.github,docker/unified: include vulkan build (#599)
Update docker/unified scripts to support building both cuda and vulkan unified images.
This commit is contained in:
Benson Wong
GitHub
+81
-26
@@ -1,14 +1,18 @@
|
||||
# Unified multi-stage Dockerfile for CUDA-accelerated AI inference tools
|
||||
# Includes: llama.cpp, whisper.cpp, stable-diffusion.cpp, llama-swap
|
||||
# Unified multi-stage Dockerfile for AI inference tools
|
||||
# Supports CUDA and Vulkan backends via BACKEND build arg
|
||||
#
|
||||
# Usage:
|
||||
# docker buildx build -t llama-swap:unified .
|
||||
# docker buildx build --build-arg BACKEND=cuda -t llama-swap:unified-cuda .
|
||||
# docker buildx build --build-arg BACKEND=vulkan -t llama-swap:unified-vulkan .
|
||||
#
|
||||
# Each project has its own install script that handles cloning, building,
|
||||
# and installing binaries. Build stages are independent for cache efficiency.
|
||||
|
||||
# Builder base: CUDA devel image with build tools
|
||||
FROM nvidia/cuda:12.4.0-devel-ubuntu22.04 AS builder-base
|
||||
ARG BACKEND=cuda
|
||||
|
||||
# ── Builder bases ──────────────────────────────────────────────────────
|
||||
|
||||
FROM nvidia/cuda:12.4.0-devel-ubuntu22.04 AS builder-base-cuda
|
||||
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
ENV CMAKE_CUDA_ARCHITECTURES="60;61;75;86;89"
|
||||
@@ -23,42 +27,72 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
|
||||
WORKDIR /build
|
||||
|
||||
# Build whisper.cpp (fastest build, run first)
|
||||
# ──
|
||||
|
||||
FROM ubuntu:22.04 AS builder-base-vulkan
|
||||
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
ENV CCACHE_DIR=/ccache
|
||||
ENV CCACHE_MAXSIZE=2G
|
||||
ENV PATH="/usr/lib/ccache:${PATH}"
|
||||
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
build-essential cmake git python3 python3-pip libssl-dev \
|
||||
curl ca-certificates ccache make wget software-properties-common \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Install LunarG Vulkan SDK (Ubuntu 22.04 repo headers are too old)
|
||||
RUN wget -qO /etc/apt/trusted.gpg.d/lunarg.asc https://packages.lunarg.com/lunarg-signing-key-pub.asc \
|
||||
&& echo "deb https://packages.lunarg.com/vulkan jammy main" > /etc/apt/sources.list.d/lunarg-vulkan.list \
|
||||
&& apt-get update && apt-get install -y --no-install-recommends vulkan-sdk \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
WORKDIR /build
|
||||
|
||||
# ── Select builder base by BACKEND ────────────────────────────────────
|
||||
|
||||
FROM builder-base-${BACKEND} AS builder-base
|
||||
|
||||
# ── Build whisper.cpp (fastest build, run first) ──────────────────────
|
||||
|
||||
FROM builder-base AS whisper-build
|
||||
ARG BACKEND=cuda
|
||||
ARG WHISPER_COMMIT_HASH=master
|
||||
COPY install-whisper.sh /build/
|
||||
RUN --mount=type=cache,id=ccache-cuda,target=/ccache \
|
||||
--mount=type=cache,id=whisper-cuda,target=/src/whisper.cpp/build \
|
||||
bash /build/install-whisper.sh "${WHISPER_COMMIT_HASH}"
|
||||
RUN --mount=type=cache,id=ccache-${BACKEND},target=/ccache \
|
||||
--mount=type=cache,id=whisper-${BACKEND},target=/src/whisper.cpp/build \
|
||||
BACKEND=${BACKEND} bash /build/install-whisper.sh "${WHISPER_COMMIT_HASH}"
|
||||
|
||||
# ── Build stable-diffusion.cpp ────────────────────────────────────────
|
||||
|
||||
# Build stable-diffusion.cpp
|
||||
FROM builder-base AS sd-build
|
||||
ARG BACKEND=cuda
|
||||
ARG SD_COMMIT_HASH=master
|
||||
COPY install-sd.sh /build/
|
||||
RUN --mount=type=cache,id=ccache-cuda,target=/ccache \
|
||||
--mount=type=cache,id=sd-cuda,target=/src/stable-diffusion.cpp/build \
|
||||
bash /build/install-sd.sh "${SD_COMMIT_HASH}"
|
||||
RUN --mount=type=cache,id=ccache-${BACKEND},target=/ccache \
|
||||
--mount=type=cache,id=sd-${BACKEND},target=/src/stable-diffusion.cpp/build \
|
||||
BACKEND=${BACKEND} bash /build/install-sd.sh "${SD_COMMIT_HASH}"
|
||||
|
||||
# ── Build llama.cpp (slowest build, run last) ─────────────────────────
|
||||
|
||||
# Build llama.cpp (slowest build, run last)
|
||||
FROM builder-base AS llama-build
|
||||
ARG BACKEND=cuda
|
||||
ARG LLAMA_COMMIT_HASH=master
|
||||
COPY install-llama.sh /build/
|
||||
RUN --mount=type=cache,id=ccache-cuda,target=/ccache \
|
||||
--mount=type=cache,id=llama-cuda,target=/src/llama.cpp/build \
|
||||
bash /build/install-llama.sh "${LLAMA_COMMIT_HASH}"
|
||||
RUN --mount=type=cache,id=ccache-${BACKEND},target=/ccache \
|
||||
--mount=type=cache,id=llama-${BACKEND},target=/src/llama.cpp/build \
|
||||
BACKEND=${BACKEND} bash /build/install-llama.sh "${LLAMA_COMMIT_HASH}"
|
||||
|
||||
# ── Download llama-swap release binary ────────────────────────────────
|
||||
|
||||
# Download llama-swap release binary
|
||||
FROM builder-base AS llama-swap-download
|
||||
ARG LS_VERSION=latest
|
||||
COPY install-llama-swap.sh /build/
|
||||
RUN bash /build/install-llama-swap.sh "${LS_VERSION}"
|
||||
|
||||
# Runtime image (no build tooling)
|
||||
FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04 AS runtime
|
||||
# ── Runtime bases ─────────────────────────────────────────────────────
|
||||
|
||||
ARG LLAMA_COMMIT_HASH=unknown
|
||||
ARG WHISPER_COMMIT_HASH=unknown
|
||||
ARG SD_COMMIT_HASH=unknown
|
||||
FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04 AS runtime-cuda
|
||||
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
ENV LD_LIBRARY_PATH="/usr/local/cuda/lib64:${LD_LIBRARY_PATH}"
|
||||
@@ -69,8 +103,29 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# CUDA stub drivers for container compatibility
|
||||
COPY --from=builder-base /usr/local/cuda/lib64/stubs/libcuda.so /usr/local/cuda/lib64/stubs/libcuda.so
|
||||
COPY --from=builder-base /usr/local/cuda/lib64/stubs/libcuda.so /usr/local/cuda/lib64/stubs/libcuda.so.1
|
||||
COPY --from=builder-base-cuda /usr/local/cuda/lib64/stubs/libcuda.so /usr/local/cuda/lib64/stubs/libcuda.so
|
||||
COPY --from=builder-base-cuda /usr/local/cuda/lib64/stubs/libcuda.so /usr/local/cuda/lib64/stubs/libcuda.so.1
|
||||
|
||||
# ──
|
||||
|
||||
FROM ubuntu:22.04 AS runtime-vulkan
|
||||
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
ENV PATH="/usr/local/bin:${PATH}"
|
||||
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
libgomp1 libvulkan1 mesa-vulkan-drivers \
|
||||
python3 python3-pip curl ca-certificates git \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# ── Select runtime base by BACKEND ────────────────────────────────────
|
||||
|
||||
FROM runtime-${BACKEND} AS runtime
|
||||
|
||||
ARG BACKEND=cuda
|
||||
ARG LLAMA_COMMIT_HASH=unknown
|
||||
ARG WHISPER_COMMIT_HASH=unknown
|
||||
ARG SD_COMMIT_HASH=unknown
|
||||
|
||||
RUN pip3 install --no-cache-dir numpy sentencepiece
|
||||
|
||||
@@ -109,7 +164,7 @@ RUN echo "llama.cpp: ${LLAMA_COMMIT_HASH}" > /versions.txt && \
|
||||
echo "whisper.cpp: ${WHISPER_COMMIT_HASH}" >> /versions.txt && \
|
||||
echo "stable-diffusion.cpp: ${SD_COMMIT_HASH}" >> /versions.txt && \
|
||||
echo "llama-swap: $(cat /tmp/llama-swap-version)" >> /versions.txt && \
|
||||
echo "backend: cuda" >> /versions.txt && \
|
||||
echo "backend: ${BACKEND}" >> /versions.txt && \
|
||||
echo "build_timestamp: $(date -u +%Y-%m-%dT%H:%M:%SZ)" >> /versions.txt
|
||||
|
||||
WORKDIR /models
|
||||
|
||||
Reference in New Issue
Block a user