mirror of
https://github.com/mudler/LocalAI.git
synced 2024-12-19 20:57:54 +00:00
feat: Upgrade to CUDA 12.5 (#2601)
Signed-off-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com>
This commit is contained in:
Rene Leonhardt
GitHub
parent
8142bdc48f
commit
43f0688a95
4
.github/workflows/image-pr.yml
vendored
4
.github/workflows/image-pr.yml
vendored
@ -46,7 +46,7 @@ jobs:
|
||||
makeflags: "--jobs=3 --output-sync=target"
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "1"
|
||||
cuda-minor-version: "5"
|
||||
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: "1"
|
||||
cuda-minor-version: "5"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'false'
|
||||
tag-suffix: '-cublas-cuda12-ffmpeg-core'
|
||||
|
||||
16
.github/workflows/image.yml
vendored
16
.github/workflows/image.yml
vendored
@ -64,7 +64,7 @@ jobs:
|
||||
makeflags: "--jobs=3 --output-sync=target"
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "11"
|
||||
cuda-minor-version: "7"
|
||||
cuda-minor-version: "8"
|
||||
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: "1"
|
||||
cuda-minor-version: "5"
|
||||
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: "7"
|
||||
cuda-minor-version: "8"
|
||||
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: "1"
|
||||
cuda-minor-version: "5"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-cublas-cuda12-ffmpeg'
|
||||
@ -273,7 +273,7 @@ jobs:
|
||||
makeflags: "--jobs=4 --output-sync=target"
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "11"
|
||||
cuda-minor-version: "7"
|
||||
cuda-minor-version: "8"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'false'
|
||||
tag-suffix: '-cublas-cuda11-core'
|
||||
@ -284,7 +284,7 @@ jobs:
|
||||
makeflags: "--jobs=4 --output-sync=target"
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "1"
|
||||
cuda-minor-version: "5"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'false'
|
||||
tag-suffix: '-cublas-cuda12-core'
|
||||
@ -295,7 +295,7 @@ jobs:
|
||||
makeflags: "--jobs=4 --output-sync=target"
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "11"
|
||||
cuda-minor-version: "7"
|
||||
cuda-minor-version: "8"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'false'
|
||||
tag-suffix: '-cublas-cuda11-ffmpeg-core'
|
||||
@ -306,7 +306,7 @@ jobs:
|
||||
makeflags: "--jobs=4 --output-sync=target"
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "12"
|
||||
cuda-minor-version: "1"
|
||||
cuda-minor-version: "5"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'false'
|
||||
tag-suffix: '-cublas-cuda12-ffmpeg-core'
|
||||
|
||||
4
.github/workflows/image_build.yml
vendored
4
.github/workflows/image_build.yml
vendored
@ -19,11 +19,11 @@ on:
|
||||
type: string
|
||||
cuda-major-version:
|
||||
description: 'CUDA major version'
|
||||
default: "11"
|
||||
default: "12"
|
||||
type: string
|
||||
cuda-minor-version:
|
||||
description: 'CUDA minor version'
|
||||
default: "7"
|
||||
default: "5"
|
||||
type: string
|
||||
platforms:
|
||||
description: 'Platforms'
|
||||
|
||||
2
.github/workflows/release.yaml
vendored
2
.github/workflows/release.yaml
vendored
@ -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: 12-4
|
||||
CUDA_VERSION: 12-5
|
||||
- name: Cache grpc
|
||||
id: cache-grpc
|
||||
uses: actions/cache@v4
|
||||
|
||||
@ -33,7 +33,7 @@ RUN curl -L -s https://go.dev/dl/go${GO_VERSION}.linux-${TARGETARCH}.tar.gz | ta
|
||||
ENV PATH $PATH:/root/go/bin:/usr/local/go/bin
|
||||
|
||||
# Install grpc compilers
|
||||
RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.1 && \
|
||||
RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2 && \
|
||||
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
|
||||
|
||||
COPY --chmod=644 custom-ca-certs/* /usr/local/share/ca-certificates/
|
||||
@ -98,8 +98,8 @@ RUN pip install --user grpcio-tools
|
||||
FROM requirements-${IMAGE_TYPE} AS requirements-drivers
|
||||
|
||||
ARG BUILD_TYPE
|
||||
ARG CUDA_MAJOR_VERSION=11
|
||||
ARG CUDA_MINOR_VERSION=8
|
||||
ARG CUDA_MAJOR_VERSION=12
|
||||
ARG CUDA_MINOR_VERSION=5
|
||||
|
||||
ENV BUILD_TYPE=${BUILD_TYPE}
|
||||
|
||||
@ -292,7 +292,7 @@ ENV REBUILD=false
|
||||
ENV HEALTHCHECK_ENDPOINT=http://localhost:8080/readyz
|
||||
ENV MAKEFLAGS=${MAKEFLAGS}
|
||||
|
||||
ARG CUDA_MAJOR_VERSION=11
|
||||
ARG CUDA_MAJOR_VERSION=12
|
||||
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
|
||||
ENV NVIDIA_REQUIRE_CUDA="cuda>=${CUDA_MAJOR_VERSION}.0"
|
||||
ENV NVIDIA_VISIBLE_DEVICES=all
|
||||
|
||||
13
Makefile
13
Makefile
@ -400,7 +400,7 @@ 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=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=11 --build-arg CUDA_MINOR_VERSION=7 --build-arg FFMPEG=true -t localai-tests .
|
||||
docker build --build-arg GRPC_BACKENDS="$(GRPC_BACKENDS)" --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=5 --build-arg FFMPEG=true -t localai-tests .
|
||||
|
||||
run-e2e-image:
|
||||
ls -liah $(abspath ./tests/e2e-fixtures)
|
||||
@ -810,6 +810,17 @@ docker:
|
||||
--build-arg BUILD_TYPE=$(BUILD_TYPE) \
|
||||
-t $(DOCKER_IMAGE) .
|
||||
|
||||
docker-cuda11:
|
||||
docker build \
|
||||
--build-arg CUDA_MAJOR_VERSION=11 \
|
||||
--build-arg CUDA_MINOR_VERSION=8 \
|
||||
--build-arg BASE_IMAGE=$(BASE_IMAGE) \
|
||||
--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
|
||||
--build-arg GO_TAGS="$(GO_TAGS)" \
|
||||
--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
|
||||
--build-arg BUILD_TYPE=$(BUILD_TYPE) \
|
||||
-t $(DOCKER_IMAGE)-cuda11 .
|
||||
|
||||
docker-aio:
|
||||
@echo "Building AIO image with base $(BASE_IMAGE) as $(DOCKER_AIO_IMAGE)"
|
||||
docker build \
|
||||
|
||||
Loading…
Reference in New Issue
Block a user