nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

docker : add OCI image labels for version and build date (#21653)

Browse Source 
* docker: add OCI image labels to all published images

* docker: propagate OCI labels as manifest and index annotations

* docker: drop hardcoded org URL and revert accidental intel version bump

The OCI image url and source are now driven by build args with a sensible default. The workflow passes the actual repository url so fork builds get labels pointing at the fork instead of upstream. Also restores the IGC, compute runtime, and IGDGMM versions in the intel Dockerfile labeled stage which I accidentally bumped in the first commit.

* docker: add skip_s390x workflow_dispatch input for fast test runs

Lets maintainers and PR authors trigger the docker workflow without the s390x build target, which depends on the IBM Z runner and is by far the slowest job in the matrix. The flag filters the s390x row out of the build matrix before merge_matrix is derived, so the merge job sees a consistent shape too.

Signed-off-by: Samaresh Kumar Singh <ssam3003@gmail.com>

---------

Signed-off-by: Samaresh Kumar Singh <ssam3003@gmail.com>
This commit is contained in:
SamareshSingh
2026-05-18 15:14:45 -05:00
committed by GitHub
parent 45b455e66f
commit 5cbaa5e69e
11 changed files with 242 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
.devops/cann.Dockerfile
View File

@@ -5,6 +5,9 @@
# Define the CANN base image for easier version updates later
ARG CHIP_TYPE=910b
ARG CANN_BASE_IMAGE=quay.io/ascend/cann:8.5.0-${CHIP_TYPE}-openeuler24.03-py3.11
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
# ==============================================================================
# BUILD STAGE
@@ -67,6 +70,19 @@ RUN mkdir -p /app/full && \
# ==============================================================================
FROM ${CANN_BASE_IMAGE} AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
# -- Install runtime dependencies --
RUN yum install -y libgomp curl && \
yum clean all && \

16
.devops/cpu.Dockerfile
View File

@@ -1,4 +1,7 @@
ARG UBUNTU_VERSION=24.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
FROM ubuntu:$UBUNTU_VERSION AS build
@@ -35,6 +38,19 @@ RUN mkdir -p /app/full \
## Base image
FROM ubuntu:$UBUNTU_VERSION AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 curl \
&& apt autoremove -y \

17
.devops/cuda.Dockerfile
View File

@@ -6,6 +6,10 @@ ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VER
ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
# CUDA architecture to build for (defaults to all supported archs)
@@ -40,6 +44,19 @@ RUN mkdir -p /app/full \
## Base image
FROM ${BASE_CUDA_RUN_CONTAINER} AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 curl \
&& apt autoremove -y \

16
.devops/intel.Dockerfile
View File

@@ -1,4 +1,7 @@
ARG ONEAPI_VERSION=2025.3.3-0-devel-ubuntu24.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
## Build Image
@@ -40,6 +43,19 @@ RUN mkdir -p /app/full \
FROM intel/deep-learning-essentials:$ONEAPI_VERSION AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
ARG IGC_VERSION=v2.20.5
ARG IGC_VERSION_FULL=2_2.20.5+19972
ARG COMPUTE_RUNTIME_VERSION=25.40.35563.10

17
.devops/llama-cli-cann.Dockerfile
View File

@@ -1,4 +1,7 @@
ARG ASCEND_VERSION=8.5.0-910b-openeuler22.03-py3.10
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
FROM ascendai/cann:$ASCEND_VERSION AS build
@@ -28,6 +31,20 @@ RUN echo "Building with static libs" && \
# TODO: use image with NNRT
FROM ascendai/cann:$ASCEND_VERSION AS runtime
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
COPY --from=build /app/build/bin/llama-cli /app/build/bin/llama-completion /
ENV LC_ALL=C.utf8

17
.devops/musa.Dockerfile
View File

@@ -6,6 +6,10 @@ ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_V
ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
FROM ${BASE_MUSA_DEV_CONTAINER} AS build
# MUSA architecture to build for (defaults to all supported archs)
@@ -45,6 +49,19 @@ RUN mkdir -p /app/full \
## Base image
FROM ${BASE_MUSA_RUN_CONTAINER} AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 curl \
&& apt autoremove -y \

16
.devops/openvino.Dockerfile
View File

@@ -18,6 +18,10 @@ ARG LIBZE1_VERSION=1.27.0-1~24.04~ppa2
ARG http_proxy=
ARG https_proxy=
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
## Build Image
FROM ubuntu:${UBUNTU_VERSION} AS build
@@ -88,6 +92,18 @@ FROM ubuntu:${UBUNTU_VERSION} AS base
# Pass proxy args to runtime stage
ARG http_proxy
ARG https_proxy
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 libtbb12 curl wget ocl-icd-libopencl1 \

17
.devops/rocm.Dockerfile
View File

@@ -7,6 +7,10 @@ ARG AMDGPU_VERSION=7.2.1
# Target the ROCm build image
ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
### Build image
FROM ${BASE_ROCM_DEV_CONTAINER} AS build
@@ -57,6 +61,19 @@ RUN mkdir -p /app/full \
## Base image
FROM ${BASE_ROCM_DEV_CONTAINER} AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 curl \
&& apt autoremove -y \

16
.devops/s390x.Dockerfile
View File

@@ -1,5 +1,8 @@
ARG GCC_VERSION=15.2.0
ARG UBUNTU_VERSION=24.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
### Build Llama.cpp stage
FROM gcc:${GCC_VERSION} AS build
@@ -52,6 +55,19 @@ COPY --from=build /opt/llama.cpp/gguf-py /llama.cpp/gguf-py
### Base image
FROM ubuntu:${UBUNTU_VERSION} AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
apt update -y && \

16
.devops/vulkan.Dockerfile
View File

@@ -1,4 +1,7 @@
ARG UBUNTU_VERSION=26.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
FROM ubuntu:$UBUNTU_VERSION AS build
@@ -31,6 +34,19 @@ RUN mkdir -p /app/full \
## Base image
FROM ubuntu:$UBUNTU_VERSION AS base
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.version=$APP_VERSION \
org.opencontainers.image.revision=$APP_REVISION \
org.opencontainers.image.title="llama.cpp" \
org.opencontainers.image.description="LLM inference in C/C++" \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 curl libvulkan1 mesa-vulkan-drivers \
libglvnd0 libgl1 libglx0 libegl1 libgles2 \