Billy D.
5f1873908f
Some checks failed
Build and Push Images / determine-version (push) Successful in 5s
Build and Push Images / build-nvidia (push) Failing after 21s
Build and Push Images / build-rdna2 (push) Failing after 21s
Build and Push Images / build-strixhalo (push) Failing after 12s
Build and Push Images / build-intel (push) Failing after 19s
Build and Push Images / Release (push) Has been skipped
Build and Push Images / Notify (push) Successful in 1s
95 lines
3.5 KiB
Docker
95 lines
3.5 KiB
Docker
# syntax=docker/dockerfile:1.7
|
|
# AMD RDNA 2 Ray Worker for drizzt (Radeon 680M - gfx1035)
|
|
# Used for: BGE Embeddings
|
|
#
|
|
# Build:
|
|
# docker build -t git.daviestechlabs.io/daviestechlabs/ray-worker-rdna2:latest \
|
|
# -f dockerfiles/Dockerfile.ray-worker-rdna2 .
|
|
#
|
|
# Multi-stage build: Extract ROCm from vendor image, use Ray base for Python 3.11
|
|
|
|
# Stage 1: ROCm libraries from AMD vendor image
|
|
FROM docker.io/rocm/pytorch:rocm6.4.4_ubuntu22.04_py3.10_pytorch_release_2.7.1 AS rocm-source
|
|
|
|
# Stage 2: Production image
|
|
FROM docker.io/rayproject/ray:2.53.0-py311 AS production
|
|
|
|
# OCI Image Spec labels
|
|
LABEL org.opencontainers.image.title="Ray Worker - AMD RDNA 2"
|
|
LABEL org.opencontainers.image.description="Ray Serve worker for AMD RDNA 2 GPUs (BGE Embeddings)"
|
|
LABEL org.opencontainers.image.vendor="DaviesTechLabs"
|
|
LABEL org.opencontainers.image.source="https://git.daviestechlabs.io/daviestechlabs/kuberay-images"
|
|
LABEL org.opencontainers.image.licenses="MIT"
|
|
LABEL gpu.target="amd-rocm-6.4-gfx1035"
|
|
LABEL ray.version="2.53.0"
|
|
|
|
WORKDIR /app
|
|
|
|
# Copy ROCm stack from vendor image (--link makes this layer independent for better caching)
|
|
COPY --link --from=rocm-source /opt/rocm /opt/rocm
|
|
|
|
# ROCm environment variables - split to ensure ROCM_HOME is set first
|
|
ENV ROCM_HOME=/opt/rocm
|
|
ENV PATH="/opt/rocm/bin:/opt/rocm/llvm/bin:/home/ray/anaconda3/bin:/home/ray/.local/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin" \
|
|
LD_LIBRARY_PATH="/opt/rocm/lib:/opt/rocm/lib64" \
|
|
HSA_PATH="/opt/rocm/hsa" \
|
|
HIP_PATH="/opt/rocm/hip" \
|
|
# RDNA 2 specific settings
|
|
HIP_VISIBLE_DEVICES=0 \
|
|
HSA_ENABLE_SDMA=0 \
|
|
PYTORCH_HIP_ALLOC_CONF=expandable_segments:True
|
|
|
|
# Install system dependencies
|
|
USER root
|
|
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
|
|
--mount=type=cache,target=/var/lib/apt,sharing=locked \
|
|
apt-get update && apt-get install -y --no-install-recommends \
|
|
libelf1 \
|
|
libnuma1 \
|
|
libdrm2 \
|
|
libdrm-amdgpu1 \
|
|
kmod \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Install uv for fast Python package management (ADR-0014)
|
|
COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
|
|
|
|
USER ray
|
|
|
|
# Install PyTorch with ROCm 6.2 wheels for Python 3.11 (uv is 10-100x faster)
|
|
RUN --mount=type=cache,target=/home/ray/.cache/uv,uid=1000,gid=1000 \
|
|
uv pip install --system \
|
|
torch==2.5.1 torchvision torchaudio \
|
|
--index-url https://download.pytorch.org/whl/rocm6.2
|
|
|
|
# Install inference dependencies
|
|
RUN --mount=type=cache,target=/home/ray/.cache/uv,uid=1000,gid=1000 \
|
|
uv pip install --system \
|
|
'transformers>=4.35.0,<5.0' \
|
|
'accelerate>=0.25.0,<1.0' \
|
|
'sentence-transformers>=2.3.0,<3.0' \
|
|
'httpx>=0.27.0,<1.0' \
|
|
'numpy>=1.26.0,<2.0' \
|
|
'scipy>=1.11.0,<2.0'
|
|
|
|
# Pre-download embedding model for faster cold starts
|
|
RUN python3 -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('BAAI/bge-large-en-v1.5')"
|
|
|
|
# Copy entrypoint script (ray-serve-apps is installed from PyPI at runtime)
|
|
COPY --chown=1000:100 --chmod=755 dockerfiles/ray-entrypoint.sh /app/ray-entrypoint.sh
|
|
|
|
# Environment configuration
|
|
ENV PYTHONPATH=/app \
|
|
PYTHONUNBUFFERED=1 \
|
|
PYTHONDONTWRITEBYTECODE=1 \
|
|
RAY_HEAD_SVC="ai-inference-raycluster-head-svc" \
|
|
GPU_RESOURCE="gpu_amd_rdna2" \
|
|
NUM_GPUS="1"
|
|
|
|
# Health check
|
|
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
|
|
CMD ray status --address=localhost:6379 || exit 1
|
|
|
|
ENTRYPOINT ["/app/ray-entrypoint.sh"]
|
|
# Trigger rebuild
|