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): split recipe backend routes for readability (seed/validate/jobs)	2026-02-26 14:05:32 +01:00
.gitkeep	root studio folder	2026-02-02 09:13:49 +00:00
__init__.py	merge nightly	2026-02-15 14:52:07 +01:00
auth.py	fix: rollback auth.db user row if token generation fails during setup	2026-02-13 10:11:07 +00:00
datasets.py	feat: parallel URL image probe with time estimate and progress reporting	2026-03-04 23:40:38 +00:00
export.py	Auto-switch transformers version (5.1.0/4.57.1) for Ministral-3, GLM-4.7-Flash, Qwen3-30B-A3B models with LoRA adapter resolution	2026-02-22 18:29:40 +00:00
inference.py	feat: subprocess-based inference for transformers version switching	2026-03-05 17:47:57 +00:00
models.py	fix: remove in-process version switching from models routes	2026-03-05 16:22:32 +00:00
training.py	fix: handle None job_id before first training run	2026-03-05 16:59:37 +00:00