Bug: MinGW build fails to load models with "error loading model: PrefetchVirtualMemory unavailable"

[jeberger]

What happened?

llama-cli and llama-bench rev. 9379d3c built with MinGW fails to load models:

llama_model_load: error loading model: PrefetchVirtualMemory unavailable
llama_load_model_from_file: failed to load model

Name and Version

./bin/llama-cli --version
version: 3664 (9379d3c)
built with for x86_64-w64-mingw32

What operating system are you seeing the problem on?

Windows

Relevant log output

llama_model_load: error loading model: PrefetchVirtualMemory unavailable
llama_load_model_from_file: failed to load model

[jeberger]

I believe the issue was introduced when the source was reorganized into folders. I'm able to work around it by adding the following to the top level CMakeLists.txt:

if (MINGW)
    add_compile_definitions(_WIN32_WINNT=0x602)
endif()

so I believe the equivalent code is missing from some CMakeLists.txt files in subfolders (I tried adding it to examples/llama-bench/CMakeLists.txt but that wasn't enough to fix the issue).

[homenkovo]

I had a similar problem. I just replaced #define _WIN32_WINNT 0x0601 with #define _WIN32_WINNT 0x0A00 in the <_mingw.h> file and it worked.

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.

[theSoberSobber]

Why was this closed, I suffered the same error as this in current latest commit and fixed it using @homenkovo's solution

[watkyns]

having same issue with b4628 and homenkovo's solution can fix it

[0dminnimda]

No need to modify no files, a simple command line argument is enough:

-DCMAKE_CXX_FLAGS=-D_WIN32_WINNT=0x602

[robbyvids]

not worked on win 11 for me, using python script. Memory more than enough, it happen when loading to gpu or cpu.

llama_model_load: error loading model: PrefetchVirtualMemory unavailable

[vishal-ahirwar]

No need to modify no files, a simple command line argument is enough:

-DCMAKE_CXX_FLAGS=-D_WIN32_WINNT=0x602

thanks it worked for me