Skip to content

LLM inference in C/C++

C++ ggml

ci : build only the ggml-hip backend for windows-rocm release (#27753)

Harkirat Gill32176338a6c8
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index ab5d3389bd..98250c8606 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -714,10 +714,10 @@ jobs:
with:
key: release-windows-2025-vs2026-${{ matrix.arch }}-cpu
- # TODO: build only the ggml-hip backend like the other windows backend jobs
- # (windows-cuda, windows-sycl), then drop the ui-build dependency
+ # note: builds only the ggml-hip backend - llama-server is injected from the
+ # windows-cpu zip during the release "Merge artifacts" step
windows-rocm:
- needs: [check-release, ui-build]
+ needs: [check-release]
if: ${{ needs.check-release.outputs.should_release == 'true' }}
runs-on: windows-2022
@@ -736,12 +736,6 @@ jobs:
with:
fetch-depth: 0
- - name: Download UI build
- uses: actions/download-artifact@v7
- with:
- name: llama-ui.zip
- path: tools/ui/dist
-
- name: Install Ninja
run: |
choco install ninja
@@ -804,17 +798,15 @@ jobs:
-DCMAKE_PREFIX_PATH="${env:HIP_PATH}" `
-DGGML_BACKEND_DL=ON `
-DGGML_NATIVE=OFF `
- -DGGML_CPU=ON `
- -DGGML_CPU_ALL_VARIANTS=ON `
+ -DGGML_CPU=OFF `
-DGGML_HIP=ON `
-DCMAKE_C_COMPILER="${env:HIP_PATH}\lib\llvm\bin\clang.exe" `
-DCMAKE_CXX_COMPILER="${env:HIP_PATH}\lib\llvm\bin\clang++.exe" `
-DCMAKE_C_FLAGS="-Wno-error=incompatible-pointer-types" `
-DCMAKE_HIP_COMPILER="${env:HIP_PATH}\lib\llvm\bin\clang.exe" `
-DHIP_PATH="${env:HIP_PATH}" `
- -DGGML_HIP_ROCWMMA_FATTN=ON `
-DAMDGPU_TARGETS="${{ matrix.gpu_targets }}"
- cmake --build build --config Release --parallel ${env:NUMBER_OF_PROCESSORS}
+ cmake --build build --config Release --parallel ${env:NUMBER_OF_PROCESSORS} --target ggml-hip
- name: Verify HIP backend was built
run: |
@@ -866,8 +858,11 @@ jobs:
- name: Pack artifacts
run: |
- cp "LICENSE" "build\bin\Release\"
- 7z a -snl llama-bin-win-rocm-${{ env.ROCM_VERSION_SHORT }}-${{ matrix.build }}.zip .\build\bin\Release\*
+ 7z a -snl llama-bin-win-rocm-${{ env.ROCM_VERSION_SHORT }}-${{ matrix.build }}.zip `
+ .\build\bin\Release\ggml-hip.dll `
+ .\build\bin\Release\amdhip64_7.dll `
+ .\build\bin\Release\rocm_kpack.dll `
+ .\build\bin\Release\amd_comgr.dll
- name: Upload artifacts
uses: actions/upload-artifact@v6