oea-framework-paper/Dockerfile.xpu 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
81
82
83
84
# OEA Framework Paper — Intel Arc / Xe XPU Container (REQ-OEA-020)
#
# COMMUNITY-TESTED ONLY — not verified by maintainer.
# Please report your result (pass or fail) at:
#   https://github.com/BitConcepts/oea-framework-paper/issues/new?template=hardware_compat.md
#
# Requirements:
#   - Intel Arc / Xe / Iris Xe GPU (A-series, B-series, or later)
#   - Intel GPU drivers installed on the Linux host
#   - Linux only (Ubuntu 22.04/24.04 recommended)
#   - Intel oneAPI Base Toolkit (optional but recommended for best performance)
#   - Intel GPU device passthrough requires /dev/dri on the host
#
# Build:
#   docker build -f Dockerfile.xpu -t oea-framework-xpu .
#
# Run real LLM experiment (Intel GPU):
#   docker run --rm \
#     --device /dev/dri \
#     -v $(pwd)/results:/app/results \
#     oea-framework-xpu \
#     python experiments/real_lm_experiment.py --model distilgpt2 --device xpu
#
# Run bigram experiments (CPU, no GPU needed):
#   docker run --rm -v $(pwd)/results:/app/results oea-framework-xpu
#
# Troubleshooting:
#   If torch.xpu.is_available() returns False:
#   1. Verify /dev/dri is accessible: ls -la /dev/dri
#   2. Check Intel GPU driver: intel_gpu_top
#   3. Verify torch XPU support: python -c "import torch; print(torch.xpu.is_available())"
#   4. See Intel Extension for PyTorch docs:
#      https://intel.github.io/intel-extension-for-pytorch/

FROM ubuntu:22.04

# Avoid interactive prompts during apt installs
ENV DEBIAN_FRONTEND=noninteractive

# System dependencies + Python 3.11
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.11 \
    python3.11-venv \
    python3-pip \
    git \
    curl \
    gpg \
    && 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 — PyTorch with XPU support
# PyTorch 2.7+ includes native XPU backend (Intel Arc/Xe via SYCL)
# intel-extension-for-pytorch provides additional optimizations (optional)
RUN pip install --no-cache-dir \
    "torch" \
    "transformers==4.41.0" \
    "rouge-score==0.1.2" \
    --index-url https://download.pytorch.org/whl/xpu

# Verify installation (XPU visibility requires /dev/dri passthrough at runtime)
RUN python -c "import numpy, matplotlib, torch, transformers; \
    print('Environment OK'); \
    print(f'PyTorch {torch.__version__}'); \
    xpu_present = hasattr(torch, 'xpu'); \
    print(f'XPU module present: {xpu_present}')"

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