Shang Chieh Tseng 6dbd8ed44e Redesign Docker build system to single-stage architecture for reliable model loading ...

Replaced complex two-stage build (builder → runtime) with single-stage
Dockerfile that builds and runs Ollama in one image. This fixes model
loading issues caused by missing CUDA libraries and LD_LIBRARY_PATH
mismatches in the previous multi-stage design.

Changes:
- Add docker/Dockerfile: Single-stage build with GCC 10, CMake 4, Go 1.25.3, CUDA 11.4
- Clone source from https://github.com/dogkeeper886/ollama37
- Compile Ollama with "CUDA 11" preset for Tesla K80 (compute capability 3.7)
- Keep complete CUDA toolkit and all libraries in final image (~20GB)
- Update docker-compose.yml: Simplified config, use ollama37:latest image
- Update docker/README.md: New build instructions and architecture docs

Trade-off: Larger image size (~20GB vs ~3GB) for guaranteed compatibility
and reliable GPU backend operation. All libraries remain accessible with
correct paths, ensuring models load properly on Tesla K80.

Tested: Successfully runs gemma3:1b on Tesla K80

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

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

2025-11-10 09:19:22 +08:00

711 B

Raw Blame History

View Raw