.github/workflows,docker/unified: add cuda based unified container (#597)
Add Docker build scripts for a unified cuda docker container with llama-server, stable-diffusion.cpp, whisper.cpp.
This commit is contained in:
Benson Wong
GitHub
@@ -0,0 +1,121 @@
|
||||
# Unified multi-stage Dockerfile for CUDA-accelerated AI inference tools
|
||||
# Includes: llama.cpp, whisper.cpp, stable-diffusion.cpp, llama-swap
|
||||
#
|
||||
# Usage:
|
||||
# docker buildx build -t llama-swap:unified .
|
||||
#
|
||||
# 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
|
||||
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
ENV CMAKE_CUDA_ARCHITECTURES="60;61;75;86;89"
|
||||
ENV CCACHE_DIR=/ccache
|
||||
ENV CCACHE_MAXSIZE=2G
|
||||
ENV PATH="/usr/lib/ccache:${PATH}"
|
||||
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
build-essential cmake git python3 python3-pip libssl-dev \
|
||||
curl ca-certificates ccache make wget \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
WORKDIR /build
|
||||
|
||||
# Build whisper.cpp (fastest build, run first)
|
||||
FROM builder-base AS whisper-build
|
||||
ARG WHISPER_COMMIT_HASH=master
|
||||
COPY install-whisper.sh /build/
|
||||
RUN --mount=type=cache,id=ccache-cuda,target=/ccache \
|
||||
--mount=type=cache,id=whisper-cuda,target=/src/whisper.cpp/build \
|
||||
bash /build/install-whisper.sh "${WHISPER_COMMIT_HASH}"
|
||||
|
||||
# Build stable-diffusion.cpp
|
||||
FROM builder-base AS sd-build
|
||||
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 "${SD_COMMIT_HASH}"
|
||||
|
||||
# Build llama.cpp (slowest build, run last)
|
||||
FROM builder-base AS llama-build
|
||||
ARG LLAMA_COMMIT_HASH=master
|
||||
COPY install-llama.sh /build/
|
||||
RUN --mount=type=cache,id=ccache-cuda,target=/ccache \
|
||||
--mount=type=cache,id=llama-cuda,target=/src/llama.cpp/build \
|
||||
bash /build/install-llama.sh "${LLAMA_COMMIT_HASH}"
|
||||
|
||||
# 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 "${LS_VERSION}"
|
||||
|
||||
# Runtime image (no build tooling)
|
||||
FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04 AS runtime
|
||||
|
||||
ARG LLAMA_COMMIT_HASH=unknown
|
||||
ARG WHISPER_COMMIT_HASH=unknown
|
||||
ARG SD_COMMIT_HASH=unknown
|
||||
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
ENV LD_LIBRARY_PATH="/usr/local/cuda/lib64:${LD_LIBRARY_PATH}"
|
||||
ENV PATH="/usr/local/bin:${PATH}"
|
||||
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
libgomp1 python3 python3-pip curl ca-certificates git \
|
||||
&& 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
|
||||
|
||||
RUN pip3 install --no-cache-dir numpy sentencepiece
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
# Copy whisper.cpp binaries and libraries
|
||||
COPY --from=whisper-build /install/bin/whisper-server /usr/local/bin/
|
||||
COPY --from=whisper-build /install/bin/whisper-cli /usr/local/bin/
|
||||
COPY --from=whisper-build /install/lib/ /usr/local/lib/
|
||||
|
||||
# Copy stable-diffusion.cpp binaries and libraries
|
||||
COPY --from=sd-build /install/bin/sd-server /usr/local/bin/
|
||||
COPY --from=sd-build /install/bin/sd-cli /usr/local/bin/
|
||||
COPY --from=sd-build /install/lib/ /usr/local/lib/
|
||||
|
||||
# Copy llama.cpp binaries and libraries
|
||||
COPY --from=llama-build /install/bin/llama-server /usr/local/bin/
|
||||
COPY --from=llama-build /install/bin/llama-cli /usr/local/bin/
|
||||
COPY --from=llama-build /install/lib/ /usr/local/lib/
|
||||
|
||||
# Copy llama-swap binary
|
||||
COPY --from=llama-swap-download /install/bin/llama-swap /usr/local/bin/
|
||||
COPY --from=llama-swap-download /install/llama-swap-version /tmp/
|
||||
|
||||
RUN ldconfig
|
||||
|
||||
# Convenience symlinks
|
||||
RUN ln -sf /usr/local/bin/llama-cli /usr/local/bin/llama && \
|
||||
ln -sf /usr/local/bin/whisper-cli /usr/local/bin/whisper && \
|
||||
ln -sf /usr/local/bin/sd-cli /usr/local/bin/stable-diffusion
|
||||
|
||||
# Validate all binaries exist
|
||||
RUN set -e && \
|
||||
for bin in llama-server llama-cli whisper-server whisper-cli sd-server sd-cli llama-swap; do \
|
||||
test -x /usr/local/bin/$bin || { echo "FATAL: $bin missing from /usr/local/bin"; exit 1; }; \
|
||||
done && \
|
||||
echo "All binaries validated successfully"
|
||||
|
||||
# Version tracking
|
||||
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 "build_timestamp: $(date -u +%Y-%m-%dT%H:%M:%SZ)" >> /versions.txt
|
||||
|
||||
WORKDIR /models
|
||||
CMD ["bash"]
|
||||
@@ -0,0 +1,8 @@
|
||||
# Unified Docker Container
|
||||
|
||||
These scripts create a custom llama-swap container that contains:
|
||||
|
||||
- llama-server for LLMs, rerank and embedding model support
|
||||
- sd-server (stable-diffusion.cpp) for image generation
|
||||
- whisper.cpp for ASR
|
||||
|
||||
Executable
+202
@@ -0,0 +1,202 @@
|
||||
#!/bin/bash
|
||||
#
|
||||
# Build script for unified CUDA container with version pinning
|
||||
#
|
||||
# Usage:
|
||||
# ./build-image.sh # Build with auto-detected versions
|
||||
# ./build-image.sh --no-cache # Build without cache
|
||||
# LLAMA_REF=b1234 ./build-image.sh # Pin llama.cpp to a commit hash
|
||||
# LLAMA_REF=v1.2.3 ./build-image.sh # Pin llama.cpp to a tag
|
||||
# LLAMA_REF=my-branch ./build-image.sh # Pin llama.cpp to a branch
|
||||
# WHISPER_REF=v1.0.0 ./build-image.sh # Pin whisper.cpp to a tag
|
||||
# SD_REF=master ./build-image.sh # Pin stable-diffusion.cpp to a branch
|
||||
# LS_VERSION=170 ./build-image.sh # Override llama-swap version
|
||||
#
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
NO_CACHE=false
|
||||
|
||||
for arg in "$@"; do
|
||||
case $arg in
|
||||
--no-cache)
|
||||
NO_CACHE=true
|
||||
;;
|
||||
--help|-h)
|
||||
echo "Usage: ./build-image.sh [--no-cache]"
|
||||
echo ""
|
||||
echo "Environment variables:"
|
||||
echo " DOCKER_IMAGE_TAG Set custom image tag (default: llama-swap:unified)"
|
||||
echo " LLAMA_REF Pin llama.cpp to a commit, tag, or branch"
|
||||
echo " WHISPER_REF Pin whisper.cpp to a commit, tag, or branch"
|
||||
echo " SD_REF Pin stable-diffusion.cpp to a commit, tag, or branch"
|
||||
echo " LS_VERSION Override llama-swap version (e.g., '170' or 'latest')"
|
||||
exit 0
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
DOCKER_IMAGE_TAG="${DOCKER_IMAGE_TAG:-llama-swap:unified}"
|
||||
|
||||
# Git repository URLs
|
||||
LLAMA_REPO="https://github.com/ggml-org/llama.cpp.git"
|
||||
WHISPER_REPO="https://github.com/ggml-org/whisper.cpp.git"
|
||||
SD_REPO="https://github.com/leejet/stable-diffusion.cpp.git"
|
||||
|
||||
# Resolve a git ref (commit hash, tag, or branch) to a full commit hash.
|
||||
# Requires only: git, network access to the remote.
|
||||
resolve_ref() {
|
||||
local repo_url="$1"
|
||||
local ref="$2"
|
||||
|
||||
# Full 40-char SHA — use as-is
|
||||
if [[ "${ref}" =~ ^[0-9a-f]{40}$ ]]; then
|
||||
echo "${ref}"
|
||||
return
|
||||
fi
|
||||
|
||||
# Try tag then branch (exact match)
|
||||
local hash
|
||||
hash=$(git ls-remote "${repo_url}" "refs/tags/${ref}" "refs/heads/${ref}" 2>/dev/null | head -1 | cut -f1)
|
||||
if [[ -n "${hash}" ]]; then
|
||||
echo "${hash}"
|
||||
return
|
||||
fi
|
||||
|
||||
# Short hash (7+ chars): scan all refs for a SHA with this prefix
|
||||
if [[ "${ref}" =~ ^[0-9a-f]{7,}$ ]]; then
|
||||
hash=$(git ls-remote "${repo_url}" 2>/dev/null | grep "^${ref}" | head -1 | cut -f1)
|
||||
if [[ -n "${hash}" ]]; then
|
||||
echo "${hash}"
|
||||
return
|
||||
fi
|
||||
fi
|
||||
|
||||
echo "ERROR: Could not resolve ref '${ref}' for ${repo_url}" >&2
|
||||
if [[ "${ref}" =~ ^[0-9a-f]+$ && ${#ref} -lt 7 ]]; then
|
||||
echo " Short hashes must be at least 7 characters (got ${#ref})." >&2
|
||||
else
|
||||
echo " Tried: tag, branch, git ls-remote prefix match" >&2
|
||||
fi
|
||||
echo " Use a full 40-char SHA, a tag name, a branch name, or a 7+ char short hash." >&2
|
||||
return 1
|
||||
}
|
||||
|
||||
# Resolve HEAD of a repo without needing to know the default branch name.
|
||||
get_latest_hash() {
|
||||
git ls-remote "${1}" HEAD 2>/dev/null | head -1 | cut -f1
|
||||
}
|
||||
|
||||
echo "=========================================="
|
||||
echo "llama-swap Unified CUDA Build"
|
||||
echo "=========================================="
|
||||
echo ""
|
||||
|
||||
# Resolve llama.cpp ref
|
||||
if [[ -n "${LLAMA_REF:-}" ]]; then
|
||||
LLAMA_HASH=$(resolve_ref "${LLAMA_REPO}" "${LLAMA_REF}") || exit 1
|
||||
echo "llama.cpp: ${LLAMA_REF} -> ${LLAMA_HASH}"
|
||||
else
|
||||
LLAMA_HASH=$(get_latest_hash "${LLAMA_REPO}")
|
||||
if [[ -z "${LLAMA_HASH}" ]]; then
|
||||
echo "ERROR: Could not determine latest commit for llama.cpp" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "llama.cpp: latest HEAD: ${LLAMA_HASH}"
|
||||
fi
|
||||
|
||||
# Resolve whisper.cpp ref
|
||||
if [[ -n "${WHISPER_REF:-}" ]]; then
|
||||
WHISPER_HASH=$(resolve_ref "${WHISPER_REPO}" "${WHISPER_REF}") || exit 1
|
||||
echo "whisper.cpp: ${WHISPER_REF} -> ${WHISPER_HASH}"
|
||||
else
|
||||
WHISPER_HASH=$(get_latest_hash "${WHISPER_REPO}")
|
||||
if [[ -z "${WHISPER_HASH}" ]]; then
|
||||
echo "ERROR: Could not determine latest commit for whisper.cpp" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "whisper.cpp: latest HEAD: ${WHISPER_HASH}"
|
||||
fi
|
||||
|
||||
# Resolve stable-diffusion.cpp ref
|
||||
if [[ -n "${SD_REF:-}" ]]; then
|
||||
SD_HASH=$(resolve_ref "${SD_REPO}" "${SD_REF}") || exit 1
|
||||
echo "stable-diffusion.cpp: ${SD_REF} -> ${SD_HASH}"
|
||||
else
|
||||
SD_HASH=$(get_latest_hash "${SD_REPO}")
|
||||
if [[ -z "${SD_HASH}" ]]; then
|
||||
echo "ERROR: Could not determine latest commit for stable-diffusion.cpp" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "stable-diffusion.cpp: latest HEAD: ${SD_HASH}"
|
||||
fi
|
||||
|
||||
# Resolve llama-swap version
|
||||
LS_VER="${LS_VERSION:-latest}"
|
||||
echo "llama-swap: ${LS_VER}"
|
||||
|
||||
echo ""
|
||||
echo "=========================================="
|
||||
echo "Starting Docker build..."
|
||||
echo "=========================================="
|
||||
echo ""
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
|
||||
BUILD_ARGS=(
|
||||
--build-arg "LLAMA_COMMIT_HASH=${LLAMA_HASH}"
|
||||
--build-arg "WHISPER_COMMIT_HASH=${WHISPER_HASH}"
|
||||
--build-arg "SD_COMMIT_HASH=${SD_HASH}"
|
||||
--build-arg "LS_VERSION=${LS_VER}"
|
||||
-t "${DOCKER_IMAGE_TAG}"
|
||||
-f "${SCRIPT_DIR}/Dockerfile"
|
||||
)
|
||||
|
||||
if [[ "$NO_CACHE" == true ]]; then
|
||||
BUILD_ARGS+=(--no-cache)
|
||||
echo "Note: Building without cache"
|
||||
fi
|
||||
|
||||
DOCKER_BUILDKIT=1 docker buildx build --load "${BUILD_ARGS[@]}" "${SCRIPT_DIR}"
|
||||
|
||||
echo ""
|
||||
echo "=========================================="
|
||||
echo "Verifying build artifacts..."
|
||||
echo "=========================================="
|
||||
echo ""
|
||||
|
||||
MISSING_BINARIES=()
|
||||
for binary in llama-server llama-cli whisper-server whisper-cli sd-server sd-cli llama-swap; do
|
||||
if ! docker run --rm "${DOCKER_IMAGE_TAG}" which "${binary}" >/dev/null 2>&1; then
|
||||
MISSING_BINARIES+=("${binary}")
|
||||
fi
|
||||
done
|
||||
|
||||
if [[ ${#MISSING_BINARIES[@]} -gt 0 ]]; then
|
||||
echo "ERROR: Build succeeded but the following binaries are missing:"
|
||||
for binary in "${MISSING_BINARIES[@]}"; do
|
||||
echo " - ${binary}"
|
||||
done
|
||||
echo ""
|
||||
echo "Try running with --no-cache flag:"
|
||||
echo " ./build-image.sh --no-cache"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "All expected binaries verified: llama-server, llama-cli, whisper-server, whisper-cli, sd-server, sd-cli, llama-swap"
|
||||
|
||||
echo ""
|
||||
echo "=========================================="
|
||||
echo "Build complete!"
|
||||
echo "=========================================="
|
||||
echo ""
|
||||
echo "Image tag: ${DOCKER_IMAGE_TAG}"
|
||||
echo ""
|
||||
echo "Built with:"
|
||||
echo " llama.cpp: ${LLAMA_HASH}"
|
||||
echo " whisper.cpp: ${WHISPER_HASH}"
|
||||
echo " stable-diffusion.cpp: ${SD_HASH}"
|
||||
echo " llama-swap: $(docker run --rm "${DOCKER_IMAGE_TAG}" cat /versions.txt | grep llama-swap | cut -d' ' -f2-)"
|
||||
echo ""
|
||||
echo "Run with:"
|
||||
echo " docker run -it --rm --gpus all ${DOCKER_IMAGE_TAG}"
|
||||
Executable
+44
@@ -0,0 +1,44 @@
|
||||
#!/bin/bash
|
||||
# Install llama-swap - download latest release binary from GitHub
|
||||
# Usage: ./install-llama-swap.sh [version]
|
||||
# version: release version number (e.g., "170") or "latest" (default)
|
||||
set -e
|
||||
|
||||
VERSION="${1:-latest}"
|
||||
# Strip leading 'v' prefix so both "198" and "v198" work
|
||||
VERSION="${VERSION#v}"
|
||||
REPO="mostlygeek/llama-swap"
|
||||
|
||||
mkdir -p /install/bin
|
||||
|
||||
# Resolve "latest" to actual version number
|
||||
if [ "$VERSION" = "latest" ]; then
|
||||
echo "=== Resolving latest llama-swap release ==="
|
||||
VERSION=$(curl -fsSL "https://api.github.com/repos/${REPO}/releases/latest" \
|
||||
| grep '"tag_name"' | head -1 | cut -d'"' -f4 | sed 's/^v//')
|
||||
if [ -z "$VERSION" ]; then
|
||||
echo "FATAL: Could not determine latest release version" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "Latest version: ${VERSION}"
|
||||
fi
|
||||
|
||||
# Download and extract
|
||||
URL="https://github.com/${REPO}/releases/download/v${VERSION}/llama-swap_${VERSION}_linux_amd64.tar.gz"
|
||||
echo "=== Downloading llama-swap v${VERSION} ==="
|
||||
echo "URL: $URL"
|
||||
curl -fSL -o /tmp/llama-swap.tar.gz "$URL"
|
||||
tar -xzf /tmp/llama-swap.tar.gz -C /install/bin/
|
||||
rm /tmp/llama-swap.tar.gz
|
||||
|
||||
# Validate
|
||||
if [ ! -x "/install/bin/llama-swap" ]; then
|
||||
echo "FATAL: llama-swap binary not found or not executable" >&2
|
||||
ls -la /install/bin/ >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "$VERSION" > /install/llama-swap-version
|
||||
|
||||
echo "=== llama-swap v${VERSION} installed ==="
|
||||
ls -la /install/bin/llama-swap
|
||||
Executable
+54
@@ -0,0 +1,54 @@
|
||||
#!/bin/bash
|
||||
# Install llama.cpp - clone, build with CUDA, and install binaries
|
||||
# Usage: ./install-llama.sh <commit_hash>
|
||||
set -e
|
||||
|
||||
COMMIT_HASH="${1:-master}"
|
||||
|
||||
mkdir -p /install/bin /install/lib
|
||||
|
||||
# Clone and checkout (init-based so cache-mounted /src/llama.cpp/build dir doesn't break clone)
|
||||
echo "=== Cloning llama.cpp at ${COMMIT_HASH} ==="
|
||||
mkdir -p /src/llama.cpp
|
||||
cd /src/llama.cpp
|
||||
if [ ! -d .git ]; then
|
||||
git init
|
||||
git remote add origin https://github.com/ggml-org/llama.cpp.git
|
||||
fi
|
||||
git fetch --depth=1 origin "${COMMIT_HASH}"
|
||||
git checkout FETCH_HEAD
|
||||
|
||||
# CUDA cmake flags + llama-specific flags
|
||||
CMAKE_FLAGS=(
|
||||
-DGGML_NATIVE=OFF
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DGGML_CUDA=ON
|
||||
-DGGML_VULKAN=OFF
|
||||
"-DCMAKE_CUDA_ARCHITECTURES=${CMAKE_CUDA_ARCHITECTURES:-60;61;75;86;89}"
|
||||
"-DCMAKE_CUDA_FLAGS=-allow-unsupported-compiler"
|
||||
"-DCMAKE_EXE_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda"
|
||||
"-DCMAKE_SHARED_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda"
|
||||
-DCMAKE_C_COMPILER_LAUNCHER=ccache
|
||||
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache
|
||||
-DLLAMA_BUILD_TESTS=OFF
|
||||
)
|
||||
|
||||
TARGETS=(llama-cli llama-server)
|
||||
|
||||
rm -rf build/CMakeCache.txt build/CMakeFiles 2>/dev/null || true
|
||||
|
||||
echo "=== Building llama.cpp for CUDA ==="
|
||||
cmake -B build "${CMAKE_FLAGS[@]}"
|
||||
cmake --build build --config Release -j"$(nproc)" --target "${TARGETS[@]}"
|
||||
|
||||
for bin in "${TARGETS[@]}"; do
|
||||
if [ ! -f "build/bin/$bin" ]; then
|
||||
echo "FATAL: $bin not found in build/bin/" >&2
|
||||
exit 1
|
||||
fi
|
||||
cp "build/bin/$bin" "/install/bin/"
|
||||
done
|
||||
find build -name "*.so*" -type f -exec cp {} /install/lib/ \;
|
||||
|
||||
echo "=== llama.cpp build complete ==="
|
||||
ls -la /install/bin/
|
||||
Executable
+56
@@ -0,0 +1,56 @@
|
||||
#!/bin/bash
|
||||
# Install stable-diffusion.cpp - clone and build with CUDA, install binaries and library
|
||||
# Usage: ./install-sd.sh <commit_hash>
|
||||
set -e
|
||||
|
||||
COMMIT_HASH="${1:-master}"
|
||||
|
||||
mkdir -p /install/bin /install/lib
|
||||
|
||||
# Clone and checkout (init-based so cache-mounted /src/stable-diffusion.cpp/build dir doesn't break clone)
|
||||
echo "=== Cloning stable-diffusion.cpp at ${COMMIT_HASH} ==="
|
||||
mkdir -p /src/stable-diffusion.cpp
|
||||
cd /src/stable-diffusion.cpp
|
||||
if [ ! -d .git ]; then
|
||||
git init
|
||||
git remote add origin https://github.com/leejet/stable-diffusion.cpp.git
|
||||
fi
|
||||
git fetch --depth=1 origin "${COMMIT_HASH}"
|
||||
git checkout FETCH_HEAD
|
||||
git submodule update --init --recursive --depth=1
|
||||
|
||||
# CUDA cmake flags + sd-specific flags
|
||||
CMAKE_FLAGS=(
|
||||
-DGGML_NATIVE=OFF
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DGGML_CUDA=ON
|
||||
-DGGML_VULKAN=OFF
|
||||
"-DCMAKE_CUDA_ARCHITECTURES=${CMAKE_CUDA_ARCHITECTURES:-60;61;75;86;89}"
|
||||
"-DCMAKE_CUDA_FLAGS=-allow-unsupported-compiler"
|
||||
"-DCMAKE_EXE_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda"
|
||||
"-DCMAKE_SHARED_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda"
|
||||
-DCMAKE_C_COMPILER_LAUNCHER=ccache
|
||||
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache
|
||||
-DSD_BUILD_EXAMPLES=ON
|
||||
-DSD_CUDA=ON
|
||||
)
|
||||
|
||||
TARGETS=(stable-diffusion sd-cli sd-server)
|
||||
|
||||
rm -rf build/CMakeCache.txt build/CMakeFiles 2>/dev/null || true
|
||||
|
||||
echo "=== Building stable-diffusion.cpp for CUDA ==="
|
||||
cmake -B build "${CMAKE_FLAGS[@]}"
|
||||
cmake --build build --config Release -j"$(nproc)" --target "${TARGETS[@]}"
|
||||
|
||||
for bin in sd-cli sd-server; do
|
||||
if [ ! -f "build/bin/$bin" ]; then
|
||||
echo "FATAL: $bin not found in build/bin/" >&2
|
||||
exit 1
|
||||
fi
|
||||
cp "build/bin/$bin" "/install/bin/"
|
||||
done
|
||||
find build -name "*.so*" -type f -exec cp {} /install/lib/ \;
|
||||
|
||||
echo "=== stable-diffusion.cpp build complete ==="
|
||||
ls -la /install/bin/ /install/lib/
|
||||
Executable
+53
@@ -0,0 +1,53 @@
|
||||
#!/bin/bash
|
||||
# Install whisper.cpp - clone, build with CUDA, and install binaries
|
||||
# Usage: ./install-whisper.sh <commit_hash>
|
||||
set -e
|
||||
|
||||
COMMIT_HASH="${1:-master}"
|
||||
|
||||
mkdir -p /install/bin /install/lib
|
||||
|
||||
# Clone and checkout (init-based so cache-mounted /src/whisper.cpp/build dir doesn't break clone)
|
||||
echo "=== Cloning whisper.cpp at ${COMMIT_HASH} ==="
|
||||
mkdir -p /src/whisper.cpp
|
||||
cd /src/whisper.cpp
|
||||
if [ ! -d .git ]; then
|
||||
git init
|
||||
git remote add origin https://github.com/ggml-org/whisper.cpp.git
|
||||
fi
|
||||
git fetch --depth=1 origin "${COMMIT_HASH}"
|
||||
git checkout FETCH_HEAD
|
||||
|
||||
# CUDA cmake flags
|
||||
CMAKE_FLAGS=(
|
||||
-DGGML_NATIVE=OFF
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DGGML_CUDA=ON
|
||||
-DGGML_VULKAN=OFF
|
||||
"-DCMAKE_CUDA_ARCHITECTURES=${CMAKE_CUDA_ARCHITECTURES:-60;61;75;86;89}"
|
||||
"-DCMAKE_CUDA_FLAGS=-allow-unsupported-compiler"
|
||||
"-DCMAKE_EXE_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda"
|
||||
"-DCMAKE_SHARED_LINKER_FLAGS=-Wl,-rpath-link,/usr/local/cuda/lib64/stubs -lcuda"
|
||||
-DCMAKE_C_COMPILER_LAUNCHER=ccache
|
||||
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache
|
||||
)
|
||||
|
||||
TARGETS=(whisper-cli whisper-server)
|
||||
|
||||
rm -rf build/CMakeCache.txt build/CMakeFiles 2>/dev/null || true
|
||||
|
||||
echo "=== Building whisper.cpp for CUDA ==="
|
||||
cmake -B build "${CMAKE_FLAGS[@]}"
|
||||
cmake --build build --config Release -j"$(nproc)" --target "${TARGETS[@]}"
|
||||
|
||||
for bin in "${TARGETS[@]}"; do
|
||||
if [ ! -f "build/bin/$bin" ]; then
|
||||
echo "FATAL: $bin not found in build/bin/" >&2
|
||||
exit 1
|
||||
fi
|
||||
cp "build/bin/$bin" "/install/bin/"
|
||||
done
|
||||
find build -name "*.so*" -type f -exec cp {} /install/lib/ \;
|
||||
|
||||
echo "=== whisper.cpp build complete ==="
|
||||
ls -la /install/bin/
|
||||
Reference in New Issue
Block a user