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>

1 files changed, 39 insertions, 30 deletions

diff --git a/scripts/sync-ggml.sh b/scripts/sync-ggml.sh
index 4843f8a4..402446ef 100755
--- a/scripts/sync-ggml.sh
+++ b/scripts/sync-ggml.sh
@@ -1,34 +1,43 @@
 #!/bin/bash
 
-cp -rpv ../ggml/src/ggml.c                  ./ggml.c
-cp -rpv ../ggml/src/ggml-alloc.c            ./ggml-alloc.c
-cp -rpv ../ggml/src/ggml-backend-impl.h     ./ggml-backend-impl.h
-cp -rpv ../ggml/src/ggml-backend.c          ./ggml-backend.c
-cp -rpv ../ggml/src/ggml-common.h           ./ggml-common.h
-cp -rpv ../ggml/src/ggml-cuda/*             ./ggml-cuda/
-cp -rpv ../ggml/src/ggml-cuda.cu            ./ggml-cuda.cu
-cp -rpv ../ggml/src/ggml-cuda.h             ./ggml-cuda.h
-cp -rpv ../ggml/src/ggml-impl.h             ./ggml-impl.h
-cp -rpv ../ggml/src/ggml-kompute.cpp        ./ggml-kompute.cpp
-cp -rpv ../ggml/src/ggml-kompute.h          ./ggml-kompute.h
-cp -rpv ../ggml/src/ggml-metal.h            ./ggml-metal.h
-cp -rpv ../ggml/src/ggml-metal.m            ./ggml-metal.m
-cp -rpv ../ggml/src/ggml-metal.metal        ./ggml-metal.metal
-cp -rpv ../ggml/src/ggml-quants.c           ./ggml-quants.c
-cp -rpv ../ggml/src/ggml-quants.h           ./ggml-quants.h
-cp -rpv ../ggml/src/ggml-rpc.cpp            ./ggml-rpc.cpp
-cp -rpv ../ggml/src/ggml-rpc.h              ./ggml-rpc.h
-cp -rpv ../ggml/src/ggml-sycl.cpp           ./ggml-sycl.cpp
-cp -rpv ../ggml/src/ggml-sycl.h             ./ggml-sycl.h
-cp -rpv ../ggml/src/ggml-vulkan.cpp         ./ggml-vulkan.cpp
-cp -rpv ../ggml/src/ggml-vulkan.h           ./ggml-vulkan.h
-cp -rpv ../ggml/include/ggml/ggml.h         ./ggml.h
-cp -rpv ../ggml/include/ggml/ggml-alloc.h   ./ggml-alloc.h
-cp -rpv ../ggml/include/ggml/ggml-backend.h ./ggml-backend.h
+cp -rpv ../ggml/CMakeLists.txt       ./ggml/CMakeLists.txt
+cp -rpv ../ggml/src/CMakeLists.txt   ./ggml/src/CMakeLists.txt
+cp -rpv ../ggml/cmake/FindSIMD.cmake ./ggml/cmake/FindSIMD.cmake
 
-cp -rpv ../ggml/tests/test-opt.cpp         ./tests/test-opt.cpp
-cp -rpv ../ggml/tests/test-grad0.cpp       ./tests/test-grad0.cpp
-cp -rpv ../ggml/tests/test-backend-ops.cpp ./tests/test-backend-ops.cpp
+cp -rpv ../ggml/src/ggml.c              ./ggml/src/ggml.c
+cp -rpv ../ggml/src/ggml-alloc.c        ./ggml/src/ggml-alloc.c
+cp -rpv ../ggml/src/ggml-backend-impl.h ./ggml/src/ggml-backend-impl.h
+cp -rpv ../ggml/src/ggml-backend.c      ./ggml/src/ggml-backend.c
+cp -rpv ../ggml/src/ggml-common.h       ./ggml/src/ggml-common.h
+cp -rpv ../ggml/src/ggml-cuda/*         ./ggml/src/ggml-cuda/
+cp -rpv ../ggml/src/ggml-cuda.cu        ./ggml/src/ggml-cuda.cu
+cp -rpv ../ggml/src/ggml-impl.h         ./ggml/src/ggml-impl.h
+cp -rpv ../ggml/src/ggml-kompute.cpp    ./ggml/src/ggml-kompute.cpp
+cp -rpv ../ggml/src/ggml-metal.m        ./ggml/src/ggml-metal.m
+cp -rpv ../ggml/src/ggml-metal.metal    ./ggml/src/ggml-metal.metal
+cp -rpv ../ggml/src/ggml-quants.c       ./ggml/src/ggml-quants.c
+cp -rpv ../ggml/src/ggml-quants.h       ./ggml/src/ggml-quants.h
+cp -rpv ../ggml/src/ggml-rpc.cpp        ./ggml/src/ggml-rpc.cpp
+cp -rpv ../ggml/src/ggml-sycl/*         ./ggml/src/ggml-sycl/
+cp -rpv ../ggml/src/ggml-sycl.cpp       ./ggml/src/ggml-sycl.cpp
+cp -rpv ../ggml/src/ggml-vulkan.cpp     ./ggml/src/ggml-vulkan.cpp
 
-cp -rpv ../LICENSE                         ./LICENSE
-cp -rpv ../ggml/scripts/gen-authors.sh     ./scripts/gen-authors.sh
+cp -rpv ../ggml/include/ggml.h         ./ggml/include/ggml.h
+cp -rpv ../ggml/include/ggml-alloc.h   ./ggml/include/ggml-alloc.h
+cp -rpv ../ggml/include/ggml-backend.h ./ggml/include/ggml-backend.h
+cp -rpv ../ggml/include/ggml-blas.h    ./ggml/include/ggml-blas.h
+cp -rpv ../ggml/include/ggml-cuda.h    ./ggml/include/ggml-cuda.h
+cp -rpv ../ggml/include/ggml-kompute.h ./ggml/include/ggml-kompute.h
+cp -rpv ../ggml/include/ggml-metal.h   ./ggml/include/ggml-metal.h
+cp -rpv ../ggml/include/ggml-rpc.h     ./ggml/include/ggml-rpc.h
+cp -rpv ../ggml/include/ggml-sycl.h    ./ggml/include/ggml-sycl.h
+cp -rpv ../ggml/include/ggml-vulkan.h  ./ggml/include/ggml-vulkan.h
+
+cp -rpv ../ggml/tests/test-opt.cpp           ./tests/test-opt.cpp
+cp -rpv ../ggml/tests/test-grad0.cpp         ./tests/test-grad0.cpp
+cp -rpv ../ggml/tests/test-quantize-fns.cpp  ./tests/test-quantize-fns.cpp
+cp -rpv ../ggml/tests/test-quantize-perf.cpp ./tests/test-quantize-perf.cpp
+cp -rpv ../ggml/tests/test-backend-ops.cpp   ./tests/test-backend-ops.cpp
+
+cp -rpv ../LICENSE                     ./LICENSE
+cp -rpv ../ggml/scripts/gen-authors.sh ./scripts/gen-authors.sh