fix: track Kompress model repo across headroom-ai 0.24.0 rename#5
Merged
Conversation
headroom-ai 0.24.0 renamed the default Kompress weights repo (chopratejas/kompress-base -> chopratejas/kompress-v2-base). worker.py hardcoded the old name in its HF-cache pre-check, which decides whether to force HF_HUB_OFFLINE. Against 0.24.0 that broke two ways: a host with only the old model cached would be forced offline against a model that version no longer loads (cold load fails), and once the new model was cached the offline optimization silently stopped engaging. Resolve the repo from the installed headroom-ai version instead of hardcoding it, so a single worker.py supports both 0.23.x and 0.24.x — including hosts mid-upgrade. The version is read via importlib.metadata, never by importing headroom, so the set-offline-env-before-importing- transformers ordering this module relies on is preserved. When the model the installed version loads isn't cached we stay online (safe) rather than forcing offline. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: Luke Kosewski <lkosewsk@tailscale.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
headroom-ai 0.24.0 renamed the default Kompress weights repo (chopratejas/kompress-base -> chopratejas/kompress-v2-base). worker.py hardcoded the old name in its HF-cache pre-check, which decides whether to force HF_HUB_OFFLINE. Against 0.24.0 that broke two ways: a host with only the old model cached would be forced offline against a model that version no longer loads (cold load fails), and once the new model was cached the offline optimization silently stopped engaging.
Resolve the repo from the installed headroom-ai version instead of hardcoding it, so a single worker.py supports both 0.23.x and 0.24.x — including hosts mid-upgrade. The version is read via importlib.metadata, never by importing headroom, so the set-offline-env-before-importing- transformers ordering this module relies on is preserved. When the model the installed version loads isn't cached we stay online (safe) rather than forcing offline.