Skip to content

v4.47.1

Choose a tag to compare

View all tags
@github-actions github-actions released this 19 Sep 11:49
v4.47.1
848b0fa
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Fixed

  • (model-serving) Every preset served from a model image sets USER, LOGNAME and TORCHINDUCTOR_CACHE_DIR — the predictor runs as the modelcar uid 1010, which llm-d-cuda v0.8.0's passwd does not know, and vLLM's import died in torch's inductor cache-dir lookup on every new preset (#591) in #604 by @teemow

Full Changelog: v4.47.0...v4.47.1

Assets 2
Loading