Skip to content

Can someone write a step-by-step guide for compiling llama.cpp with openBLAS on Windows? #1153

Answered by SlyEcho
Folko-Ven asked this question in Q&A
Discussion options

You must be logged in to vote

I have done this, I'll try to explain.

First, get w64devkit w64devkit-1.18.0.zip

Then, get OpenBLAS OpenBLAS-0.3.23-x64.zip

Put w64devkit somewhere you like, no need to set up anything else like PATH, there is just one executable that opens a shell, from there you can build llama.cpp with make as usual.

Now take the OpenBLAS release and from there copy lib/libopenblas.a into w64devkit/x86_64-w64-mingw32/lib and from include copy all the .h files to w64devkit/x86_64-w64-mingw32/include

make LLAMA_OPENBLAS=1 should work now.

The files are going to be big because of static linking, you can also copy libopenblas.dll.a but then you have to keep the .dll file around where OS can load it.

You ca…

Replies: 1 comment 10 replies

Comment options

SlyEcho
Apr 25, 2023
Collaborator Sponsor

You must be logged in to vote
10 replies
@SlyEcho
Comment options

SlyEcho Apr 25, 2023
Collaborator Sponsor

@Folko-Ven
Comment options

@Folko-Ven
Comment options

@SlyEcho
Comment options

SlyEcho Apr 25, 2023
Collaborator Sponsor

@Folko-Ven
Comment options

Answer selected by Folko-Ven
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants