mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-08 07:18:31 -04:00
Adds an escape hatch for hardware-gated backends (e.g. ds4) where the model is too large for Docker build context. When BACKEND_BINARY points at a run.sh produced by 'make -C backend/cpp/<name> package', the suite skips docker image extraction and drives the binary directly. Signed-off-by: Ettore Di Giacinto <mudler@localai.io>