src/ggml-metal/ggml-metal-impl.h
View File

@@ -192,6 +192,30 @@ typedef struct {
int16_t r3;
} ggml_metal_kargs_mul_mv;
typedef struct {
int32_t ne00;
int32_t ne01;
int32_t ne02;
uint64_t nb00;
uint64_t nb01;
uint64_t nb02;
uint64_t nb03;
int32_t ne10;
int32_t ne11;
int32_t ne12;
uint64_t nb10;
uint64_t nb11;
uint64_t nb12;
uint64_t nb13;
int32_t ne0;
int32_t ne1;
int16_t r2;
int16_t r3;
int16_t nsg;
int16_t nxpsg;
int16_t r1ptg;
} ggml_metal_kargs_mul_mv_ext;
typedef struct {
int32_t nei0;
int32_t nei1;