starred/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-26 10:45:57 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
6b1f84e171ea5fbf88f0dfca8d00856d8e4e4555
ollama/Dockerfile
Vadim Grinco 6b1f84e171 Merging the latest stable (#2) 
* Applied 00-fix-vulkan-building.patch

* Implemented vulkan backend based on the work done by whyvl, Dts0, McBane87 and others

Tested on AMD Ryzen 7 8845HS w/ Radeon 780M Graphics with ROCm disabled

```
[GIN-debug] POST   /v1/chat/completions      --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers)
[GIN-debug] POST   /v1/completions           --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers)
[GIN-debug] POST   /v1/embeddings            --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (6 handlers)
[GIN-debug] GET    /v1/models                --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (6 handlers)
[GIN-debug] GET    /v1/models/:model         --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (6 handlers)
time=2025-03-11T13:00:40.793Z level=INFO source=gpu.go:199 msg="vulkan: load libvulkan and libcap ok"
time=2025-03-11T13:00:40.877Z level=INFO source=gpu.go:421 msg="error looking up vulkan GPU memory" error="device is a CPU"
time=2025-03-11T13:00:40.878Z level=WARN source=amd_linux.go:443 msg="amdgpu detected, but no compatible rocm library found.  Either install rocm v6, or follow manual install instructions at https://github.com/ollama/ollama/blob/main/docs/linux.md#manual-install"
time=2025-03-11T13:00:40.878Z level=WARN source=amd_linux.go:348 msg="unable to verify rocm library: no suitable rocm found, falling back to CPU"
time=2025-03-11T13:00:40.879Z level=INFO source=types.go:137 msg="inference compute" id=0 library=vulkan variant="" compute=1.3 driver=1.3 name="AMD Radeon Graphics (RADV GFX1103_R1)" total="15.6 GiB" available="15.6 GiB"
```

```
 # ollama run phi4:14b
>>> /set verbose
Set 'verbose' mode.
>>> how's it going?
Hello! I'm here to help you with any questions or tasks you have. How can I assist you today? 😊

total duration:       3.341959745s
load duration:        18.165612ms
prompt eval count:    15 token(s)
prompt eval duration: 475ms
prompt eval rate:     31.58 tokens/s
eval count:           26 token(s)
eval duration:        2.846s
eval rate:            9.14 tokens/s
>>>
```
2025-03-11 14:09:47 +01:00

151 lines
6.7 KiB
Docker
Raw Blame History

# vim: filetype=dockerfile
ARG FLAVOR=${TARGETARCH}
ARG ROCMVERSION=6.3.3
ARG JETPACK5VERSION=r35.4.1
ARG JETPACK6VERSION=r36.4.0
ARG CMAKEVERSION=3.31.2
ARG VULKANVERSION=1.4.304.1
# CUDA v11 requires gcc v10. v10.3 has regressions, so the rockylinux 8.5 AppStream has the latest compatible version
FROM --platform=linux/amd64 rocm/dev-almalinux-8:${ROCMVERSION}-complete AS base-amd64
RUN yum install -y yum-utils \
&& yum-config-manager --add-repo https://dl.rockylinux.org/vault/rocky/8.5/AppStream/\$basearch/os/ \
&& rpm --import https://dl.rockylinux.org/pub/rocky/RPM-GPG-KEY-Rocky-8 \
&& dnf install -y yum-utils ccache gcc-toolset-10-gcc-10.2.1-8.2.el8 gcc-toolset-10-gcc-c++-10.2.1-8.2.el8 gcc-toolset-10-binutils-2.35-11.el8 \
&& yum-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/x86_64/cuda-rhel8.repo
ENV PATH=/opt/rh/gcc-toolset-10/root/usr/bin:$PATH
ARG VULKANVERSION
RUN wget https://sdk.lunarg.com/sdk/download/${VULKANVERSION}/linux/vulkansdk-linux-x86_64-${VULKANVERSION}.tar.xz -O /tmp/vulkansdk-linux-x86_64-${VULKANVERSION}.tar.xz \
&& tar xvf /tmp/vulkansdk-linux-x86_64-${VULKANVERSION}.tar.xz \
&& dnf -y install ninja-build libcap-devel \
&& ln -s /usr/bin/python3 /usr/bin/python \
&& /${VULKANVERSION}/vulkansdk -j 8 vulkan-headers \
&& /${VULKANVERSION}/vulkansdk -j 8 shaderc
RUN cp -r /${VULKANVERSION}/x86_64/include/* /usr/local/include/ \
&& cp -r /${VULKANVERSION}/x86_64/lib/* /usr/local/lib
ENV PATH=/${VULKANVERSION}/x86_64/bin:$PATH
FROM --platform=linux/arm64 almalinux:8 AS base-arm64
# install epel-release for ccache
RUN yum install -y yum-utils epel-release \
&& dnf install -y clang ccache \
&& yum-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/sbsa/cuda-rhel8.repo
ENV CC=clang CXX=clang++
FROM base-${TARGETARCH} AS base
ARG CMAKEVERSION
RUN curl -fsSL https://github.com/Kitware/CMake/releases/download/v${CMAKEVERSION}/cmake-${CMAKEVERSION}-linux-$(uname -m).tar.gz | tar xz -C /usr/local --strip-components 1
COPY CMakeLists.txt CMakePresets.json .
COPY ml/backend/ggml/ggml ml/backend/ggml/ggml
ENV LDFLAGS=-s
FROM base AS cpu
RUN dnf install -y gcc-toolset-11-gcc gcc-toolset-11-gcc-c++
ENV PATH=/opt/rh/gcc-toolset-11/root/usr/bin:$PATH
RUN --mount=type=cache,target=/root/.ccache \
cmake --preset 'CPU' \
&& cmake --build --parallel --preset 'CPU' \
&& cmake --install build --component CPU --strip --parallel 8
FROM base AS cuda-11
ARG CUDA11VERSION=11.3
RUN dnf install -y cuda-toolkit-${CUDA11VERSION//./-}
ENV PATH=/usr/local/cuda-11/bin:$PATH
RUN --mount=type=cache,target=/root/.ccache \
cmake --preset 'CUDA 11' \
&& cmake --build --parallel --preset 'CUDA 11' \
&& cmake --install build --component CUDA --strip --parallel 8
FROM base AS cuda-12
ARG CUDA12VERSION=12.8
RUN dnf install -y cuda-toolkit-${CUDA12VERSION//./-}
ENV PATH=/usr/local/cuda-12/bin:$PATH
RUN --mount=type=cache,target=/root/.ccache \
cmake --preset 'CUDA 12' \
&& cmake --build --parallel --preset 'CUDA 12' \
&& cmake --install build --component CUDA --strip --parallel 8
FROM base AS rocm-6
ENV PATH=/opt/rocm/hcc/bin:/opt/rocm/hip/bin:/opt/rocm/bin:/opt/rocm/hcc/bin:$PATH
RUN --mount=type=cache,target=/root/.ccache \
cmake --preset 'ROCm 6' \
&& cmake --build --parallel --preset 'ROCm 6' \
&& cmake --install build --component HIP --strip --parallel 8
FROM --platform=linux/arm64 nvcr.io/nvidia/l4t-jetpack:${JETPACK5VERSION} AS jetpack-5
ARG CMAKEVERSION
RUN apt-get update && apt-get install -y curl ccache \
&& curl -fsSL https://github.com/Kitware/CMake/releases/download/v${CMAKEVERSION}/cmake-${CMAKEVERSION}-linux-$(uname -m).tar.gz | tar xz -C /usr/local --strip-components 1
COPY CMakeLists.txt CMakePresets.json .
COPY ml/backend/ggml/ggml ml/backend/ggml/ggml
RUN --mount=type=cache,target=/root/.ccache \
cmake --preset 'JetPack 5' \
&& cmake --build --parallel --preset 'JetPack 5' \
&& cmake --install build --component CUDA --strip --parallel 8
FROM --platform=linux/arm64 nvcr.io/nvidia/l4t-jetpack:${JETPACK6VERSION} AS jetpack-6
ARG CMAKEVERSION
RUN apt-get update && apt-get install -y curl ccache \
&& curl -fsSL https://github.com/Kitware/CMake/releases/download/v${CMAKEVERSION}/cmake-${CMAKEVERSION}-linux-$(uname -m).tar.gz | tar xz -C /usr/local --strip-components 1
COPY CMakeLists.txt CMakePresets.json .
COPY ml/backend/ggml/ggml ml/backend/ggml/ggml
RUN --mount=type=cache,target=/root/.ccache \
cmake --preset 'JetPack 6' \
&& cmake --build --parallel --preset 'JetPack 6' \
&& cmake --install build --component CUDA --strip --parallel 8
FROM base AS vulkan
RUN --mount=type=cache,target=/root/.ccache \
cmake --preset 'Vulkan' \
&& cmake --build --parallel --preset 'Vulkan' \
&& cmake --install build --component Vulkan --strip --parallel 8
FROM base AS build
WORKDIR /go/src/github.com/ollama/ollama
COPY go.mod go.sum .
RUN curl -fsSL https://golang.org/dl/go$(awk '/^go/ { print $2 }' go.mod).linux-$(case $(uname -m) in x86_64) echo amd64 ;; aarch64) echo arm64 ;; esac).tar.gz | tar xz -C /usr/local
ENV PATH=/usr/local/go/bin:$PATH
RUN go mod download
COPY . .
ARG GOFLAGS="'-ldflags=-w -s'"
ENV CGO_ENABLED=1
RUN --mount=type=cache,target=/root/.cache/go-build \
go build -trimpath -buildmode=pie -o /bin/ollama .
FROM --platform=linux/amd64 scratch AS amd64
COPY --from=cuda-11 dist/lib/ollama/cuda_v11 /lib/ollama/cuda_v11
COPY --from=cuda-12 dist/lib/ollama/cuda_v12 /lib/ollama/cuda_v12
COPY --from=vulkan dist/lib/ollama/vulkan /lib/ollama/vulkan
FROM --platform=linux/arm64 scratch AS arm64
COPY --from=cuda-11 dist/lib/ollama/cuda_v11 /lib/ollama/cuda_v11
COPY --from=cuda-12 dist/lib/ollama/cuda_v12 /lib/ollama/cuda_v12
COPY --from=jetpack-5 dist/lib/ollama/cuda_v11 lib/ollama/cuda_jetpack5
COPY --from=jetpack-6 dist/lib/ollama/cuda_v12 lib/ollama/cuda_jetpack6
FROM scratch AS rocm
COPY --from=rocm-6 dist/lib/ollama/rocm /lib/ollama/rocm
FROM ${FLAVOR} AS archive
ARG VULKANVERSION
COPY --from=cpu dist/lib/ollama /lib/ollama
COPY --from=build /bin/ollama /bin/ollama
FROM ubuntu:24.04
RUN apt-get update \
&& apt-get install -y ca-certificates libcap2 libvulkan1 \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
COPY --from=archive /bin /usr/bin
COPY --from=archive /lib/ollama /usr/lib/ollama
ENV PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
ENV NVIDIA_VISIBLE_DEVICES=all
ENV OLLAMA_HOST=0.0.0.0:11434
EXPOSE 11434
ENTRYPOINT ["/bin/ollama"]
CMD ["serve"]
Reference in New Issue View Git Blame Copy Permalink