From 280345968dabc00d212d43e31145f5c9961a7604 Mon Sep 17 00:00:00 2001 From: slaren Date: Tue, 26 Mar 2024 01:16:01 +0100 Subject: cuda : rename build flag to LLAMA_CUDA (#6299) --- examples/main-cmake-pkg/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'examples/main-cmake-pkg/README.md') diff --git a/examples/main-cmake-pkg/README.md b/examples/main-cmake-pkg/README.md index 6d665f28..f599fbae 100644 --- a/examples/main-cmake-pkg/README.md +++ b/examples/main-cmake-pkg/README.md @@ -8,7 +8,7 @@ Because this example is "outside of the source tree", it is important to first b ### Considerations -When hardware acceleration libraries are used (e.g. CUBlas, Metal, CLBlast, etc.), CMake must be able to locate the associated CMake package. In the example below, when building _main-cmake-pkg_ notice the `CMAKE_PREFIX_PATH` includes the Llama CMake package location _in addition to_ the CLBlast package—which was used when compiling _llama.cpp_. +When hardware acceleration libraries are used (e.g. CUDA, Metal, CLBlast, etc.), CMake must be able to locate the associated CMake package. In the example below, when building _main-cmake-pkg_ notice the `CMAKE_PREFIX_PATH` includes the Llama CMake package location _in addition to_ the CLBlast package—which was used when compiling _llama.cpp_. ### Build llama.cpp and install to C:\LlamaCPP directory -- cgit v1.2.3