Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
20 commits
Select commit Hold shift + click to select a range
0666ad2
ci : target ROCm 7.14 for build and release (#25775)
superm1 Aug 10, 2026
689e227
opencl: transpose the K tile in local memory for FA prefill kernels (…
wanghqc Aug 10, 2026
030ebb5
Address review comment of PR 25532 (#26852)
gaugarg-nv Aug 10, 2026
84f7129
ggml-webgpu: fix CI errors from #25025 and #25262 (#26566)
yomaytk Aug 11, 2026
48d22e2
common/peg : suppress incomplete escape sequences (#26780)
aldehir Aug 11, 2026
14e78dd
model : fix SWA not being enabled for EXAONE 4.5 (#26848)
junmo-kim Aug 11, 2026
4801e3c
tests : disable backend sampler hip multi output (#26878)
jimw567 Aug 11, 2026
b3df572
tests : clean-up server test, use `tests.sh` in ci (#26886)
ggerganov Aug 11, 2026
153d324
llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)
0cc4m Aug 11, 2026
9afff1b
tests : fix running server tests on windows (#26889)
ggerganov Aug 11, 2026
1138b85
model-conversion : use save_output_data for causual embeddings [no ci…
danbev Aug 11, 2026
7044859
ci: hip-quality-check: update vgpr spill ignore list (#26859)
IMbackK Aug 11, 2026
8d274dd
ui: fix context gauge for single-model usage (#25738)
intel00000 Aug 11, 2026
6e62ba5
mtmd: support pocket-tts (#26871)
ngxson Aug 11, 2026
cc078b4
Dflash support for nemotron-3.5 (#26905)
lnigam Aug 11, 2026
5d16e81
convert : keep quantization scales for nemotron --mtp export (#26903)
ynankani Aug 11, 2026
2468576
requirements: use stable torch packages on s390x (#26864)
nikwen Aug 11, 2026
38406d5
imatrix.cpp: Move finite check and only check touched experts (#26861)
bartowski1182 Aug 11, 2026
70dfba5
ci : add windows-rocm to check-release (#26897)
CISC Aug 11, 2026
ba360ef
chat : tighten bare function parsing for Qwen models (#26793)
aldehir Aug 11, 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
28 changes: 23 additions & 5 deletions .github/actions/windows-setup-rocm/action.yml
Original file line number Diff line number Diff line change
Expand Up @@ -8,8 +8,26 @@ inputs:
runs:
using: "composite"
steps:
- name: Setup ROCm
uses: ./.github/actions/install-exe
with:
url: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-${{ inputs.version }}-Win11-For-HIP.exe
args: -install
- name: Install ROCm with Wheels
shell: pwsh
run: |
$ErrorActionPreference = "Stop"
write-host "Setting up Python virtual environment"

# Create the venv directly at the cache location to avoid relocation issues
New-Item -Path "C:\TheRock\build" -ItemType Directory -Force | Out-Null
python -m venv C:\TheRock\build\.venv
& C:\TheRock\build\.venv\Scripts\Activate.ps1

write-host "Upgrading pip"
python -m pip install --upgrade pip

write-host "Installing ROCm wheels for multi-arch support"
# Install ROCm wheels for multi-arch support (this may take several minutes)
python -m pip install --index-url https://repo.amd.com/rocm/whl-multi-arch/ "rocm[libraries,devel]==${{ inputs.version }}"

# Pre-expand the devel tree so it is included in the cache
write-host "Initializing ROCm devel tree"
rocm-sdk init
if ($LASTEXITCODE -ne 0) { throw "rocm-sdk init failed with exit code $LASTEXITCODE" }
write-host "Completed ROCm wheel installation to C:\TheRock\build"
10 changes: 5 additions & 5 deletions .github/workflows/build-cache.yml
Original file line number Diff line number Diff line change
Expand Up @@ -123,8 +123,8 @@ jobs:
runs-on: windows-2022

env:
# Make sure this is in sync with build.yml
HIPSDK_INSTALLER_VERSION: "26.Q1"
# Make sure this is in sync with release.yml and build-cuda-windows.yml
ROCM_VERSION: "7.14.0"

steps:
- name: Clone
Expand All @@ -135,11 +135,11 @@ jobs:
uses: actions/cache@v5
id: cache-rocm
with:
path: C:\Program Files\AMD\ROCm
key: cache-gha-rocm-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ runner.os }}
path: C:\TheRock\build
key: rocm-wheels-${{ env.ROCM_VERSION }}-multi-arch-${{ runner.os }}

- name: Setup ROCm
if: steps.cache-rocm.outputs.cache-hit != 'true'
uses: ./.github/actions/windows-setup-rocm
with:
version: ${{ env.HIPSDK_INSTALLER_VERSION }}
version: ${{ env.ROCM_VERSION }}
76 changes: 46 additions & 30 deletions .github/workflows/build-cuda-windows.yml
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@ jobs:

env:
# Make sure this is in sync with build-cache.yml
HIPSDK_INSTALLER_VERSION: "26.Q1"
ROCM_VERSION: "7.14.0"

strategy:
matrix:
Expand All @@ -97,65 +97,81 @@ jobs:
id: checkout
uses: actions/checkout@v6

- name: Grab rocWMMA package
id: grab_rocwmma
run: |
curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2.1/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70201-81~24.04_amd64.deb"
7z x rocwmma.deb
7z x data.tar

- name: Use ROCm Installation Cache
- name: Cache ROCm Installation
uses: actions/cache@v5
id: cache-rocm
with:
path: C:\Program Files\AMD\ROCm
key: cache-gha-rocm-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ runner.os }}
path: C:\TheRock\build
key: rocm-wheels-${{ env.ROCM_VERSION }}-multi-arch-${{ runner.os }}

- name: Setup ROCm
if: steps.cache-rocm.outputs.cache-hit != 'true'
uses: ./.github/actions/windows-setup-rocm
with:
version: ${{ env.HIPSDK_INSTALLER_VERSION }}
version: ${{ env.ROCM_VERSION }}

- name: Setup ROCm Environment
run: |
$ErrorActionPreference = "Stop"

# Activate venv from cache or fresh install
& C:\TheRock\build\.venv\Scripts\Activate.ps1

# Expand the devel tree (idempotent; no-op if already done during install)
rocm-sdk init
if ($LASTEXITCODE -ne 0) { throw "rocm-sdk init failed with exit code $LASTEXITCODE" }

# Get ROCm installation paths using the rocm-sdk CLI tool
$rocmPath = (rocm-sdk path --root)
if (-not $rocmPath) { throw "rocm-sdk path --root returned empty - devel package may not be installed" }
$rocmPath = $rocmPath.Trim()
$cmakePath = (rocm-sdk path --cmake).Trim()
$binPath = (rocm-sdk path --bin).Trim()
write-host "ROCm root: $rocmPath"

echo "HIP_PATH=$rocmPath" >> $env:GITHUB_ENV
echo "CMAKE_PREFIX_PATH=$cmakePath" >> $env:GITHUB_ENV
echo "HIP_DEVICE_LIB_PATH=$rocmPath\lib\llvm\amdgcn\bitcode" >> $env:GITHUB_ENV
echo "HIP_PLATFORM=amd" >> $env:GITHUB_ENV
echo "LLVM_PATH=$rocmPath\lib\llvm" >> $env:GITHUB_ENV
echo "$binPath" >> $env:GITHUB_PATH

# Keep venv in PATH for subsequent steps
echo "C:\TheRock\build\.venv\Scripts" >> $env:GITHUB_PATH

- name: Verify ROCm
id: verify
run: |
# Find and test ROCm installation
$clangPath = Get-ChildItem 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | Select-Object -First 1
if (-not $clangPath) {
Write-Error "ROCm installation not found"
exit 1
}
& $clangPath.FullName --version
# Test the ROCm clang shipped in the installed wheel
& "${env:HIP_PATH}\lib\llvm\bin\clang.exe" --version

- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
# TODO: this build does not match the build in release.yml, so we use a different cache key
# ideally, the builds should match, similar to the CUDA build above so that we would be able
# to populate the ccache for the release with manual runs of this workflow
#key: release-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
key: cuda-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
#key: release-windows-2022-x64-hip-${{ env.ROCM_VERSION }}-${{ matrix.name }}
key: cuda-windows-2022-x64-hip-${{ env.ROCM_VERSION }}-${{ matrix.name }}

- name: Build
id: cmake_build
run: |
$env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path)
$env:CMAKE_PREFIX_PATH="${env:HIP_PATH}"
cmake -G "Unix Makefiles" -B build -S . `
-DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" `
-DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" `
-DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.1/include/" `
-DCMAKE_PREFIX_PATH="${env:HIP_PATH}" `
-DCMAKE_C_COMPILER="${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" `
-DCMAKE_BUILD_TYPE=Release `
-DLLAMA_BUILD_BORINGSSL=ON `
-DROCM_DIR="${env:HIP_PATH}" `
-DHIP_PATH="${env:HIP_PATH}" `
-DGGML_HIP=ON `
-DGPU_TARGETS="gfx1100" `
-DGPU_TARGETS="gfx1100" `
-DGGML_RPC=ON
cmake --build build -j ${env:NUMBER_OF_PROCESSORS}

- name: ccache-clear
uses: ./.github/actions/ccache-clear
with:
#key: release-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
key: cuda-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
#key: release-windows-2022-x64-hip-${{ env.ROCM_VERSION }}-${{ matrix.name }}
key: cuda-windows-2022-x64-hip-${{ env.ROCM_VERSION }}-${{ matrix.name }}
Loading