Skip to content

feat(nvidia-gpu): bump images to cuda 12.8 #6239

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 9, 2025
Merged

feat(nvidia-gpu): bump images to cuda 12.8 #6239

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
38 changes: 19 additions & 19 deletions .github/workflows/backend.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,7 @@ jobs:
context: "./backend"
- build-type: 'l4t'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-l4t-diffusers'
Expand Down Expand Up @@ -175,7 +175,7 @@ jobs:
# CUDA 12 builds
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-rerankers'
Expand All @@ -187,7 +187,7 @@ jobs:
context: "./backend"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-llama-cpp'
Expand All @@ -199,7 +199,7 @@ jobs:
context: "./"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-vllm'
Expand All @@ -211,7 +211,7 @@ jobs:
context: "./backend"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-transformers'
Expand All @@ -223,7 +223,7 @@ jobs:
context: "./backend"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-diffusers'
Expand All @@ -236,7 +236,7 @@ jobs:
# CUDA 12 additional backends
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-kokoro'
Expand All @@ -248,7 +248,7 @@ jobs:
context: "./backend"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-faster-whisper'
Expand All @@ -260,7 +260,7 @@ jobs:
context: "./backend"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-coqui'
Expand All @@ -272,7 +272,7 @@ jobs:
context: "./backend"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-bark'
Expand All @@ -284,7 +284,7 @@ jobs:
context: "./backend"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-chatterbox'
Expand Down Expand Up @@ -566,7 +566,7 @@ jobs:
context: "./"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/arm64'
skip-drivers: 'true'
tag-latest: 'auto'
Expand Down Expand Up @@ -603,7 +603,7 @@ jobs:
context: "./"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-stablediffusion-ggml'
Expand Down Expand Up @@ -663,7 +663,7 @@ jobs:
context: "./"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/arm64'
skip-drivers: 'true'
tag-latest: 'auto'
Expand All @@ -688,7 +688,7 @@ jobs:
context: "./"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-whisper'
Expand Down Expand Up @@ -748,7 +748,7 @@ jobs:
context: "./"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/arm64'
skip-drivers: 'true'
tag-latest: 'auto'
Expand Down Expand Up @@ -824,7 +824,7 @@ jobs:
context: "./backend"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-rfdetr'
Expand Down Expand Up @@ -860,7 +860,7 @@ jobs:
context: "./backend"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/arm64'
skip-drivers: 'true'
tag-latest: 'auto'
Expand All @@ -885,7 +885,7 @@ jobs:
context: "./backend"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-exllama2'
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/image-pr.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ jobs:
include:
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'false'
tag-suffix: '-gpu-nvidia-cuda-12'
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/image.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,7 +91,7 @@ jobs:
aio: "-aio-gpu-nvidia-cuda-11"
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12'
Expand Down Expand Up @@ -144,7 +144,7 @@ jobs:
include:
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
cuda-minor-version: "8"
platforms: 'linux/arm64'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64'
Expand Down
2 changes: 1 addition & 1 deletion Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ FROM requirements AS requirements-drivers

ARG BUILD_TYPE
ARG CUDA_MAJOR_VERSION=12
ARG CUDA_MINOR_VERSION=0
ARG CUDA_MINOR_VERSION=8
ARG SKIP_DRIVERS=false
ARG TARGETARCH
ARG TARGETVARIANT
Expand Down
2 changes: 1 addition & 1 deletion Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,7 +170,7 @@ 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 $(TEST_DIR)/ggllm-test-model.bin
docker build --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=0 -t localai-tests .
docker build --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=8 -t localai-tests .

run-e2e-image:
ls -liah $(abspath ./tests/e2e-fixtures)
Expand Down
2 changes: 1 addition & 1 deletion backend/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,7 +111,7 @@ docker build -f backend/Dockerfile.python \
--build-arg BACKEND=transformers \
--build-arg BUILD_TYPE=cublas12 \
--build-arg CUDA_MAJOR_VERSION=12 \
--build-arg CUDA_MINOR_VERSION=0 \
--build-arg CUDA_MINOR_VERSION=8 \
-t localai-backend-transformers .

# Build Go backend
Expand Down
Loading