6c5ccb11f9
This refines where we extract the LLM libraries to by adding a new OLLAMA_HOME env var, that defaults to `~/.ollama` The logic was already idempotenent, so this should speed up startups after the first time a new release is deployed. It also cleans up after itself. We now build only a single ROCm version (latest major) on both windows and linux. Given the large size of ROCms tensor files, we split the dependency out. It's bundled into the installer on windows, and a separate download on windows. The linux install script is now smart and detects the presence of AMD GPUs and looks to see if rocm v6 is already present, and if not, then downloads our dependency tar file. For Linux discovery, we now use sysfs and check each GPU against what ROCm supports so we can degrade to CPU gracefully instead of having llama.cpp+rocm assert/crash on us. For Windows, we now use go's windows dynamic library loading logic to access the amdhip64.dll APIs to query the GPU information.
173 lines
5.3 KiB
YAML
173 lines
5.3 KiB
YAML
name: test
|
|
|
|
on:
|
|
pull_request:
|
|
|
|
jobs:
|
|
generate:
|
|
strategy:
|
|
matrix:
|
|
os: [ubuntu-latest, macos-latest, windows-2019]
|
|
arch: [amd64, arm64]
|
|
exclude:
|
|
- os: ubuntu-latest
|
|
arch: arm64
|
|
- os: windows-2019
|
|
arch: arm64
|
|
runs-on: ${{ matrix.os }}
|
|
env:
|
|
GOARCH: ${{ matrix.arch }}
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
- uses: actions/setup-go@v5
|
|
with:
|
|
go-version: '1.22'
|
|
cache: true
|
|
- run: go get ./...
|
|
- run: |
|
|
$gopath=(get-command go).source | split-path -parent
|
|
& "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\Common7\Tools\Launch-VsDevShell.ps1"
|
|
cd $env:GITHUB_WORKSPACE
|
|
$env:CMAKE_SYSTEM_VERSION="10.0.22621.0"
|
|
$env:PATH="$gopath;$env:PATH"
|
|
go generate -x ./...
|
|
if: ${{ startsWith(matrix.os, 'windows-') }}
|
|
name: "Windows Go Generate"
|
|
- run: go generate -x ./...
|
|
if: ${{ ! startsWith(matrix.os, 'windows-') }}
|
|
name: "Unix Go Generate"
|
|
- uses: actions/upload-artifact@v4
|
|
with:
|
|
name: ${{ matrix.os }}-${{ matrix.arch }}-libraries
|
|
path: llm/llama.cpp/build/**/lib/*
|
|
generate-cuda:
|
|
strategy:
|
|
matrix:
|
|
cuda-version:
|
|
- '11.8.0'
|
|
runs-on: linux
|
|
container: nvidia/cuda:${{ matrix.cuda-version }}-devel-ubuntu20.04
|
|
steps:
|
|
- run: |
|
|
apt-get update && apt-get install -y git build-essential curl
|
|
curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.28.1/cmake-3.28.1-linux-x86_64.tar.gz \
|
|
| tar -zx -C /usr --strip-components 1
|
|
env:
|
|
DEBIAN_FRONTEND: noninteractive
|
|
- uses: actions/checkout@v4
|
|
- uses: actions/setup-go@v4
|
|
with:
|
|
go-version: '1.22'
|
|
cache: true
|
|
- run: go get ./...
|
|
- run: |
|
|
git config --global --add safe.directory /__w/ollama/ollama
|
|
go generate -x ./...
|
|
env:
|
|
OLLAMA_SKIP_CPU_GENERATE: '1'
|
|
- uses: actions/upload-artifact@v4
|
|
with:
|
|
name: cuda-${{ matrix.cuda-version }}-libraries
|
|
path: llm/llama.cpp/build/**/lib/*
|
|
generate-rocm:
|
|
strategy:
|
|
matrix:
|
|
rocm-version:
|
|
- '6.0'
|
|
runs-on: linux
|
|
container: rocm/dev-ubuntu-20.04:${{ matrix.rocm-version }}
|
|
steps:
|
|
- run: |
|
|
apt-get update && apt-get install -y git build-essential curl rocm-libs
|
|
curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.28.1/cmake-3.28.1-linux-x86_64.tar.gz \
|
|
| tar -zx -C /usr --strip-components 1
|
|
env:
|
|
DEBIAN_FRONTEND: noninteractive
|
|
- uses: actions/checkout@v4
|
|
- uses: actions/setup-go@v4
|
|
with:
|
|
go-version: '1.22'
|
|
cache: true
|
|
- run: go get ./...
|
|
- run: |
|
|
git config --global --add safe.directory /__w/ollama/ollama
|
|
go generate -x ./...
|
|
env:
|
|
OLLAMA_SKIP_CPU_GENERATE: '1'
|
|
- uses: actions/upload-artifact@v4
|
|
with:
|
|
name: rocm-${{ matrix.rocm-version }}-libraries
|
|
path: llm/llama.cpp/build/**/lib/*
|
|
lint:
|
|
strategy:
|
|
matrix:
|
|
os: [ubuntu-latest, macos-latest, windows-2019]
|
|
arch: [amd64, arm64]
|
|
exclude:
|
|
- os: ubuntu-latest
|
|
arch: arm64
|
|
- os: windows-2019
|
|
arch: arm64
|
|
- os: macos-latest
|
|
arch: amd64
|
|
runs-on: ${{ matrix.os }}
|
|
env:
|
|
GOARCH: ${{ matrix.arch }}
|
|
CGO_ENABLED: '1'
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
with:
|
|
submodules: recursive
|
|
- uses: actions/setup-go@v5
|
|
with:
|
|
go-version: '1.22'
|
|
cache: false
|
|
- run: |
|
|
mkdir -p llm/llama.cpp/build/linux/${{ matrix.arch }}/stub/lib/
|
|
touch llm/llama.cpp/build/linux/${{ matrix.arch }}/stub/lib/stub.so
|
|
if: ${{ startsWith(matrix.os, 'ubuntu-') }}
|
|
- run: |
|
|
mkdir -p llm/llama.cpp/build/darwin/${{ matrix.arch }}/stub/lib/
|
|
touch llm/llama.cpp/build/darwin/${{ matrix.arch }}/stub/lib/stub.dylib
|
|
touch llm/llama.cpp/ggml-metal.metal
|
|
if: ${{ startsWith(matrix.os, 'macos-') }}
|
|
- run: |
|
|
mkdir -p llm/llama.cpp/build/windows/${{ matrix.arch }}/stub/lib/
|
|
touch llm/llama.cpp/build/windows/${{ matrix.arch }}/stub/lib/stub.dll
|
|
if: ${{ startsWith(matrix.os, 'windows-') }}
|
|
- uses: golangci/golangci-lint-action@v3
|
|
test:
|
|
needs: generate
|
|
strategy:
|
|
matrix:
|
|
os: [ubuntu-latest, macos-latest, windows-2019]
|
|
arch: [amd64]
|
|
exclude:
|
|
- os: ubuntu-latest
|
|
arch: arm64
|
|
- os: windows-2019
|
|
arch: arm64
|
|
runs-on: ${{ matrix.os }}
|
|
env:
|
|
GOARCH: ${{ matrix.arch }}
|
|
CGO_ENABLED: '1'
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
with:
|
|
submodules: recursive
|
|
- uses: actions/setup-go@v5
|
|
with:
|
|
go-version: '1.22'
|
|
cache: true
|
|
- run: go get
|
|
- uses: actions/download-artifact@v4
|
|
with:
|
|
name: ${{ matrix.os }}-${{ matrix.arch }}-libraries
|
|
path: llm/llama.cpp/build
|
|
- run: go build
|
|
- run: go test -v ./...
|
|
- uses: actions/upload-artifact@v4
|
|
with:
|
|
name: ${{ matrix.os }}-binaries
|
|
path: ollama
|