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
..
assets	Add GLM, Qwen3 MoE, TinyQwen3 MoE, and Ministral 3 VL model defaults and GLM train_on_responses_only mapping	2026-02-23 05:51:43 +00:00
auth	fix: replace datetime.UTC with timezone.utc for Python 3.9+ compatibility	2026-02-24 14:37:00 -06:00
core	feat: subprocess-based inference for transformers version switching	2026-03-05 17:47:57 +00:00
loggers	root studio folder	2026-02-02 09:13:49 +00:00
models	feat: parallel URL image probe with time estimate and progress reporting	2026-03-04 23:40:38 +00:00
requirements	feat: introduce single-env Python dependency management for streamlined compatibility	2026-02-24 07:45:40 +01:00
routes	feat: subprocess-based inference for transformers version switching	2026-03-05 17:47:57 +00:00
state	root studio folder	2026-02-02 09:13:49 +00:00
tests	added @needs_torch to test_cuda_oom	2026-02-11 16:12:37 +00:00
utils	fix: exclude bitsandbytes from module purge to prevent duplicate operator registration	2026-03-05 16:40:20 +00:00
colab.py	feat: Add simple 2-cell Colab notebook (no tunnel needed)	2026-02-17 04:57:30 -06:00
main.py	Merge nightly into feature/transformers-v5-support	2026-03-05 06:49:44 +00:00
run.py	fix path in run_server	2026-02-14 05:06:17 +00:00