llama.cpp icon indicating copy to clipboard operation
llama.cpp copied to clipboard

Published 20 hours ago • verified publisher icon ggml-org

cuBLAS - windows - static not compiling

Open cmp-nct opened this issue 1 year ago • 1 comments

When static linking is selected the CUDA::cublas_static target is not found. Dynamic binary compilation works.

cmp-nct avatar Apr 20 '23 21:04 cmp-nct

I don't know why that may be, these targets are listed in the documentation.

slaren avatar Apr 20 '23 23:04 slaren

cublas has no static targets on windows.

Green-Sky avatar May 02 '23 00:05 Green-Sky

What does software that depend on it (or other libraries in the CUDA toolkit) do, distribute the dll files along with the software?

slaren avatar May 02 '23 00:05 slaren

https://github.com/ggerganov/llama.cpp/pull/1271 python ships the dynamic libraries. one of the reason each virtual env is so bloated.

Green-Sky avatar May 02 '23 00:05 Green-Sky

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

github-actions[bot] avatar Apr 09 '24 01:04 github-actions[bot]