CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-12 10:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed painfully slow single process builds. (#7326)

Browse Source 
* Fixed painfully slow single process builds.

* Added nproc for systems that don't default to nproc
This commit is contained in:
JohnnyB
2024-05-30 21:32:38 +01:00
committed by GitHub
parent 5921b8f089
commit 9022c33646
9 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.devops/main-cuda.Dockerfile
View File

@@ -23,7 +23,7 @@ ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
# Enable CUDA
ENV LLAMA_CUDA=1
RUN make
RUN make -j$(nproc)
FROM ${BASE_CUDA_RUN_CONTAINER} as runtime