diff --git a/.github/workflows/image-pr.yml b/.github/workflows/image-pr.yml index 2452ef04..3e4d8e4d 100644 --- a/.github/workflows/image-pr.yml +++ b/.github/workflows/image-pr.yml @@ -46,7 +46,7 @@ jobs: makeflags: "--jobs=3 --output-sync=target" - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "5" + cuda-minor-version: "4" platforms: 'linux/amd64' tag-latest: 'false' tag-suffix: '-cublas-cuda12-ffmpeg' @@ -119,7 +119,7 @@ jobs: makeflags: "--jobs=3 --output-sync=target" - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "5" + cuda-minor-version: "4" platforms: 'linux/amd64' tag-latest: 'false' tag-suffix: '-cublas-cuda12-ffmpeg-core' diff --git a/.github/workflows/image.yml b/.github/workflows/image.yml index 0a30e46f..73899e15 100644 --- a/.github/workflows/image.yml +++ b/.github/workflows/image.yml @@ -64,7 +64,7 @@ jobs: makeflags: "--jobs=3 --output-sync=target" - build-type: 'cublas' cuda-major-version: "11" - cuda-minor-version: "8" + cuda-minor-version: "7" platforms: 'linux/amd64' tag-latest: 'false' tag-suffix: '-cublas-cuda11' @@ -75,7 +75,7 @@ jobs: makeflags: "--jobs=3 --output-sync=target" - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "5" + cuda-minor-version: "4" platforms: 'linux/amd64' tag-latest: 'false' tag-suffix: '-cublas-cuda12' @@ -86,7 +86,7 @@ jobs: makeflags: "--jobs=3 --output-sync=target" - build-type: 'cublas' cuda-major-version: "11" - cuda-minor-version: "8" + cuda-minor-version: "7" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-cublas-cuda11-ffmpeg' @@ -100,7 +100,7 @@ jobs: makeflags: "--jobs=3 --output-sync=target" - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "5" + cuda-minor-version: "4" platforms: 'linux/amd64' tag-latest: 'auto' tag-suffix: '-cublas-cuda12-ffmpeg' @@ -274,7 +274,7 @@ jobs: makeflags: "--jobs=4 --output-sync=target" - build-type: 'cublas' cuda-major-version: "11" - cuda-minor-version: "8" + cuda-minor-version: "7" platforms: 'linux/amd64' tag-latest: 'false' tag-suffix: '-cublas-cuda11-core' @@ -285,7 +285,7 @@ jobs: makeflags: "--jobs=4 --output-sync=target" - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "5" + cuda-minor-version: "4" platforms: 'linux/amd64' tag-latest: 'false' tag-suffix: '-cublas-cuda12-core' @@ -296,7 +296,7 @@ jobs: makeflags: "--jobs=4 --output-sync=target" - build-type: 'cublas' cuda-major-version: "11" - cuda-minor-version: "8" + cuda-minor-version: "7" platforms: 'linux/amd64' tag-latest: 'false' tag-suffix: '-cublas-cuda11-ffmpeg-core' @@ -307,7 +307,7 @@ jobs: makeflags: "--jobs=4 --output-sync=target" - build-type: 'cublas' cuda-major-version: "12" - cuda-minor-version: "5" + cuda-minor-version: "4" platforms: 'linux/amd64' tag-latest: 'false' tag-suffix: '-cublas-cuda12-ffmpeg-core' diff --git a/.github/workflows/image_build.yml b/.github/workflows/image_build.yml index 53015565..c891d3dd 100644 --- a/.github/workflows/image_build.yml +++ b/.github/workflows/image_build.yml @@ -23,7 +23,7 @@ on: type: string cuda-minor-version: description: 'CUDA minor version' - default: "5" + default: "4" type: string platforms: description: 'Platforms' diff --git a/.github/workflows/release.yaml b/.github/workflows/release.yaml index efd33f83..86d60921 100644 --- a/.github/workflows/release.yaml +++ b/.github/workflows/release.yaml @@ -40,7 +40,7 @@ jobs: sudo apt-get update sudo apt-get install -y cuda-cross-aarch64 cuda-nvcc-cross-aarch64-${CUDA_VERSION} libcublas-cross-aarch64-${CUDA_VERSION} env: - CUDA_VERSION: 12-5 + CUDA_VERSION: 12-4 - name: Cache grpc id: cache-grpc uses: actions/cache@v4 diff --git a/Dockerfile b/Dockerfile index ac42db5d..907ad54b 100644 --- a/Dockerfile +++ b/Dockerfile @@ -99,7 +99,7 @@ FROM requirements-${IMAGE_TYPE} AS requirements-drivers ARG BUILD_TYPE ARG CUDA_MAJOR_VERSION=12 -ARG CUDA_MINOR_VERSION=5 +ARG CUDA_MINOR_VERSION=4 ENV BUILD_TYPE=${BUILD_TYPE} diff --git a/Makefile b/Makefile index e2ae5c49..d4ca1e4f 100644 --- a/Makefile +++ b/Makefile @@ -425,7 +425,7 @@ prepare-e2e: mkdir -p $(TEST_DIR) cp -rfv $(abspath ./tests/e2e-fixtures)/gpu.yaml $(TEST_DIR)/gpu.yaml test -e $(TEST_DIR)/ggllm-test-model.bin || wget -q https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q2_K.gguf -O $(TEST_DIR)/ggllm-test-model.bin - docker build --build-arg GRPC_BACKENDS="$(GRPC_BACKENDS)" --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=5 --build-arg FFMPEG=true -t localai-tests . + docker build --build-arg GRPC_BACKENDS="$(GRPC_BACKENDS)" --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=4 --build-arg FFMPEG=true -t localai-tests . run-e2e-image: ls -liah $(abspath ./tests/e2e-fixtures)