oea-framework-paper/Dockerfile.cuda at main · BitConcepts/oea-framework-paper · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
# OEA Framework Paper — NVIDIA CUDA Reproducibility Container (REQ-OEA-020)
# Requires: NVIDIA GPU + nvidia-container-toolkit installed on the host.
# Verified on: RTX 4070 SUPER, CUDA 12.1, Windows 11 / Ubuntu 22.04
#
# Hardware test status:
#   This image (NVIDIA CUDA 12.1): verified by maintainer
#   AMD ROCm / Intel XPU:          community-tested only — no Dockerfile provided
#   Report hardware issues:        https://github.com/BitConcepts/oea-framework-paper/issues
#
# Build:
#   docker build -f Dockerfile.cuda -t oea-framework-cuda .
#
# Run real LLM experiment (GPU, full config, ~20-30 min per model):
#   docker run --rm --gpus all \
#     -v $(pwd)/results:/app/results \
#     oea-framework-cuda \
#     python experiments/real_lm_experiment.py --model distilgpt2
#
# Run all 4 validated models:
#   for model in distilgpt2 gpt2 EleutherAI/gpt-neo-125M Qwen/Qwen2.5-1.5B; do
#     docker run --rm --gpus all -v $(pwd)/results:/app/results \
#       oea-framework-cuda \
#       python experiments/real_lm_experiment.py --model $model
#   done
#
# Run bigram experiments (CPU, no GPU needed):
#   docker run --rm -v $(pwd)/results:/app/results oea-framework-cuda
#
# Requirements:
#   nvidia-container-toolkit must be installed on the host:
#   https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html
#
# For AMD ROCm or Intel XPU Docker, see requirements-lock.txt for install commands.

FROM nvidia/cuda:12.1.1-runtime-ubuntu22.04

# Avoid interactive prompts during apt installs
ENV DEBIAN_FRONTEND=noninteractive

# System dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.11 \
    python3.11-venv \
    python3-pip \
    git \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Make python3.11 the default python/pip
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.11 1 \
    && update-alternatives --install /usr/bin/pip pip /usr/bin/pip3 1

WORKDIR /app

# Copy project files
COPY . .

# Core experiment dependencies (no GPU required)
RUN pip install --no-cache-dir \
    "numpy==2.4.5" \
    "matplotlib==3.10.9" \
    "scipy==1.17.1" \
    "pytest==9.0.3" \
    "reportlab==4.5.1"

# Neural LLM dependencies — CUDA 12.1 torch wheel
RUN pip install --no-cache-dir \
    "torch==2.3.1+cu121" \
    "transformers==4.41.0" \
    "rouge-score==0.1.2" \
    --index-url https://download.pytorch.org/whl/cu121

# Verify installation and GPU visibility
RUN python -c "import numpy, matplotlib, torch, transformers; \
    print('Environment OK'); \
    print(f'PyTorch {torch.__version__}'); \
    print(f'CUDA available: {torch.cuda.is_available()}')"

# Default: run all CPU bigram experiments (GPU available for real LLM experiments)
CMD ["bash", "scripts/run_all_experiments.sh"]