feature: allow all BLA_VENDOR to be assigned in cmake arguments. align with whisper.cpp pr 927

Author: zenixls2

BLIS.md

@@ -39,7 +39,7 @@ CMake:
 ```bash
 mkdir build
 cd build
-cmake -DLLAMA_BLIS=ON ..
+cmake -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=FLAME ..
 make -j
 ```
 

CMakeLists.txt

@@ -1,4 +1,4 @@
-cmake_minimum_required(VERSION 3.12) # Don't bump this version for no reason
+cmake_minimum_required(VERSION 3.25) # Don't bump this version for no reason
 project("llama.cpp" C CXX)
 
 set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
@@ -65,8 +65,8 @@ endif()
 
 # 3rd party libs
 option(LLAMA_ACCELERATE             "llama: enable Accelerate framework"                    ON)
-option(LLAMA_OPENBLAS               "llama: use OpenBLAS"                                   OFF)
-option(LLAMA_BLIS                   "llama: use blis"                                       OFF)
+option(LLAMA_BLAS                   "llama: use BLAS"                                       OFF)
+option(LLAMA_BLAS_VENDOR            "llama: BLA_VENDOR from https://cmake.org/cmake/help/latest/module/FindBLAS.html#blas-lapack-vendors" Generic)
 option(LLAMA_CUBLAS                 "llama: use cuBLAS"                                     OFF)
 option(LLAMA_CLBLAST                "llama: use CLBlast"                                    OFF)
 
@@ -146,57 +146,26 @@ if (APPLE AND LLAMA_ACCELERATE)
     endif()
 endif()
 
-if (LLAMA_OPENBLAS)
+if (LLAMA_BLAS)
     if (LLAMA_STATIC)
         set(BLA_STATIC ON)
     endif()
-
-    set(BLA_VENDOR OpenBLAS)
+    set(BLA_SIZEOF_INTEGRER 8)
+    set(BLA_VENDOR ${LLAMA_BLAS_VENDOR})
     find_package(BLAS)
     if (BLAS_FOUND)
-        message(STATUS "OpenBLAS found")
+        message(STATUS "BLAS found, Libraries: ${BLAS_LIBRARIES}")
 
         add_compile_definitions(GGML_USE_OPENBLAS)
-        add_link_options(${BLAS_LIBRARIES})
-        set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} openblas)
-
-        # find header file
-        set(OPENBLAS_INCLUDE_SEARCH_PATHS
-            /usr/include
-            /usr/include/openblas
-            /usr/include/openblas-base
-            /usr/local/include
-            /usr/local/include/openblas
-            /usr/local/include/openblas-base
-            /opt/OpenBLAS/include
-            $ENV{OpenBLAS_HOME}
-            $ENV{OpenBLAS_HOME}/include
-            )
-        find_path(OPENBLAS_INC NAMES cblas.h PATHS ${OPENBLAS_INCLUDE_SEARCH_PATHS})
-        add_compile_options(-I${OPENBLAS_INC})
+        set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} ${BLAS_LIBRARIES})
+
+        message("${BLAS_LIBRARIES}")
+        include_directories(${BLAS_INCLUDE_DIRS})
     else()
-        message(WARNING "OpenBLAS not found")
+        message(WARNING "BLAS not found, please refer to https://cmake.org/cmake/help/latest/module/FindBLAS.html#blas-lapack-vendors to set correct LLAMA_BLAS_VENDOR")
     endif()
 endif()
 
-if (LLAMA_BLIS)
-    add_compile_definitions(GGML_USE_BLIS)
-    # we don't directly call BLIS apis, use cblas wrapper instead
-    add_compile_definitions(GGML_USE_OPENBLAS)
-    set(BLIS_INCLUDE_SEARCH_PATHS
-        /usr/include
-        /usr/include/blis
-        /usr/local/include
-        /usr/local/include/blis
-        $ENV{BLIS_HOME}
-        $ENV{BLIS_HOME}/include
-        )
-    find_path(BLIS_INC NAMES blis.h PATHS ${BLIS_INCLUDE_SEARCH_PATHS})
-    add_compile_definitions(BLIS_ENABLE_CBLAS)
-    add_link_options(-lblis)
-    add_compile_options(-I${BLIS_INC})
-endif()
-
 if (LLAMA_CUBLAS)
     cmake_minimum_required(VERSION 3.17)
 

README.md

@@ -55,9 +55,8 @@ The main goal of `llama.cpp` is to run the LLaMA model using 4-bit integer quant
 - Mixed F16 / F32 precision
 - 4-bit, 5-bit and 8-bit integer quantization support
 - Runs on the CPU
-- OpenBLAS support
+- Supports OpenBLAS/Apple BLAS/ARM Performance Lib/ATLAS/BLIS/Intel MKL/NVHPC/ACML/SCSL/SGIMATH and [more](https://cmake.org/cmake/help/latest/module/FindBLAS.html#blas-lapack-vendors) in BLAS
 - cuBLAS and CLBlast support
-- BLIS support (cblas wrapper)
 
 The original implementation of `llama.cpp` was [hacked in an evening](https://github.com/ggerganov/llama.cpp/issues/33#issuecomment-1465108022).
 Since then, the project has improved significantly thanks to many contributions. This project is for educational purposes and serves
@@ -273,14 +272,25 @@ Building the program with BLAS support may lead to some performance improvements
       ```bash
       mkdir build
       cd build
-      cmake .. -DLLAMA_OPENBLAS=ON
+      cmake .. -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
       cmake --build . --config Release
       ```
 
 - BLIS
 
   Check [BLIS.md](BLIS.md) for more information.
 
+- Intel MKL
+
+  By default, `LLAMA_BLAS_VENDOR` is set to `Generic`, so if you already sourced intel environment script and assign `-DLLAMA_BLAS=ON` in cmake, the mkl version of Blas will automatically been selected. You may also specify it by:
+
+  ```bash
+  mkdir build
+  cd build
+  cmake .. -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=Intel10_64lp -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
+  cmake --build . -config Release
+  ```
+
 - cuBLAS
 
   This provides BLAS acceleration using the CUDA cores of your Nvidia GPU. Make sure to have the CUDA toolkit installed. You can download it from your Linux distro's package manager or from here: [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads).