feat: add custom CA support and fix deprecated image tags#124
Merged
Conversation
Adds a new flag --ca-cert-configmap to the controller manager. If provided, the controller will mount the specified ConfigMap to the model-downloader init container and configure curl to use the CA certificate found within it. This enables model downloading in environments with SSL inspection or custom internal CAs. Signed-off-by: Christopher Maher <chris@mahercode.io>
This commit addresses two key issues: 1. Adds support for custom CA certificates via a new --ca-cert-configmap flag on the controller. This allows model downloads to work in environments with SSL inspection or private CAs. 2. Updates all references to the deprecated `ghcr.io/ggerganov/llama.cpp:server` image to the new upstream location `ghcr.io/ggml-org/llama.cpp:server`. Closes #122 Closes #123 Signed-off-by: Christopher Maher <chris@mahercode.io>
Defilan
force-pushed
the
feat/custom-ca-cert
branch
from
851c285 to
84dbceb
Compare
Merged
Closed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This PR addresses two critical issues for enterprise and production deployments:
--ca-cert-configmapflag to the controller. This enables users in air-gapped or corporate environments (with SSL inspection) to provide a custom CA bundle for the model downloader.llama.cppproject renamed their organization and reorganized tags. The old defaultghcr.io/ggerganov/llama.cpp:serveris now deprecated/missing. This PR updates all references toghcr.io/ggml-org/llama.cpp:server.Closes #122
Closes #123
Changes
--ca-cert-configmapflag and logic to mount the ConfigMap to init containers.ghcr.io/ggml-org/llama.cpp:server.Verification
model-downloadermounted it and exportedCURL_CA_BUNDLE.ghcr.io/ggml-org/llama.cpp:serverexists (via docs/search) and replaced all occurrences in the codebase.