feat: Add GPU-specific Ray worker images with CI/CD

- Add Dockerfiles for nvidia, rdna2, strixhalo, and intel GPU targets
- Add ray-serve modules (embeddings, whisper, tts, llm, reranker)
- Add Gitea Actions workflow for automated builds
- Add Makefile for local development
- Update README with comprehensive documentation

dockerfiles/Dockerfile.ray-worker-rdna2

@@ -0,0 +1,65 @@
+# Ray Worker for AMD RDNA 2 (gfx1035 - Radeon 680M)
+# Pre-bakes all dependencies for fast startup
+#
+# Build from llm-workflows root:
+#   docker build -t git.daviestechlabs.io/daviestechlabs/ray-worker-rdna2:latest -f dockerfiles/Dockerfile.ray-worker-rdna2 .
+#
+# Multi-stage build to ensure Python 3.11.11 matches Ray head node
+
+# Stage 1: Extract ROCm libraries from vendor image
+FROM docker.io/rocm/pytorch:rocm6.4.4_ubuntu22.04_py3.10_pytorch_release_2.7.1 AS rocm-libs
+
+# Stage 2: Build on Ray base with Python 3.11
+FROM rayproject/ray:2.53.0-py311 AS base
+
+# Copy ROCm stack from vendor image
+COPY --from=rocm-libs /opt/rocm /opt/rocm
+
+# Set up ROCm environment
+ENV ROCM_HOME=/opt/rocm
+ENV PATH="${ROCM_HOME}/bin:${ROCM_HOME}/llvm/bin:${PATH}"
+ENV LD_LIBRARY_PATH="${ROCM_HOME}/lib:${ROCM_HOME}/lib64:${LD_LIBRARY_PATH}"
+ENV HSA_PATH="${ROCM_HOME}/hsa"
+ENV HIP_PATH="${ROCM_HOME}/hip"
+
+# ROCm environment for RDNA 2 (gfx1035)
+ENV HIP_VISIBLE_DEVICES=0 \
+    HSA_ENABLE_SDMA=0 \
+    PYTORCH_HIP_ALLOC_CONF=expandable_segments:True \
+    PYTHONPATH=/app
+
+WORKDIR /app
+
+# Install ROCm system dependencies
+USER root
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libelf1 \
+    libnuma1 \
+    libdrm2 \
+    libdrm-amdgpu1 \
+    kmod \
+    && rm -rf /var/lib/apt/lists/*
+USER ray
+
+# Install PyTorch ROCm wheels compatible with Python 3.11 and ROCm 6.2
+RUN pip install --no-cache-dir \
+    torch==2.5.1 torchvision torchaudio \
+    --index-url https://download.pytorch.org/whl/rocm6.2
+
+# Install Ray Serve and AI inference dependencies
+RUN pip install --no-cache-dir \
+    transformers \
+    accelerate \
+    sentence-transformers \
+    httpx \
+    numpy \
+    scipy
+
+# Pre-download embedding model for faster cold starts
+RUN python3 -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('BAAI/bge-large-en-v1.5')"
+
+# Copy application code
+COPY ray-serve/ /app/ray_serve/
+COPY --chmod=755 dockerfiles/ray-entrypoint.sh /app/ray-entrypoint.sh
+
+ENTRYPOINT ["/app/ray-entrypoint.sh"]