llama-cpp-vulkan-strixhalo-src (b7b85da9-dspark-fused)

Published 2026-08-03 19:37:58 +00:00 by dan

Pull the image from the command line:

docker pull forge.coffee-anon.com/dan/llama-cpp-vulkan-strixhalo-src:b7b85da9-dspark-fused

Digest

sha256:718071591e9c2166aca6faece003a03200b7ceeac5a939879f4faadc20f6158c

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"]

LABEL maintainer=citizendaniel

LABEL description=llama.cpp with MTP (PR #22673) + batch checkpoints (PR #19970) on Vulkan RADV

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

LABEL patch.pr.batch_checkpoints=https://github.com/ggml-org/llama.cpp/pull/19970

LABEL patch.purpose=A/B bench MTP speculative decoding on Qwen3.6-35B-A3B (hybrid SSM/MoE)

LABEL patch.removal=Revert to a stock build once PR #22673 + #19970 land upstream

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 /staging/usr/share/llama.cpp /usr/share/llama.cpp # buildkit

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

RUN /bin/sh -c ldconfig # buildkit

RUN /bin/sh -c echo "=== MTP + batch-checkpoints overlay verification ===" && ls -la /usr/bin/llama-server && ls -la /usr/bin/llama-swap && ls -la /usr/lib64/libllama* 2>/dev/null && ls -la /usr/lib64/libggml* 2>/dev/null && echo "=== Binary check ===" && llama-server --version 2>&1 || true && llama-swap --help 2>&1 | head -3 || true # buildkit

Key	Value
description	llama.cpp with MTP (PR #22673) + batch checkpoints (PR #19970) on Vulkan RADV
io.buildah.version	1.43.2
license	MIT
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
patch.pr.batch_checkpoints	https://github.com/ggml-org/llama.cpp/pull/19970
patch.pr.mtp	https://github.com/ggml-org/llama.cpp/pull/22673
patch.purpose	A/B bench MTP speculative decoding on Qwen3.6-35B-A3B (hybrid SSM/MoE)
patch.removal	Revert to a stock build once PR #22673 + #19970 land upstream
vendor	Fedora Project
version	43

Details

Container

2026-08-03 19:37:58 +00:00

OCI / Docker

linux/amd64

MIT

Project website

639 MiB

Versions (1) View all

b7b85da9-dspark-fused

2026-08-03

llama-cpp-vulkan-strixhalo-src (b7b85da9-dspark-fused)

Installation

Image layers

Labels