container-images/intel-gpu/Containerfile

FROM quay.io/fedora/fedora:43 as builder

COPY container-images/intel-gpu/oneAPI.repo /etc/yum.repos.d/
COPY container-images/scripts/build_llama.sh \
     container-images/scripts/lib.sh \
     /src/
WORKDIR /src/
RUN ./build_llama.sh intel-gpu

FROM quay.io/fedora/fedora:43

COPY --from=builder /tmp/install/ /usr/
COPY container-images/intel-gpu/oneAPI.repo /etc/yum.repos.d/

RUN dnf install -y --setopt=install_weak_deps=false \
      procps-ng intel-oneapi-runtime-mkl intel-oneapi-mkl-sycl-dft \
      intel-level-zero oneapi-level-zero intel-compute-runtime lspci \
      clinfo intel-oneapi-runtime-compilers intel-oneapi-mkl-core \
      intel-oneapi-mkl-sycl-blas intel-oneapi-runtime-dnnl gawk

COPY --chmod=755 container-images/intel-gpu/entrypoint.sh /usr/bin/

ENTRYPOINT ["/usr/bin/entrypoint.sh"]
Move images to fedora 43 Signed-off-by: Daniel J Walsh <dwalsh@redhat.com> 2025-10-12 08:56:52 +01:00			`FROM quay.io/fedora/fedora:43 as builder`
Add container image to support Intel ARC GPU Signed-off-by: Charro Gruver <cgruver@redhat.com> 2025-01-28 14:56:10 +00:00
install ramalama into containers from the current checkout Copy the current checkout of the ramalama repo into the containers and use that for installation. This removes the need for an extra checkout of the ramalama repo, and is consistent with the build process used by container_build.sh (which used a bind-mount rather than a copy). This keeps the version of ramalama in sync with the Containerfiles, and makes testing and CI more useful. Signed-off-by: Mike Bonnet <mikeb@redhat.com> 2025-06-18 11:00:30 -07:00			`COPY container-images/intel-gpu/oneAPI.repo /etc/yum.repos.d/`
remove whisper.cpp from all images Remove build and installation of whisper.cpp, and installation of ffmpeg. Rename build_llama_and_whisper.sh to build_llama.sh. Update Containerfiles to reference new script name. Consolidate management of cmake args in build_llama.sh. Remove references to whisper-server in various locations. Signed-off-by: Mike Bonnet <mikeb@redhat.com> 2026-01-27 15:58:45 -08:00			`COPY container-images/scripts/build_llama.sh \`
don't install ramalama (or anything python-related) into the inference engine images Since RAG has been moved into its own images, no python runtime environment is required in the inference engine images. Signed-off-by: Mike Bonnet <mikeb@redhat.com> 2025-11-18 06:41:14 -08:00			`container-images/scripts/lib.sh \`
			`/src/`
			`WORKDIR /src/`
remove whisper.cpp from all images Remove build and installation of whisper.cpp, and installation of ffmpeg. Rename build_llama_and_whisper.sh to build_llama.sh. Update Containerfiles to reference new script name. Consolidate management of cmake args in build_llama.sh. Remove references to whisper-server in various locations. Signed-off-by: Mike Bonnet <mikeb@redhat.com> 2026-01-27 15:58:45 -08:00			`RUN ./build_llama.sh intel-gpu`
Add container image to support Intel ARC GPU Signed-off-by: Charro Gruver <cgruver@redhat.com> 2025-01-28 14:56:10 +00:00
Move images to fedora 43 Signed-off-by: Daniel J Walsh <dwalsh@redhat.com> 2025-10-12 08:56:52 +01:00			`FROM quay.io/fedora/fedora:43`
Add container image to support Intel ARC GPU Signed-off-by: Charro Gruver <cgruver@redhat.com> 2025-01-28 14:56:10 +00:00
Add logic to build intel-gpu image to build_llama_and_whisper.sh Signed-off-by: Charro Gruver <cgruver@redhat.com> 2025-02-03 23:24:01 +00:00			`COPY --from=builder /tmp/install/ /usr/`
install ramalama into containers from the current checkout Copy the current checkout of the ramalama repo into the containers and use that for installation. This removes the need for an extra checkout of the ramalama repo, and is consistent with the build process used by container_build.sh (which used a bind-mount rather than a copy). This keeps the version of ramalama in sync with the Containerfiles, and makes testing and CI more useful. Signed-off-by: Mike Bonnet <mikeb@redhat.com> 2025-06-18 11:00:30 -07:00			`COPY container-images/intel-gpu/oneAPI.repo /etc/yum.repos.d/`
Add container image to support Intel ARC GPU Signed-off-by: Charro Gruver <cgruver@redhat.com> 2025-01-28 14:56:10 +00:00
don't install ramalama (or anything python-related) into the inference engine images Since RAG has been moved into its own images, no python runtime environment is required in the inference engine images. Signed-off-by: Mike Bonnet <mikeb@redhat.com> 2025-11-18 06:41:14 -08:00			`RUN dnf install -y --setopt=install_weak_deps=false \`
			`procps-ng intel-oneapi-runtime-mkl intel-oneapi-mkl-sycl-dft \`
update llama.cpp build flags Remove -DLLAMA_CURL=ON, llama.cpp no longer uses curl, the option is ignored. Remove unused curl devel dependencies. Remove unnecessary ARM_NEON defines. Disable building of tests and examples for llama.cpp and ggml, for efficiency. Signed-off-by: Mike Bonnet <mikeb@redhat.com> 2026-01-23 23:04:29 -08:00			`intel-level-zero oneapi-level-zero intel-compute-runtime lspci \`
Add gawk For awk binary Signed-off-by: Eric Curtin <ecurtin@redhat.com> 2025-04-23 12:33:41 +01:00			`clinfo intel-oneapi-runtime-compilers intel-oneapi-mkl-core \`
don't install ramalama (or anything python-related) into the inference engine images Since RAG has been moved into its own images, no python runtime environment is required in the inference engine images. Signed-off-by: Mike Bonnet <mikeb@redhat.com> 2025-11-18 06:41:14 -08:00			`intel-oneapi-mkl-sycl-blas intel-oneapi-runtime-dnnl gawk`
Add logic to build intel-gpu image to build_llama_and_whisper.sh Signed-off-by: Charro Gruver <cgruver@redhat.com> 2025-02-03 23:24:01 +00:00
don't install ramalama (or anything python-related) into the inference engine images Since RAG has been moved into its own images, no python runtime environment is required in the inference engine images. Signed-off-by: Mike Bonnet <mikeb@redhat.com> 2025-11-18 06:41:14 -08:00			`COPY --chmod=755 container-images/intel-gpu/entrypoint.sh /usr/bin/`
Fix handling of entrypoint for Intel Additional Fix from https://github.com/lirc572 Signed-off-by: Daniel J Walsh <dwalsh@redhat.com> 2025-03-31 11:06:24 -04:00
			`ENTRYPOINT ["/usr/bin/entrypoint.sh"]`