baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge pull request #1679 from ollama/mxyng/build-gpus

Browse source 
build cuda and rocm
This commit is contained in:
Michael Yang 2024-01-25 16:38:14 -08:00 committed by GitHub
commit 2ae0556292
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 64 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

80
.github/workflows/test.yaml vendored
View file

@ -23,27 +23,71 @@ jobs:
with:
go-version: '1.21'
cache: true
- if: ${{ startsWith(matrix.os, 'windows-') }}
shell: pwsh
run: |
$path = vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath
if ($path) {
$path = join-path $path 'Common7\Tools\vsdevcmd.bat'
if (test-path $path) {
cmd /s /c """$path"" $args && set" | where { $_ -match '(\w+)=(.*)' } | foreach {
echo "$($Matches[1])=$($Matches[2])" | Out-File -FilePath $Env:GITHUB_ENV -Encoding utf8 -Append
}
}
}
echo "C:\Program Files\Git\usr\bin" | Out-File -FilePath $Env:GITHUB_PATH -Encoding utf8 -Append
- run: go get ./...
- run: go generate -x ./...
- uses: actions/upload-artifact@v4
with:
name: ${{ matrix.os }}-${{ matrix.arch }}-libraries
path: |
llm/llama.cpp/build/**/lib/*
path: llm/llama.cpp/build/**/lib/*
generate-cuda:
strategy:
matrix:
cuda-version:
- '11.8.0'
runs-on: ubuntu-latest
container: nvidia/cuda:${{ matrix.cuda-version }}-devel-ubuntu20.04
steps:
- run: |
apt-get update && apt-get install -y git build-essential curl
curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.28.1/cmake-3.28.1-linux-x86_64.tar.gz \
| tar -zx -C /usr --strip-components 1
env:
DEBIAN_FRONTEND: noninteractive
- uses: actions/checkout@v4
- uses: actions/setup-go@v4
with:
go-version: '1.21'
cache: true
- run: go get ./...
- run: |
git config --global --add safe.directory /__w/ollama/ollama
go generate -x ./...
env:
OLLAMA_SKIP_CPU_GENERATE: '1'
- uses: actions/upload-artifact@v4
with:
name: cuda-${{ matrix.cuda-version }}-libraries
path: llm/llama.cpp/build/**/lib/*
generate-rocm:
strategy:
matrix:
rocm-version:
- '5.7.1'
- '6.0'
runs-on: ubuntu-latest
container: rocm/dev-ubuntu-20.04:${{ matrix.rocm-version }}
steps:
- run: |
apt-get update && apt-get install -y git build-essential curl rocm-libs
curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.28.1/cmake-3.28.1-linux-x86_64.tar.gz \
| tar -zx -C /usr --strip-components 1
env:
DEBIAN_FRONTEND: noninteractive
- uses: actions/checkout@v4
- uses: actions/setup-go@v4
with:
go-version: '1.21'
cache: true
- run: go get ./...
- run: |
git config --global --add safe.directory /__w/ollama/ollama
go generate -x ./...
env:
OLLAMA_SKIP_CPU_GENERATE: '1'
- uses: actions/upload-artifact@v4
with:
name: rocm-${{ matrix.rocm-version }}-libraries
path: llm/llama.cpp/build/**/lib/*
lint:
strategy:
matrix:
@ -112,3 +156,7 @@ jobs:
path: llm/llama.cpp/build
- run: go build
- run: go test -v ./...
- uses: actions/upload-artifact@v4
with:
name: ${{ matrix.os }}-binaries
path: ollama