root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-28 20:34:37 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
f139d2ea61
llama.cpp/ggml/src/ggml-metal
History
Georgi Gerganov cf32a9b93a
metal : refactor kernel args into structs (#10238) 
* metal : add kernel arg structs (wip)

* metal : fattn args

ggml-ci

* metal : cont + avoid potential int overflow [no ci]

* metal : mul mat struct (wip)

* cont : mul mat vec

* cont : pass by reference

* cont : args is first argument

* cont : use char ptr

* cont : shmem style

* cont : thread counters style

* cont : mul mm id

ggml-ci

* cont : int safety + register optimizations

ggml-ci

* metal : GGML_OP_CONCAT

ggml-ci

* metal : GGML_OP_ADD, GGML_OP_SUB, GGML_OP_MUL, GGML_OP_DIV

* metal : GGML_OP_REPEAT

* metal : GGML_OP_CPY

* metal : GGML_OP_RMS_NORM

* metal : GGML_OP_NORM

* metal : add TODOs for rest of ops

* ggml : add ggml-metal-impl.h

ggml-ci
2024-11-17 11:23:01 +02:00
..
CMakeLists.txt metal : refactor kernel args into structs (#10238) 2024-11-17 11:23:01 +02:00
ggml-metal-impl.h metal : refactor kernel args into structs (#10238) 2024-11-17 11:23:01 +02:00
ggml-metal.m metal : refactor kernel args into structs (#10238) 2024-11-17 11:23:01 +02:00
ggml-metal.metal metal : refactor kernel args into structs (#10238) 2024-11-17 11:23:01 +02:00