matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-11 08:17:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add LD_LIBRARY_PATH to GitHub Actions workflows for CUDA library discovery

Browse Source 
Set LD_LIBRARY_PATH in all workflow steps to ensure CUDA 11.4 libraries
are found during both compile time and runtime. This fixes the issue where
the GGML CUDA backend (libggml-cuda.so) fails to load when running
'ollama serve'.

Library paths added:
- /usr/local/cuda-11.4/lib64
- /usr/local/cuda-11.4/targets/x86_64-linux/lib
- /usr/lib64
- /usr/local/lib64

Updated workflows:
- tesla-k80-ci.yml: CMake configure, C++/CUDA build, Go build, binary verify
- tesla-k80-single-gpu-tests.yml: All test execution steps
- tesla-k80-multi-gpu-tests.yml: All test execution steps
This commit is contained in:
Shang Chieh Tseng
2025-10-30 13:28:44 +08:00
parent bc8992d014
commit c022e79e77
3 changed files with 25 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.github/workflows/tesla-k80-single-gpu-tests.yml vendored
View File

@@ -27,6 +27,8 @@ jobs:
chmod +x ollama
ls -lh ollama
./ollama --version
env:
LD_LIBRARY_PATH: /usr/local/cuda-11.4/lib64:/usr/local/cuda-11.4/targets/x86_64-linux/lib:/usr/lib64:/usr/local/lib64
- name: Build test-runner
run: |
@@ -36,15 +38,21 @@ jobs:
go build -o ../../test-runner .
cd ../..
ls -lh test-runner
env:
LD_LIBRARY_PATH: /usr/local/cuda-11.4/lib64:/usr/local/cuda-11.4/targets/x86_64-linux/lib:/usr/lib64:/usr/local/lib64
- name: Validate test configuration
run: |
./test-runner validate --config test/config/quick.yaml
env:
LD_LIBRARY_PATH: /usr/local/cuda-11.4/lib64:/usr/local/cuda-11.4/targets/x86_64-linux/lib:/usr/lib64:/usr/local/lib64
- name: Run quick tests
run: |
./test-runner run --profile quick --config test/config/quick.yaml --output test-report-quick --verbose
timeout-minutes: 10
env:
LD_LIBRARY_PATH: /usr/local/cuda-11.4/lib64:/usr/local/cuda-11.4/targets/x86_64-linux/lib:/usr/lib64:/usr/local/lib64
- name: Check quick test results
run: |
@@ -71,6 +79,8 @@ jobs:
run: |
./test-runner run --profile full --config test/config/models.yaml --output test-report-full --verbose
timeout-minutes: 45
env:
LD_LIBRARY_PATH: /usr/local/cuda-11.4/lib64:/usr/local/cuda-11.4/targets/x86_64-linux/lib:/usr/lib64:/usr/local/lib64
- name: Check full test results
if: success()