feat: add llamacpp Docker image - #2
Merged
Merged
Conversation
Based on ghcr.io/ggml-org/llama.cpp:server-cuda with dstack runner prerequisites (openssh-server, sudo, dstack user). Includes MTP and Jinja autoparser support from the official llama.cpp image.
megheaiulian
force-pushed
the
add-llamacpp-image
branch
from
May 26, 2026 11:20
1063f3a to
4dfa43a
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds a Docker image based on
ghcr.io/ggml-org/llama.cpp:server-cudawith dstack runner prerequisites.Changes
images/llamacpp/Dockerfile— layers openssh-server, sudo, dstack user on top of the official llama.cpp server-cuda imageTag
ghcr.io/plumelo/dstack-images:llamacpp-latestWhy
The official llama.cpp image is minimal (no SSH, no sudo, no dstack user). This image pre-installs what dstack needs so pods start without the 2-4 minute apt-get delay.
Unlike the previous llama-mtp image that built llama.cpp from source, this one simply layers on top of the official image — no cmake, no CUDA build step, no source clone.