dan

Repositories

1

Projects Packages

24

Public activity Starred repositories

llama-cpp-vulkan-mtp-batch-checkpoints (master-4f0e43da-draft-mtp-swap)

Published 2026-05-26 16:51:42 +00:00 by dan

Installation

Pull the image from the command line:

docker pull forge.coffee-anon.com/dan/llama-cpp-vulkan-mtp-batch-checkpoints:master-4f0e43da-draft-mtp-swap

Digest

sha256:4a2fffbfadc7330cd1bc490fa1a60902987483730d00e19aa587c08488b320c9

For more information on the Container registry, see the documentation.

Image layers

KIWI 10.3.0

RUN /bin/sh -c microdnf -y --nodocs --setopt=install_weak_deps=0 install bash ca-certificates libatomic libstdc++ libgcc vulkan-loader vulkan-loader-devel vulkaninfo mesa-vulkan-drivers radeontop procps-ng && microdnf clean all && rm -rf /var/cache/dnf/* # buildkit

COPY /usr/ /usr/ # buildkit

COPY /usr/local/ /usr/local/ # buildkit

COPY /opt/llama.cpp/build/bin/rpc-* /usr/local/bin/ # buildkit

RUN /bin/sh -c echo "/usr/local/lib" > /etc/ld.so.conf.d/local.conf && echo "/usr/local/lib64" >> /etc/ld.so.conf.d/local.conf && ldconfig && cp -n /usr/local/lib/libllama*.so* /usr/lib64/ 2>/dev/null || true && ldconfig # buildkit

COPY gguf-vram-estimator.py /usr/local/bin/gguf-vram-estimator.py # buildkit

RUN /bin/sh -c chmod +x /usr/local/bin/gguf-vram-estimator.py # buildkit

CMD ["/bin/bash"]

LABEL maintainer=citizendaniel

LABEL description=llama.cpp Vulkan-RADV mainline (post-#22673 + #23269) + llama-swap

LABEL backend=vulkan-radv-mainline-mtp

LABEL gpu.target=gfx1151

LABEL llamacpp.pr=https://github.com/ggml-org/llama.cpp/pull/22673

LABEL llamacpp.followup=https://github.com/ggml-org/llama.cpp/pull/23269

LABEL llamacpp.sha=4f0e43da6

LABEL llamaswap.version=197

COPY /staging/usr/bin/llama-* /usr/bin/ # buildkit

COPY /staging/usr/lib64/libllama* /usr/lib64/ # buildkit

COPY /staging/usr/lib64/libggml* /usr/lib64/ # buildkit

COPY /tmp/llama-swap /usr/bin/llama-swap # buildkit

RUN /bin/sh -c ldconfig # buildkit

RUN /bin/sh -c echo "=== Overlay verification ===" && ls -la /usr/bin/llama-server /usr/bin/llama-swap && /usr/bin/llama-server --version && /usr/bin/llama-swap --help 2>&1 | head -3 && echo "=== spec-type flag check ===" && /usr/bin/llama-server --help 2>&1 | grep -E "^\s*--spec-type" || (echo "FATAL: --spec-type flag missing — wrong llama.cpp SHA pinned"; exit 1) # buildkit

EXPOSE [8080/tcp]

ENTRYPOINT ["/usr/bin/llama-swap"]

CMD ["--config" "/config/llama-swap/config.yaml" "--listen" "0.0.0.0:8080"]

Labels

Key	Value
backend	vulkan-radv-mainline-mtp
description	llama.cpp Vulkan-RADV mainline (post-#22673 + #23269) + llama-swap
gpu.target	gfx1151
io.buildah.version	1.43.1
license	MIT
llamacpp.followup	https://github.com/ggml-org/llama.cpp/pull/23269
llamacpp.pr	https://github.com/ggml-org/llama.cpp/pull/22673
llamacpp.sha	4f0e43da6
llamaswap.version	197
maintainer	citizendaniel
name	fedora-minimal
org.opencontainers.image.license	MIT
org.opencontainers.image.licenses	MIT
org.opencontainers.image.name	fedora-minimal
org.opencontainers.image.title	fedora-minimal
org.opencontainers.image.url	https://fedoraproject.org/
org.opencontainers.image.vendor	Fedora Project
org.opencontainers.image.version	43
vendor	Fedora Project
version	43

Details

Container

2026-05-26 16:51:42 +00:00

4

OCI / Docker

linux/amd64

MIT

Project website

633 MiB

Versions (3) View all

master-d403f00e-draft-mtp-swap 2026-06-08

master-19e92c33-draft-mtp-swap 2026-05-29

master-4f0e43da-draft-mtp-swap 2026-05-26