diff options
author | Jose Maldonado <63384398+yukiteruamano@users.noreply.github.com> | 2023-07-23 07:52:08 -0400 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-07-23 14:52:08 +0300 |
commit | 91171b8072f6f0c8ae3a61e23451acb538bb9ece (patch) | |
tree | 361b3bb789a174e3487ec6ac06855c1371aae569 | |
parent | 355c80f49e32b0b15c0a457f3bad380e57f5b9ac (diff) |
make : fix CLBLAST compile support in FreeBSD (#2331)
* Fix Makefile for CLBLAST compile support and instructions for compile llama.cpp FreeBSD
* More general use-case for CLBLAST support (Linux and FreeBSD)
-rw-r--r-- | Makefile | 8 | ||||
-rw-r--r-- | README.md | 17 |
2 files changed, 22 insertions, 3 deletions
@@ -235,13 +235,15 @@ ggml-cuda.o: ggml-cuda.cu ggml-cuda.h endif # LLAMA_CUBLAS ifdef LLAMA_CLBLAST - CFLAGS += -DGGML_USE_CLBLAST - CXXFLAGS += -DGGML_USE_CLBLAST + + CFLAGS += -DGGML_USE_CLBLAST $(shell pkg-config --cflags clblast OpenCL) + CXXFLAGS += -DGGML_USE_CLBLAST $(shell pkg-config --cflags clblast OpenCL) + # Mac provides OpenCL as a framework ifeq ($(UNAME_S),Darwin) LDFLAGS += -lclblast -framework OpenCL else - LDFLAGS += -lclblast -lOpenCL + LDFLAGS += $(shell pkg-config --libs clblast OpenCL) endif OBJS += ggml-opencl.o @@ -242,6 +242,23 @@ In order to build llama.cpp you have three different options. zig build -Doptimize=ReleaseFast ``` +- Using `gmake` (FreeBSD): + + 1. Install and activate [DRM in FreeBSD](https://wiki.freebsd.org/Graphics) + 2. Add your user to **video** group + 3. Install compilation dependencies. + + ```bash + sudo pkg install gmake automake autoconf pkgconf llvm15 clinfo clover \ + opencl clblast openblas + + gmake CC=/usr/local/bin/clang15 CXX=/usr/local/bin/clang++15 -j4 + ``` + + **Notes:** With this packages you can build llama.cpp with OPENBLAS and + CLBLAST support for use OpenCL GPU acceleration in FreeBSD. Please read + the instructions for use and activate this options in this document below. + ### Metal Build Using Metal allows the computation to be executed on the GPU for Apple devices: |