Roland Tannous 4eabc74f34 feat: subprocess-based inference for transformers version switching ... Inference now runs in a persistent subprocess, solving the same transformers version-switching problem that was fixed for training. The subprocess stays alive between requests (model in GPU memory) and is only restarted when switching transformers versions. New files: - core/inference/worker.py: subprocess entry point with command loop - core/inference/orchestrator.py: parent-side proxy with same API Modified: - core/inference/__init__.py: exports orchestrator as default backend - routes/inference.py: removed in-process ensure_transformers_version()		2026-03-05 17:47:57 +00:00
..
data_recipe	refactor(data-recipe): centralize json+stage constants, tighten parser/errors, sync seed ui	2026-02-26 14:06:53 +01:00
export	Move llama.cpp clone/build from in-tree to ~/.unsloth/llama.cpp	2026-03-02 04:04:41 +00:00
inference	feat: subprocess-based inference for transformers version switching	2026-03-05 17:47:57 +00:00
training	feat: subprocess-based training for transformers version switching	2026-03-05 15:40:32 +00:00
__init__.py	fix: lazy imports in core/__init__ to prevent subprocess importing ML libs early	2026-03-05 16:56:45 +00:00