Fix GitHub Actions workflows to upload build libraries and remove LD_LIBRARY_PATH

Changes:
- Update tesla-k80-ci.yml to upload build/lib/ollama/ containing CUDA backend
- Remove all LD_LIBRARY_PATH environment variables (no longer needed with RPATH)
- Test workflows now receive libggml-cuda.so enabling GPU offload

This fixes the issue where test workflows couldn't offload to GPU because the
CUDA backend library wasn't included in the artifact.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

.github/workflows/tesla-k80-ci.yml

@@ -28,31 +28,26 @@ jobs:
           CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake -B build
         env:
           CMAKE_BUILD_TYPE: Release
-          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 C++/CUDA components
         run: |
           CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ cmake --build build -j$(nproc)
         timeout-minutes: 30
-        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 Go binary
         run: |
           go build -v -o ollama .
-        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: Verify binary was created
         run: |
           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: Upload ollama binary as artifact
+      - name: Upload ollama binary and libraries as artifact
         uses: actions/upload-artifact@v4
         with:
           name: ollama-binary
-          path: ollama
+          path: |
+            ollama
+            build/lib/ollama/
           retention-days: 7

.github/workflows/tesla-k80-multi-gpu-tests.yml

@@ -30,8 +30,6 @@ 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: Verify multi-GPU setup
         run: |
@@ -51,21 +49,15 @@ 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 multi-GPU test configuration
         run: |
           ./test-runner validate --config test/config/models.yaml --profile multi-gpu
-        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 multi-GPU tests
         run: |
           ./test-runner run --profile multi-gpu --config test/config/models.yaml --output test-report-multi-gpu --verbose
         timeout-minutes: 60
-        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 multi-GPU test results
         run: |

.github/workflows/tesla-k80-single-gpu-tests.yml

@@ -27,8 +27,6 @@ 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: |
@@ -38,21 +36,15 @@ 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: |
@@ -79,8 +71,6 @@ 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()