llama-cpp-vulkan-qwen38-flash-next-mtp (pr144-b8e89f2-ondevspec)

Published 2026-09-01 18:13:58 +00:00 by dan

Pull the image from the command line:

docker pull forge.coffee-anon.com/dan/llama-cpp-vulkan-qwen38-flash-next-mtp:pr144-b8e89f2-ondevspec

Digest

sha256:9f58ae21f50b3c72323da61845f1b6a58ee374af84e5168320a3d744aad66dd3

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

KIWI 10.3.0

RUN /bin/sh -c microdnf -y --nodocs --setopt=install_weak_deps=0 install bash ca-certificates libatomic libstdc++ libgcc libibverbs 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/ggml-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"]

ARG LLAMA_CPP_COMMIT=b8e89f2f365dbe4ec04915ad576a041a4706dffd

ARG ONDEVCKPT_PATCH_SHA256=69c08cdabc6c373eb8d733fc8662a7e708b1b012f7510ef3772fd325f0e14212

LABEL maintainer=citizendaniel

LABEL org.opencontainers.image.revision=b8e89f2f365dbe4ec04915ad576a041a4706dffd

LABEL org.opencontainers.image.source=https://github.com/unslothai/llama.cpp

LABEL llamacpp.pr=https://github.com/unslothai/llama.cpp/pull/144

LABEL llamacpp.patch.ondevckpt=https://github.com/JayToltTech/llama.cpp/pull/1

LABEL llamacpp.patch.ondevckpt.sha256=69c08cdabc6c373eb8d733fc8662a7e708b1b012f7510ef3772fd325f0e14212

LABEL backend=vulkan-radv-qwen4exp-mtp

LABEL gpu.target=gfx1151

LABEL llamaswap.version=197

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

COPY /staging/usr/lib64/ /usr/lib64/ # buildkit

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

RUN |2 LLAMA_CPP_COMMIT=b8e89f2f365dbe4ec04915ad576a041a4706dffd ONDEVCKPT_PATCH_SHA256=69c08cdabc6c373eb8d733fc8662a7e708b1b012f7510ef3772fd325f0e14212 /bin/sh -c ldconfig && /usr/bin/llama-server --help >/tmp/llama-server-help.txt 2>&1 && grep -q "draft-mtp" /tmp/llama-server-help.txt && /usr/bin/llama-server --version && test -x /usr/bin/llama-swap && rm /tmp/llama-server-help.txt # buildkit

EXPOSE [8080/tcp]

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

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

Key	Value
backend	vulkan-radv-qwen4exp-mtp
gpu.target	gfx1151
io.buildah.version	1.43.2
license	MIT
llamacpp.patch.ondevckpt	https://github.com/JayToltTech/llama.cpp/pull/1
llamacpp.patch.ondevckpt.sha256	69c08cdabc6c373eb8d733fc8662a7e708b1b012f7510ef3772fd325f0e14212
llamacpp.pr	https://github.com/unslothai/llama.cpp/pull/144
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.revision	b8e89f2f365dbe4ec04915ad576a041a4706dffd
org.opencontainers.image.source	https://github.com/unslothai/llama.cpp
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