matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-10 07:46:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Optimize container images for startup (#6547)

Browse Source 
* Optimize container images for startup

This change adjusts how to handle runner payloads to support
container builds where we keep them extracted in the filesystem.
This makes it easier to optimize the cpu/cuda vs cpu/rocm images for
size, and should result in faster startup times for container images.

* Refactor payload logic and add buildx support for faster builds

* Move payloads around

* Review comments

* Converge to buildx based helper scripts

* Use docker buildx action for release
This commit is contained in:
Daniel Hiltgen
2024-09-12 12:10:30 -07:00
committed by GitHub
parent fef257c5c5
commit cd5c8f6471
32 changed files with 861 additions and 689 deletions
Download Patch File Download Diff File Expand all files Collapse all files

103
Dockerfile
View File

@@ -47,7 +47,7 @@ RUN --mount=type=cache,target=/root/.ccache \
OLLAMA_CUSTOM_CUDA_DEFS="-DGGML_CUDA_USE_GRAPHS=on" \
bash gen_linux.sh
FROM --platform=linux/arm64 nvidia/cuda:$CUDA_VERSION_11-devel-rockylinux8 AS cuda-11-build-server-arm64
FROM --platform=linux/arm64 nvidia/cuda:$CUDA_VERSION_11-devel-rockylinux8 AS cuda-11-build-runner-arm64
ARG CMAKE_VERSION
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
@@ -63,7 +63,7 @@ RUN OLLAMA_SKIP_STATIC_GENERATE=1 \
CUDA_VARIANT="_v11" \
bash gen_linux.sh
FROM --platform=linux/arm64 nvidia/cuda:$CUDA_VERSION_12-devel-rockylinux8 AS cuda-12-build-server-arm64
FROM --platform=linux/arm64 nvidia/cuda:$CUDA_VERSION_12-devel-rockylinux8 AS cuda-12-build-runner-arm64
ARG CMAKE_VERSION
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
@@ -143,64 +143,103 @@ RUN --mount=type=cache,target=/root/.ccache \
OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_CPU_TARGET="cpu" bash gen_linux.sh
# Intermediate stage used for ./scripts/build_linux.sh
# Intermediate stages used for ./scripts/build_linux.sh
FROM --platform=linux/amd64 cpu-build-amd64 AS build-amd64
ENV CGO_ENABLED=1
WORKDIR /go/src/github.com/ollama/ollama
COPY . .
COPY --from=static-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cpu_avx-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cpu_avx2-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=static-build-amd64 /go/src/github.com/ollama/ollama/llm/build/ llm/build/
COPY --from=cpu_avx-build-amd64 /go/src/github.com/ollama/ollama/build/ build/
COPY --from=cpu_avx2-build-amd64 /go/src/github.com/ollama/ollama/build/ build/
COPY --from=cuda-11-build-amd64 /go/src/github.com/ollama/ollama/dist/ dist/
COPY --from=cuda-11-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cuda-11-build-amd64 /go/src/github.com/ollama/ollama/build/ build/
COPY --from=cuda-12-build-amd64 /go/src/github.com/ollama/ollama/dist/ dist/
COPY --from=cuda-12-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cuda-12-build-amd64 /go/src/github.com/ollama/ollama/build/ build/
COPY --from=rocm-build-amd64 /go/src/github.com/ollama/ollama/dist/ dist/
COPY --from=rocm-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=rocm-build-amd64 /go/src/github.com/ollama/ollama/build/ build/
ARG GOFLAGS
ARG CGO_CFLAGS
RUN --mount=type=cache,target=/root/.ccache \
go build -trimpath -o dist/linux-amd64/bin/ollama .
RUN cd dist/linux-$GOARCH && \
tar --exclude runners -cf - . | pigz --best > ../ollama-linux-$GOARCH.tgz
RUN cd dist/linux-$GOARCH-rocm && \
tar -cf - . | pigz --best > ../ollama-linux-$GOARCH-rocm.tgz
# Intermediate stage used for ./scripts/build_linux.sh
FROM --platform=linux/arm64 cpu-build-arm64 AS build-arm64
ENV CGO_ENABLED=1
ARG GOLANG_VERSION
WORKDIR /go/src/github.com/ollama/ollama
COPY . .
COPY --from=static-build-arm64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cuda-11-build-server-arm64 /go/src/github.com/ollama/ollama/dist/ dist/
COPY --from=cuda-11-build-server-arm64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cuda-12-build-server-arm64 /go/src/github.com/ollama/ollama/dist/ dist/
COPY --from=cuda-12-build-server-arm64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=static-build-arm64 /go/src/github.com/ollama/ollama/llm/build/ llm/build/
COPY --from=cuda-11-build-runner-arm64 /go/src/github.com/ollama/ollama/dist/ dist/
COPY --from=cuda-11-build-runner-arm64 /go/src/github.com/ollama/ollama/build/ build/
COPY --from=cuda-12-build-runner-arm64 /go/src/github.com/ollama/ollama/dist/ dist/
COPY --from=cuda-12-build-runner-arm64 /go/src/github.com/ollama/ollama/build/ build/
ARG GOFLAGS
ARG CGO_CFLAGS
RUN --mount=type=cache,target=/root/.ccache \
go build -trimpath -o dist/linux-arm64/bin/ollama .
RUN cd dist/linux-$GOARCH && \
tar --exclude runners -cf - . | pigz --best > ../ollama-linux-$GOARCH.tgz
FROM --platform=linux/amd64 scratch AS dist-amd64
COPY --from=build-amd64 /go/src/github.com/ollama/ollama/dist/ollama-linux-*.tgz /
FROM --platform=linux/arm64 scratch AS dist-arm64
COPY --from=build-arm64 /go/src/github.com/ollama/ollama/dist/ollama-linux-*.tgz /
FROM dist-$TARGETARCH as dist
# Optimized container images do not cary nested payloads
FROM --platform=linux/amd64 static-build-amd64 AS container-build-amd64
WORKDIR /go/src/github.com/ollama/ollama
COPY . .
ARG GOFLAGS
ARG CGO_CFLAGS
RUN --mount=type=cache,target=/root/.ccache \
go build -trimpath -o dist/linux-amd64/bin/ollama .
FROM --platform=linux/arm64 static-build-arm64 AS container-build-arm64
WORKDIR /go/src/github.com/ollama/ollama
COPY . .
ARG GOFLAGS
ARG CGO_CFLAGS
RUN --mount=type=cache,target=/root/.ccache \
go build -trimpath -o dist/linux-arm64/bin/ollama .
# Strip out ROCm dependencies to keep the primary image lean
FROM --platform=linux/amd64 ubuntu:22.04 AS amd64-libs-without-rocm
COPY --from=build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /scratch/
RUN cd /scratch/ollama/ && rm -rf rocblas libamd* libdrm* libroc* libhip* libhsa*
# Runtime stages
FROM --platform=linux/amd64 ubuntu:22.04 AS runtime-amd64
COPY --from=amd64-libs-without-rocm /scratch/ /lib/
RUN apt-get update && apt-get install -y ca-certificates && \
RUN apt-get update && \
apt-get install -y ca-certificates && \
apt-get clean && rm -rf /var/lib/apt/lists/*
COPY --from=build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/bin/ /bin/
COPY --from=container-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/bin/ /bin/
COPY --from=cpu-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /lib/
COPY --from=cpu_avx-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /lib/
COPY --from=cpu_avx2-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /lib/
COPY --from=cuda-11-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /lib/
COPY --from=cuda-12-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /lib/
FROM --platform=linux/arm64 ubuntu:22.04 AS runtime-arm64
COPY --from=build-arm64 /go/src/github.com/ollama/ollama/dist/linux-arm64/lib/ /lib/
RUN apt-get update && apt-get install -y ca-certificates && \
RUN apt-get update && \
apt-get install -y ca-certificates && \
apt-get clean && rm -rf /var/lib/apt/lists/*
COPY --from=build-arm64 /go/src/github.com/ollama/ollama/dist/linux-arm64/bin/ /bin/
COPY --from=container-build-arm64 /go/src/github.com/ollama/ollama/dist/linux-arm64/bin/ /bin/
COPY --from=cpu-build-arm64 /go/src/github.com/ollama/ollama/dist/linux-arm64/lib/ /lib/
COPY --from=cuda-11-build-runner-arm64 /go/src/github.com/ollama/ollama/dist/linux-arm64/lib/ /lib/
COPY --from=cuda-12-build-runner-arm64 /go/src/github.com/ollama/ollama/dist/linux-arm64/lib/ /lib/
# Radeon images are much larger so we keep it distinct from the CPU/CUDA image
FROM rocm/dev-centos-7:${ROCM_VERSION}-complete AS runtime-rocm
RUN update-pciids
COPY --from=build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/bin/ /bin/
RUN ln -s /opt/rocm/lib /lib/ollama
# ROCm libraries larger so we keep it distinct from the CPU/CUDA image
FROM --platform=linux/amd64 ubuntu:22.04 AS runtime-rocm
# Frontload the rocm libraries which are large, and rarely change to increase chance of a common layer
# across releases
COPY --from=rocm-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64-rocm/lib/ /lib/
RUN apt-get update && \
apt-get install -y ca-certificates && \
apt-get clean && rm -rf /var/lib/apt/lists/*
COPY --from=container-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/bin/ /bin/
COPY --from=cpu-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /lib/
COPY --from=cpu_avx-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /lib/
COPY --from=cpu_avx2-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /lib/
COPY --from=rocm-build-amd64 /go/src/github.com/ollama/ollama/dist/linux-amd64/lib/ /lib/
EXPOSE 11434
ENV OLLAMA_HOST=0.0.0.0