diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-07-27 07:55:01 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-07-27 07:55:01 +0200 |
| commit | 154e0d75fccf1784fe9ff6fd76a630b66563da3d (patch) | |
| tree | 81ce6dbb5b1900c1aa78a879f0593c694cab9d27 /examples/main-cmake-pkg | |
| parent | 0684c3e9c70d49323b4fc517128cbe222cab7f96 (diff) | |
Merge mainline llama.cpp (#3)
* Merging mainline - WIP
* Merging mainline - WIP
AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.
* Merging mainline - fix Metal
* Remove check
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/main-cmake-pkg')
| -rw-r--r-- | examples/main-cmake-pkg/.gitignore | 1 | ||||
| -rw-r--r-- | examples/main-cmake-pkg/CMakeLists.txt | 1 |
2 files changed, 0 insertions, 2 deletions
diff --git a/examples/main-cmake-pkg/.gitignore b/examples/main-cmake-pkg/.gitignore index e32c11c7..67c01d64 100644 --- a/examples/main-cmake-pkg/.gitignore +++ b/examples/main-cmake-pkg/.gitignore @@ -48,4 +48,3 @@ build*/ out/ tmp/ - diff --git a/examples/main-cmake-pkg/CMakeLists.txt b/examples/main-cmake-pkg/CMakeLists.txt index a97ded36..3b38db29 100644 --- a/examples/main-cmake-pkg/CMakeLists.txt +++ b/examples/main-cmake-pkg/CMakeLists.txt @@ -30,4 +30,3 @@ target_include_directories(${TARGET} PRIVATE ${_common_path}) install(TARGETS ${TARGET} RUNTIME) target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT}) target_compile_features(${TARGET} PRIVATE cxx_std_11) - |