update

2026-07-14 12:34:44 -05:00
parent 6c3786f200
commit 96eb7ad9b9
2 changed files with 71 additions and 21 deletions
--- a/bayarea-ai-server/Dockerfile.cuda
+++ b/bayarea-ai-server/Dockerfile.cuda
@@ -19,6 +19,7 @@ RUN git clone --depth 1 https://github.com/ggml-org/llama.cpp /src
 RUN cmake /src -B /build \
      -DGGML_CUDA=ON \
      -DCMAKE_CUDA_ARCHITECTURES=120 \
+      -DGGML_CUDA_FORCE_CUBLAS=OFF \
      -DBUILD_SHARED_LIBS=OFF \
      -DLLAMA_CURL=ON \
    && cmake --build /build --config Release -j --target llama-server