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-intel

@@ -0,0 +1,77 @@
+# Intel GPU Ray Worker for danilo (Intel i915 iGPU)
+# Used for: Reranker
+#
+# Build from llm-workflows root:
+#   docker build -t git.daviestechlabs.io/daviestechlabs/ray-worker-intel:latest -f dockerfiles/Dockerfile.ray-worker-intel .
+#
+# Multi-stage build to ensure Python 3.11.11 matches Ray head node
+FROM rayproject/ray:2.53.0-py311 AS base
+
+LABEL maintainer="billy-davies-2"
+LABEL description="Ray worker for Intel GPUs (Reranker)"
+LABEL gpu.target="intel-xpu"
+
+WORKDIR /app
+
+# Install system dependencies for Intel GPU support
+USER root
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    git \
+    curl \
+    wget \
+    gnupg2 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Add Intel oneAPI repository for runtime libraries
+RUN wget -qO - https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor -o /usr/share/keyrings/intel-oneapi-archive-keyring.gpg && \
+    echo "deb [signed-by=/usr/share/keyrings/intel-oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" > /etc/apt/sources.list.d/intel-oneapi.list
+
+# Add Intel compute-runtime repository for Level Zero
+RUN wget -qO - https://repositories.intel.com/gpu/intel-graphics.key | gpg --dearmor -o /usr/share/keyrings/intel-graphics-archive-keyring.gpg && \
+    echo "deb [signed-by=/usr/share/keyrings/intel-graphics-archive-keyring.gpg arch=amd64] https://repositories.intel.com/gpu/ubuntu jammy client" > /etc/apt/sources.list.d/intel-gpu.list && \
+    apt-get update && apt-get install -y --no-install-recommends \
+    intel-oneapi-runtime-opencl \
+    intel-oneapi-runtime-compilers \
+    intel-level-zero-gpu \
+    level-zero \
+    && rm -rf /var/lib/apt/lists/*
+
+USER ray
+
+# Ensure Ray CLI is in PATH
+ENV PATH="/home/ray/.local/bin:${PATH}"
+
+# Install Intel Extension for PyTorch (IPEX) for Python 3.11
+# This provides XPU support for Intel GPUs
+RUN pip install --no-cache-dir \
+    torch==2.5.1 \
+    intel-extension-for-pytorch==2.5.10+xpu \
+    --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
+
+# Install Ray Serve and AI inference dependencies
+RUN pip install --no-cache-dir \
+    sentence-transformers \
+    FlagEmbedding \
+    fastapi \
+    uvicorn \
+    httpx \
+    pydantic \
+    transformers \
+    huggingface_hub
+
+# Copy Ray Serve Python code
+COPY ray-serve/ /app/ray_serve/
+ENV PYTHONPATH=/app
+
+# Copy Ray Serve entrypoint
+COPY --chmod=755 dockerfiles/ray-entrypoint.sh /app/ray-entrypoint.sh
+
+# Default environment variables
+ENV RAY_HEAD_SVC="ai-inference-raycluster-head-svc"
+ENV GPU_RESOURCE="gpu_intel"
+ENV NUM_GPUS="1"
+# Intel XPU settings
+ENV ZE_AFFINITY_MASK=0
+ENV SYCL_DEVICE_FILTER=level_zero:gpu
+
+ENTRYPOINT ["/app/ray-entrypoint.sh"]

dockerfiles/Dockerfile.ray-worker-nvidia

@@ -0,0 +1,53 @@
+# NVIDIA GPU Ray Worker for elminster (RTX 2070)
+# Used for: Whisper STT, TTS
+#
+# Build from llm-workflows root:
+#   docker build -t git.daviestechlabs.io/daviestechlabs/ray-worker-nvidia:latest -f dockerfiles/Dockerfile.ray-worker-nvidia .
+#
+FROM rayproject/ray:2.53.0-py311-cu121
+
+LABEL maintainer="billy-davies-2"
+LABEL description="Ray worker for NVIDIA GPUs (Whisper, TTS)"
+LABEL gpu.target="nvidia-cuda"
+
+WORKDIR /app
+
+# Install system dependencies for audio processing
+USER root
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    ffmpeg \
+    libsndfile1 \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+USER ray
+
+# Install Python dependencies for inference
+RUN pip install --no-cache-dir \
+    faster-whisper \
+    openai-whisper \
+    TTS \
+    soundfile \
+    pydub \
+    librosa \
+    torch \
+    torchaudio \
+    fastapi \
+    uvicorn \
+    httpx \
+    pydantic
+
+# Copy Ray Serve Python code
+COPY --chown=ray:ray ray-serve/ /app/ray_serve/
+ENV PYTHONPATH=/app
+
+# Copy Ray Serve entrypoint
+COPY --chown=ray:ray dockerfiles/ray-entrypoint.sh /app/ray-entrypoint.sh
+RUN chmod +x /app/ray-entrypoint.sh
+
+# Default environment variables
+ENV CUDA_VISIBLE_DEVICES=0
+ENV RAY_HEAD_SVC="ai-inference-raycluster-head-svc"
+ENV GPU_RESOURCE="gpu_nvidia"
+ENV NUM_GPUS="1"
+
+ENTRYPOINT ["/app/ray-entrypoint.sh"]

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"]

dockerfiles/Dockerfile.ray-worker-strixhalo

@@ -0,0 +1,72 @@
+# Ray Worker for AMD Strix Halo (gfx1151 / RDNA 3.5)
+# Pre-bakes all dependencies for fast startup
+#
+# Build from llm-workflows root:
+#   docker build -t git.daviestechlabs.io/daviestechlabs/ray-worker-strixhalo:latest -f dockerfiles/Dockerfile.ray-worker-strixhalo .
+#
+# Multi-stage build to ensure Python 3.11.11 matches Ray head node
+
+# Stage 1: Extract ROCm 7.1 libraries from vendor image
+FROM docker.io/rocm/pytorch:rocm7.1_ubuntu24.04_py3.12_pytorch_release_2.9.1 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 AMD Strix Halo (gfx1151 / RDNA 3.5)
+ENV HIP_VISIBLE_DEVICES=0
+ENV HSA_ENABLE_SDMA=0
+ENV PYTORCH_HIP_ALLOC_CONF=expandable_segments:True,max_split_size_mb:512
+ENV HSA_OVERRIDE_GFX_VERSION=11.0.0
+ENV ROCM_TARGET_LST=gfx1151,gfx1100
+ENV 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
+
+# WORKAROUND: ROCm/ROCm#5853 - Standard PyTorch ROCm wheels cause segfault
+# in libhsa-runtime64.so during VRAM allocation on gfx1151 (Strix Halo).
+# TheRock gfx110X-all packages provide Python 3.11 compatible wheels.
+RUN pip install --no-cache-dir \
+    --index-url https://rocm.nightlies.amd.com/v2/gfx110X-all/ \
+    torch torchaudio torchvision
+
+# Install Ray Serve and AI inference dependencies
+RUN pip install --no-cache-dir \
+    vllm \
+    transformers \
+    accelerate \
+    sentence-transformers \
+    httpx \
+    numpy \
+    scipy
+
+# Pre-download common models for faster cold starts
+RUN python3 -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('BAAI/bge-large-en-v1.5')" || true
+
+# Copy Ray Serve Python code
+COPY ray-serve/ /app/ray_serve/
+
+# Ray worker entrypoint
+COPY --chmod=755 dockerfiles/ray-entrypoint.sh /app/ray-entrypoint.sh
+
+ENTRYPOINT ["/app/ray-entrypoint.sh"]

dockerfiles/ray-entrypoint.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+# Ray Worker Entrypoint
+# Connects to Ray head node and registers custom resources
+
+set -e
+
+# Ensure Ray is in PATH (works across all base images)
+export PATH="/home/ray/.local/bin:/home/ray/anaconda3/bin:${PATH}"
+
+# Get Ray head address from environment or default
+RAY_HEAD_ADDRESS="${RAY_HEAD_SVC:-ray-head-svc}:6379"
+
+# Get custom resources from environment
+GPU_RESOURCE="${GPU_RESOURCE:-gpu_amd}"
+NUM_GPUS="${NUM_GPUS:-1}"
+
+echo "Starting Ray worker..."
+echo "  Head address: $RAY_HEAD_ADDRESS"
+echo "  GPU resource: $GPU_RESOURCE"
+echo "  Num GPUs: $NUM_GPUS"
+
+# Start Ray worker with custom resources
+exec ray start \
+    --address="$RAY_HEAD_ADDRESS" \
+    --num-gpus="$NUM_GPUS" \
+    --resources="{\"$GPU_RESOURCE\": 1}" \
+    --block