Skip to content

Update ROCm Windows builds #1282

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
superm1 wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Update ROCm Windows builds #1282

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4550d62
Add a Windows ROCm job to use tarball distribution of TheRock
superm1 Feb 14, 2026
5f8d89a
Update HIP target to use 26.Q1 (ROCm 7.1.1)
superm1 Feb 14, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
103 changes: 95 additions & 8 deletions .github/workflows/build.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -387,12 +387,98 @@ jobs:
path: |
sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip

windows-latest-rocm:
runs-on: windows-2022

env:
ROCM_VERSION: "7.11.0"
GPU_TARGETS: "gfx906;gfx908;gfx90a;gfx942;gfx950;gfx1100;gfx1101;gfx1102;gfx1150;gfx1151;gfx1200;gfx1201"

steps:
- uses: actions/checkout@v3
with:
submodules: recursive

- name: Cache ROCm Installation
id: cache-rocm
uses: actions/cache@v4
with:
path: C:\TheRock\build
key: rocm-${{ env.ROCM_VERSION }}-gfx1151-${{ runner.os }}

- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: windows-latest-rocm-${{ env.ROCM_VERSION }}-x64
evict-old-files: 1d

- name: Install ROCm
if: steps.cache-rocm.outputs.cache-hit != 'true'
run: |
$ErrorActionPreference = "Stop"
write-host "Downloading AMD ROCm ${{ env.ROCM_VERSION }} tarball"
Invoke-WebRequest -Uri "https://repo.amd.com/rocm/tarball/therock-dist-windows-gfx1151-${{ env.ROCM_VERSION }}.tar.gz" -OutFile "${env:RUNNER_TEMP}\rocm.tar.gz"
write-host "Extracting ROCm tarball"
mkdir C:\TheRock\build -Force
tar -xzf "${env:RUNNER_TEMP}\rocm.tar.gz" -C C:\TheRock\build --strip-components=1
write-host "Completed ROCm extraction"

- name: Setup ROCm Environment
run: |
$rocmPath = "C:\TheRock\build"
echo "HIP_PATH=$rocmPath" >> $env:GITHUB_ENV
echo "HIP_DEVICE_LIB_PATH=$rocmPath\lib\llvm\amdgcn\bitcode" >> $env:GITHUB_ENV
echo "HIP_PLATFORM=amd" >> $env:GITHUB_ENV
echo "LLVM_PATH=$rocmPath\lib\llvm" >> $env:GITHUB_ENV
echo "$rocmPath\bin" >> $env:GITHUB_PATH
echo "$rocmPath\lib\llvm\bin" >> $env:GITHUB_PATH

- name: Build
run: |
mkdir build
cd build
cmake .. `
-G "Unix Makefiles" `
-DCMAKE_PREFIX_PATH="${env:HIP_PATH}" `
-DSD_HIPBLAS=ON `
-DSD_BUILD_SHARED_LIBS=ON `
-DGGML_NATIVE=OFF `
-DCMAKE_C_COMPILER="${env:HIP_PATH}\lib\llvm\bin\clang.exe" `
-DCMAKE_CXX_COMPILER="${env:HIP_PATH}\lib\llvm\bin\clang++.exe" `
-DCMAKE_HIP_COMPILER="${env:HIP_PATH}\lib\llvm\bin\clang.exe" `
-DHIP_PATH="${env:HIP_PATH}" `
-DCMAKE_BUILD_TYPE=Release `
-DGPU_TARGETS="${{ env.GPU_TARGETS }}"
cmake --build . --config Release --parallel ${env:NUMBER_OF_PROCESSORS}

- name: Get commit hash
id: commit
if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
uses: pr-mpt/actions-commit-hash@v2

- name: Pack artifacts
if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
run: |
cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\"
cp "${env:HIP_PATH}\bin\libhipblaslt.dll" "build\bin\"
cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\"
7z a sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-${{ env.ROCM_VERSION }}-x64.zip .\build\bin\*

- name: Upload artifacts
if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
uses: actions/upload-artifact@v4
with:
name: sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-${{ env.ROCM_VERSION }}-x64.zip
path: |
sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-${{ env.ROCM_VERSION }}-x64.zip

windows-latest-cmake-hip:
runs-on: windows-2022

env:
HIPSDK_INSTALLER_VERSION: "25.Q3"
GPU_TARGETS: "gfx1151;gfx1200;gfx1201;gfx1100;gfx1101;gfx1102;gfx1030;gfx1031;gfx1032"
HIPSDK_INSTALLER_VERSION: "26.Q1"
ROCM_VERSION: "7.1.1"
GPU_TARGETS: "gfx1150;gfx1151;gfx1200;gfx1201;gfx1100;gfx1101;gfx1102;gfx1030;gfx1031;gfx1032"

steps:
- uses: actions/checkout@v3
Expand All @@ -417,7 +503,7 @@ jobs:
run: |
$ErrorActionPreference = "Stop"
write-host "Downloading AMD HIP SDK Installer"
Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-${{ env.HIPSDK_INSTALLER_VERSION }}-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe"
Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-${{ env.HIPSDK_INSTALLER_VERSION }}-Win11-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe"
write-host "Installing AMD HIP SDK"
$proc = Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -PassThru
$completed = $proc.WaitForExit(600000)
Expand Down Expand Up @@ -470,20 +556,20 @@ jobs:
run: |
md "build\bin\rocblas\library\"
md "build\bin\hipblaslt\library"
cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\"
cp "${env:HIP_PATH}\bin\hipblaslt.dll" "build\bin\"
cp "${env:HIP_PATH}\bin\libhipblas.dll" "build\bin\"
cp "${env:HIP_PATH}\bin\libhipblaslt.dll" "build\bin\"
cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\"
cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\"
cp "${env:HIP_PATH}\bin\hipblaslt\library\*" "build\bin\hipblaslt\library\"
7z a sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-x64.zip .\build\bin\*
7z a sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-${{ env.ROCM_VERSION }}-x64.zip .\build\bin\*

- name: Upload artifacts
if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
uses: actions/upload-artifact@v4
with:
name: sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-x64.zip
name: sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-${{ env.ROCM_VERSION }}-x64.zip
path: |
sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-x64.zip
sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-${{ env.ROCM_VERSION }}-x64.zip

ubuntu-latest-rocm:
runs-on: ubuntu-latest
Expand Down Expand Up @@ -638,6 +724,7 @@ jobs:
- macOS-latest-cmake
- windows-latest-cmake
- windows-latest-cmake-hip
- windows-latest-rocm

steps:
- name: Clone
Expand Down
21 changes: 12 additions & 9 deletions docs/hipBLAS_on_Windows.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,12 +26,12 @@ Fortunately, `AMD` provides complete help documentation, you can use the help do

Then we must set `ROCM` as environment variables before running cmake.

Usually if you install according to the official tutorial and do not modify the ROCM path, then there is a high probability that it is here `C:\Program Files\AMD\ROCm\5.5\bin`
Usually if you install according to the official tutorial and do not modify the ROCM path, then there is a high probability that it is here `C:\Program Files\AMD\ROCm\7.1.1\bin`

This is what I use to set the clang:
```Commandline
set CC=C:\Program Files\AMD\ROCm\5.5\bin\clang.exe
set CXX=C:\Program Files\AMD\ROCm\5.5\bin\clang++.exe
set CC=C:\Program Files\AMD\ROCm\7.1.1\bin\clang.exe
set CXX=C:\Program Files\AMD\ROCm\7.1.1\bin\clang++.exe
```

## Ninja
Expand All @@ -46,7 +46,7 @@ set ninja=C:\Program Files\ninja\ninja.exe
## Building stable-diffusion.cpp

The thing different from the regular CPU build is `-DSD_HIPBLAS=ON` ,
`-G "Ninja"`, `-DCMAKE_C_COMPILER=clang`, `-DCMAKE_CXX_COMPILER=clang++`, `-DAMDGPU_TARGETS=gfx1100`
`-G "Ninja"`, `-DCMAKE_C_COMPILER=clang`, `-DCMAKE_CXX_COMPILER=clang++`, `-DAMDGPU_TARGETS=gfx1150;gfx1151;gfx1200;gfx1201;gfx1100;gfx1101;gfx1102;gfx1030;gfx1031;gfx1032`

>**Notice**: check the `clang` and `clang++` information:
```Commandline
Expand All @@ -59,26 +59,29 @@ If you see like this, we can continue:
clang version 17.0.0 (git@github.amd.com:Compute-Mirrors/llvm-project e3201662d21c48894f2156d302276eb1cf47c7be)
Target: x86_64-pc-windows-msvc
Thread model: posix
InstalledDir: C:\Program Files\AMD\ROCm\5.5\bin
InstalledDir: C:\Program Files\AMD\ROCm\7.1.1\bin
```

```
clang version 17.0.0 (git@github.amd.com:Compute-Mirrors/llvm-project e3201662d21c48894f2156d302276eb1cf47c7be)
Target: x86_64-pc-windows-msvc
Thread model: posix
InstalledDir: C:\Program Files\AMD\ROCm\5.5\bin
InstalledDir: C:\Program Files\AMD\ROCm\7.1.1\bin
```

>**Notice** that the `gfx1100` is the GPU architecture of my GPU, you can change it to your GPU architecture. Click here to see your architecture [LLVM Target](https://rocm.docs.amd.com/en/latest/release/windows_support.html#windows-supported-gpus)
>**Notice** that the GPU targets are now compatible with multiple GPU architectures (ROCm 7.1.1 targets). You can change them to match your GPU architecture. Click here to see your architecture [LLVM Target](https://rocm.docs.amd.com/en/latest/release/windows_support.html#windows-supported-gpus)

My GPU is AMD Radeon™ RX 7900 XTX Graphics, so I set it to `gfx1100`.
Examples:
- AMD Radeon™ RX 7900 XTX Graphics: `gfx1100`
- AMD Radeon™ RX 7900 XT Graphics: `gfx1101`
- AMD Radeon™ RX 7900 GRE Graphics: `gfx1102`

option:

```commandline
mkdir build
cd build
cmake .. -G "Ninja" -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DSD_HIPBLAS=ON -DCMAKE_BUILD_TYPE=Release -DAMDGPU_TARGETS=gfx1100
cmake .. -G "Ninja" -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DSD_HIPBLAS=ON -DCMAKE_BUILD_TYPE=Release -DAMDGPU_TARGETS="gfx1150;gfx1151;gfx1200;gfx1201;gfx1100;gfx1101;gfx1102;gfx1030;gfx1031;gfx1032"
cmake --build . --config Release
```

Expand Down