thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

metal : refactor + optimize v2 (#15995)

Browse source 
* metal : improve naming

* metal : refactor device

ggml-ci

* cont : props

ggml-ci

* metal : apply ggml_mem_ranges_t

ggml-ci

* metal : remove GGML_METAL_USE_BF16

ggml-ci

* metal : refactor device buffer

ggml-ci

* cont : fix naming

* metal : sync before destroying the backend

ggml-ci

* metal : refactor context

ggml-ci

* metal : migrate ggml-metal.m to ggml-metal.cpp

ggml-ci

* metal : adjust ops API

ggml-ci

* metal : use C++ to store piplienes

ggml-ci

* metal : migrate ops to separate functions

ggml-ci

* metal : add ggml_metal_library_t

ggml-ci

* metal : improve naming

ggml-ci

* metal : cleanp

ggml-ci

* metal : add support for GGML_OP_LOG

ggml-ci

* metal : fix error handling

ggml-ci
This commit is contained in:
Georgi Gerganov 2025-09-17 20:38:12 +03:00 • committed by GitHub
parent a7a98e0fff
commit 0320ac5264
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 7873 additions and 7184 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ci/run.sh
View file

@ -45,7 +45,7 @@ SRC=`pwd`
CMAKE_EXTRA="-DLLAMA_FATAL_WARNINGS=ON -DLLAMA_CURL=ON"
if [ ! -z ${GG_BUILD_METAL} ]; then
CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_METAL=ON -DGGML_METAL_USE_BF16=ON"
CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_METAL=ON"
fi
if [ ! -z ${GG_BUILD_CUDA} ]; then