Skip to content

fix CI errors in when compiling in linux and docker #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
khanhnd61-vr merged 1 commit into from
Aug 13, 2026
Merged

fix CI errors in when compiling in linux and docker #19

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/release.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ jobs:
wget -q https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/x86_64/cuda-keyring_1.1-1_all.deb
sudo dpkg -i cuda-keyring_1.1-1_all.deb
sudo apt-get update -qq
sudo apt-get install -y -qq --no-install-recommends cuda-toolkit-12-6
sudo apt-get install -y -qq --no-install-recommends cuda-toolkit-12-8
echo "/usr/local/cuda/bin" >> "$GITHUB_PATH"

- name: build
Expand Down
12 changes: 7 additions & 5 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,16 +30,18 @@ set(LLAMA_BUILD_TOOLS ON CACHE BOOL "" FORCE)
set(LLAMA_BUILD_SERVER OFF CACHE BOOL "" FORCE)
set(LLAMA_BUILD_EXAMPLES OFF CACHE BOOL "" FORCE)
set(LLAMA_BUILD_TESTS OFF CACHE BOOL "" FORCE)
# PATCH_COMMAND adds the CUDA extension hook; see scripts/patch_ggml_cuda_ext_hook.py.
find_package(Python3 COMPONENTS Interpreter REQUIRED)
set(_vla_llama_patch "")
if(GGML_CUDA)
find_package(Python3 COMPONENTS Interpreter REQUIRED)
set(_vla_llama_patch PATCH_COMMAND ${Python3_EXECUTABLE}
${CMAKE_CURRENT_SOURCE_DIR}/scripts/patch_ggml_cuda_ext_hook.py <SOURCE_DIR>)
endif()
include(FetchContent)
FetchContent_Declare(llama
GIT_REPOSITORY https://github.com/ggml-org/llama.cpp
GIT_TAG b10331
GIT_SHALLOW TRUE
PATCH_COMMAND ${Python3_EXECUTABLE}
${CMAKE_CURRENT_SOURCE_DIR}/scripts/patch_ggml_cuda_ext_hook.py
<SOURCE_DIR>
${_vla_llama_patch}
)
FetchContent_MakeAvailable(llama)

Expand Down
2 changes: 1 addition & 1 deletion Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ ARG BASE_IMAGE=nvidia/cuda:12.9.1-devel-ubuntu24.04
FROM ${BASE_IMAGE}

RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
build-essential cmake git ca-certificates pkg-config \
build-essential cmake git ca-certificates pkg-config python3 \
libzmq3-dev cppzmq-dev libprotobuf-dev protobuf-compiler \
&& rm -rf /var/lib/apt/lists/*

Expand Down
Loading