LLM inference in C/C++
C++ ggml
ci: rm `GGML_HIP_ROCWMMA_FATTN` (#26760)
Aaron Teo61141f1487e6
diff --git a/.devops/rocm.Dockerfile b/.devops/rocm.Dockerfileindex a8bc4e1fcd..20f6ad6360 100644--- a/.devops/rocm.Dockerfile+++ b/.devops/rocm.Dockerfile@@ -57,7 +57,6 @@ COPY --from=web /app/tools/ui/dist tools/ui/distRUN HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \cmake -S . -B build \-DGGML_HIP=ON \- -DGGML_HIP_ROCWMMA_FATTN=ON \-DAMDGPU_TARGETS="$ROCM_DOCKER_ARCH" \-DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON \-DCMAKE_BUILD_TYPE=Release -DLLAMA_BUILD_TESTS=OFF \diff --git a/.github/workflows/build-cuda-ubuntu.yml b/.github/workflows/build-cuda-ubuntu.ymlindex 6271b22cbd..2528b18573 100644--- a/.github/workflows/build-cuda-ubuntu.yml+++ b/.github/workflows/build-cuda-ubuntu.yml@@ -99,7 +99,6 @@ jobs:run: |cmake -B build -S . \-DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \- -DGGML_HIP_ROCWMMA_FATTN=ON \-DGPU_TARGETS="gfx1030" \-DGGML_HIP=ONcmake --build build --config Release -j $(nproc)diff --git a/.github/workflows/build-cuda-windows.yml b/.github/workflows/build-cuda-windows.ymlindex e9e941421b..367a3a8546 100644--- a/.github/workflows/build-cuda-windows.yml+++ b/.github/workflows/build-cuda-windows.yml@@ -150,7 +150,6 @@ jobs:-DLLAMA_BUILD_BORINGSSL=ON `-DROCM_DIR="${env:HIP_PATH}" `-DGGML_HIP=ON `- -DGGML_HIP_ROCWMMA_FATTN=ON `-DGPU_TARGETS="gfx1100" `-DGGML_RPC=ONcmake --build build -j ${env:NUMBER_OF_PROCESSORS}diff --git a/.github/workflows/release.yml b/.github/workflows/release.ymlindex f587ed93c5..968d2d4b7e 100644--- a/.github/workflows/release.yml+++ b/.github/workflows/release.yml@@ -1229,7 +1229,6 @@ jobs:-DGPU_TARGETS="${{ matrix.gpu_targets }}" \-DGGML_HIP=ON \-DHIP_PLATFORM=amd \- -DGGML_HIP_ROCWMMA_FATTN=ON \-DHF_UI_VERSION=${{ needs.get-version.outputs.ui_version }} \${{ env.CMAKE_ARGS }}cmake --build build --config Release -j $(nproc)@@ -1353,7 +1352,6 @@ jobs:-DGGML_NATIVE=OFF `-DGGML_CPU=OFF `-DGPU_TARGETS="${{ matrix.gpu_targets }}" `- -DGGML_HIP_ROCWMMA_FATTN=ON `-DGGML_HIP=ON `-DHF_UI_VERSION=${{ needs.get-version.outputs.ui_version }} `-DLLAMA_BUILD_BORINGSSL=ONdiff --git a/ci/run.sh b/ci/run.shindex 8506bb4089..f6c7eb0d5c 100755--- a/ci/run.sh+++ b/ci/run.sh@@ -92,7 +92,7 @@ if [ ! -z ${GG_BUILD_CUDA} ]; thenfiif [ ! -z ${GG_BUILD_ROCM} ]; then- CMAKE_EXTRA="${CMAKE_EXTRA} -DCMAKE_HIP_COMPILER=$(hipconfig -l)/clang -DGGML_HIP=ON -DGGML_HIP_ROCWMMA_FATTN=ON"+ CMAKE_EXTRA="${CMAKE_EXTRA} -DCMAKE_HIP_COMPILER=$(hipconfig -l)/clang -DGGML_HIP=ON"if [ -z ${GG_BUILD_AMDGPU_TARGETS} ]; thenecho "Missing GG_BUILD_AMDGPU_TARGETS, please set it to your GPU architecture (e.g. gfx90a, gfx1100, etc.)"exit 1