Skip to content

fix(ci): better handling of latest images for backends #5735

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
Jun 27, 2025
Merged

fix(ci): better handling of latest images for backends #5735

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
45 changes: 1 addition & 44 deletions .github/workflows/backend.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,6 @@ jobs:
runs-on: ${{ matrix.runs-on }}
base-image: ${{ matrix.base-image }}
backend: ${{ matrix.backend }}
latest-image: ${{ matrix.latest-image }}
dockerfile: $${ matrix.dockerfile }}
context: $${ matrix.context }}
secrets:
Expand All @@ -49,7 +48,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "rerankers"
latest-image: 'latest-gpu-nvidia-cuda-11-rerankers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -61,7 +59,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "vllm"
latest-image: 'latest-gpu-nvidia-cuda-11-vllm'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -73,7 +70,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "transformers"
latest-image: 'latest-gpu-nvidia-cuda-11-transformers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -85,7 +81,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "diffusers"
latest-image: 'latest-gpu-nvidia-cuda-11-diffusers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# CUDA 11 additional backends
Expand All @@ -98,7 +93,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "kokoro"
latest-image: 'latest-gpu-nvidia-cuda-11-kokoro'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -110,7 +104,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "faster-whisper"
latest-image: 'latest-gpu-nvidia-cuda-11-faster-whisper'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -122,7 +115,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "coqui"
latest-image: 'latest-gpu-nvidia-cuda-11-coqui'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -134,7 +126,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "bark"
latest-image: 'latest-gpu-nvidia-cuda-11-bark'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -146,7 +137,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "chatterbox"
latest-image: 'latest-gpu-nvidia-cuda-11-chatterbox'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# CUDA 12 builds
Expand All @@ -159,7 +149,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "rerankers"
latest-image: 'latest-gpu-nvidia-cuda-12-rerankers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -171,7 +160,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "vllm"
latest-image: 'latest-gpu-nvidia-cuda-12-vllm'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -183,7 +171,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "transformers"
latest-image: 'latest-gpu-nvidia-cuda-12-transformers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -194,8 +181,7 @@ jobs:
tag-suffix: '-gpu-nvidia-cuda-12-diffusers'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "diffusers"
latest-image: 'latest-gpu-nvidia-cuda-12-diffusers'
backend: "diffusers"
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# CUDA 12 additional backends
Expand All @@ -208,7 +194,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "kokoro"
latest-image: 'latest-gpu-nvidia-cuda-12-kokoro'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -220,7 +205,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "faster-whisper"
latest-image: 'latest-gpu-nvidia-cuda-12-faster-whisper'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -232,7 +216,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "coqui"
latest-image: 'latest-gpu-nvidia-cuda-12-coqui'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -244,7 +227,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "bark"
latest-image: 'latest-gpu-nvidia-cuda-12-bark'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'cublas'
Expand All @@ -256,7 +238,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "chatterbox"
latest-image: 'latest-gpu-nvidia-cuda-12-chatterbox'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# hipblas builds
Expand All @@ -269,7 +250,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "rerankers"
latest-image: 'latest-gpu-rocm-hipblas-rerankers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
Expand All @@ -281,7 +261,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "vllm"
latest-image: 'latest-gpu-rocm-hipblas-vllm'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
Expand All @@ -293,7 +272,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "transformers"
latest-image: 'latest-gpu-rocm-hipblas-transformers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
Expand All @@ -305,7 +283,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "diffusers"
latest-image: 'latest-gpu-rocm-hipblas-diffusers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# ROCm additional backends
Expand All @@ -318,7 +295,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "kokoro"
latest-image: 'latest-gpu-rocm-hipblas-kokoro'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
Expand All @@ -330,7 +306,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "faster-whisper"
latest-image: 'latest-gpu-rocm-hipblas-faster-whisper'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
Expand All @@ -342,7 +317,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "coqui"
latest-image: 'latest-gpu-rocm-hipblas-coqui'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'hipblas'
Expand All @@ -354,7 +328,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "rocm/dev-ubuntu-22.04:6.1"
backend: "bark"
latest-image: 'latest-gpu-rocm-hipblas-bark'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# sycl builds
Expand All @@ -367,7 +340,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "rerankers"
latest-image: 'latest-gpu-intel-sycl-f32-rerankers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
Expand All @@ -379,7 +351,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "rerankers"
latest-image: 'latest-gpu-intel-sycl-f16-rerankers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
Expand All @@ -391,7 +362,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "vllm"
latest-image: 'latest-gpu-intel-sycl-f32-vllm'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
Expand All @@ -403,7 +373,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "vllm"
latest-image: 'latest-gpu-intel-sycl-f16-vllm'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
Expand All @@ -415,7 +384,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "transformers"
latest-image: 'latest-gpu-intel-sycl-f32-transformers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
Expand All @@ -427,7 +395,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "transformers"
latest-image: 'latest-gpu-intel-sycl-f16-transformers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
Expand All @@ -439,7 +406,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "diffusers"
latest-image: 'latest-gpu-intel-sycl-f32-diffusers'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# SYCL additional backends
Expand All @@ -452,7 +418,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "kokoro"
latest-image: 'latest-gpu-intel-sycl-f32-kokoro'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
Expand All @@ -464,7 +429,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "kokoro"
latest-image: 'latest-gpu-intel-sycl-f16-kokoro'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
Expand All @@ -476,7 +440,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "faster-whisper"
latest-image: 'latest-gpu-intel-sycl-f32-faster-whisper'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
Expand All @@ -488,7 +451,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "faster-whisper"
latest-image: 'latest-gpu-intel-sycl-f16-faster-whisper'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
Expand All @@ -500,7 +462,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "coqui"
latest-image: 'latest-gpu-intel-sycl-f32-coqui'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
Expand All @@ -512,7 +473,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "coqui"
latest-image: 'latest-gpu-intel-sycl-f16-coqui'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f32'
Expand All @@ -524,7 +484,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "bark"
latest-image: 'latest-gpu-intel-sycl-f32-bark'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
- build-type: 'sycl_f16'
Expand All @@ -536,7 +495,6 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
backend: "bark"
latest-image: 'latest-gpu-intel-sycl-f16-bark'
dockerfile: "./backend/Dockerfile.python"
context: "./backend"
# bark-cpp
Expand All @@ -549,6 +507,5 @@ jobs:
runs-on: 'ubuntu-latest'
base-image: "ubuntu:22.04"
backend: "bark"
latest-image: 'latest-bark-cpp'
dockerfile: "./backend/Dockerfile.go"
context: "./"
Loading
Loading