Shang Chieh Tseng d8ea75a3e2 Fix test-runner to inherit LD_LIBRARY_PATH for CUDA backend loading ...

The test-runner was starting the ollama server subprocess without inheriting
environment variables, causing the GGML CUDA backend to fail loading even
though LD_LIBRARY_PATH was set in the GitHub Actions workflow.

Changes:
- Added s.cmd.Env = os.Environ() to inherit all environment variables
- This ensures LD_LIBRARY_PATH is passed to the ollama server subprocess
- Fixes GPU offloading failure where layers were not being loaded to GPU

Root cause analysis from logs:
- GPUs were detected: Tesla K80 with 11.1 GiB available
- Server scheduled 35 layers for GPU offload
- But actual offload was 0/35 layers (all stayed on CPU)
- Runner subprocess couldn't find CUDA libraries without LD_LIBRARY_PATH

This fix ensures the runner subprocess can dynamically load libggml-cuda.so
by inheriting the CUDA library paths from the parent process.

2025-10-30 14:08:24 +08:00

4.0 KiB

Raw Blame History

View Raw