Update main 030925 #6
Merged
Conversation
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
* Fixed tests. * PR fix suggestions. --------- Co-authored-by: Aku Rouhe <akurouhe@amd.com>
* all updates * Add helm to rag app (#359) * add helm chart * add basic dockerfile * add code and data via configmap * get rid of dockerfile * move app files inside helm * add configmaps for knowledge-base and chroma folder * update readme * readme formatting * readme formatting updates * custom release name in readme * parametrize services hostnames * cleanup configmaps and volumemounts * update infinity and vllm ports to 80 * move readme inside helm * add cleanup section * merge configmaps; parametrize name * image pull policy to always * add exponential backof * add support for v1 completions * update readme * main.py updated with new features to observe Rag pipeline functionality * update default infinity model name * improve naming in infinity readme and override * improve readme for custom deployments * small readme update * overrides naming adjustments * adjust defaults to match workloads defaults * clean up yamls * remove explicit vector size; add error handling instead * latest updates * update readme --------- Co-authored-by: Vladyslav Sokol <vladyslav.sokol@amd.com>
* Add MLFlow dev center overlays and config auto-pvc annotations * Fix resource requirements and metadata
* Enhance liveness and readiness probes with HTTP GET paths in values.yaml * Update liveness and readiness probes to use /api/status path * Update startup probe configuration * Refactor and simplify probes using tpl templating --------- Co-authored-by: Mark van Heeswijk <mark.vanheeswijk@amd.com>
* Add DeepSeek V3.1 model configuration * Add config DeepSeek V3.1 download to s3 * Add served_model_name
* Update port-forwards to use services rather than deployments Co-authored-by: markvanheeswijk <4988912+markvanheeswijk@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: markvanheeswijk <4988912+markvanheeswijk@users.noreply.github.com>
…torage control (#413) * Enable VSCode settings persistence on PVC Co-authored-by: markvanheeswijk <4988912+markvanheeswijk@users.noreply.github.com> * Add documentation and example override for VSCode persistence Co-authored-by: markvanheeswijk <4988912+markvanheeswijk@users.noreply.github.com> * Fix PVC annotation coupling with persistent storage setting - Move PVC annotations from static values.yaml to conditional template logic - PVC annotations now only applied when persistent_storage.enabled=true - Resolves issue where disabling persistent storage still created PVCs - Add documentation comments explaining persistent storage behavior - Maintains backward compatibility with custom annotations Co-authored-by: markvanheeswijk <4988912+markvanheeswijk@users.noreply.github.com> * Move PVC annotations to values.yaml with conditional template inclusion Co-authored-by: markvanheeswijk <4988912+markvanheeswijk@users.noreply.github.com> * Remove unnecesary override * Disable persistent_storage by default * Update workloads/dev-workspace-vscode/helm/README.md --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: markvanheeswijk <4988912+markvanheeswijk@users.noreply.github.com> Co-authored-by: Mark van Heeswijk <mark.vanheeswijk@amd.com> Co-authored-by: aivanni <4340981+aivanni@users.noreply.github.com>
…(#416) * Fix missing -X POST flags in curl commands for chat completions APIs --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
… with complete override support (#423) * Implement explicit served_model_name parameter for vLLM inference API Co-authored-by: markvanheeswijk <4988912+markvanheeswijk@users.noreply.github.com> * Add served_model_name parameter to all model override files Co-authored-by: markvanheeswijk <4988912+markvanheeswijk@users.noreply.github.com> * Minor tweaks to values.yaml documentation and hints * Minor fixes for consistency --------- Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: markvanheeswijk <4988912+markvanheeswijk@users.noreply.github.com> Co-authored-by: Mark van Heeswijk <mark.vanheeswijk@amd.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Add installation script for S3 storage clients and update entrypoint configuration override * rename s3 config * Add S3 extensions to default values (#395) * Remove unnecessary override --------- Co-authored-by: Aku Rouhe <akurouhe@amd.com> Co-authored-by: Mark van Heeswijk <mark.vanheeswijk@amd.com>
Gastron
approved these changes
Sep 3, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
No description provided.