unsloth/studio/backend/core
Unsloth 571a0ef35f Merge main: rewire deep research send to the on-device auto-load
The deep research path from main called the removed autoLoadSmallestModel;
it now uses autoLoadOnDeviceModel with the same no-download guarantee and
duplicate-toast suppression as the plain send path. Test conflict resolved
by keeping both the autoload contract section and main's Vulkan picker
test.
2026-07-27 05:29:43 -07:00
..
data_recipe Studio: add configurable model download location (#7274) 2026-07-23 01:34:38 -07:00
export Pin utf-8 on shipping-code text I/O instead of the operator locale (#7486) 2026-07-27 02:14:20 -07:00
inference Merge main: rewire deep research send to the on-device auto-load 2026-07-27 05:29:43 -07:00
rag Pin utf-8 on shipping-code text I/O instead of the operator locale (#7486) 2026-07-27 02:14:20 -07:00
training AMD: CI coverage for recent fixes, plus three wrong gfx ids (#7431) 2026-07-25 18:58:02 -05:00
__init__.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
_torchao_stub.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
import_guards.py Studio: self-heal unsloth namespace shadows; clearer failed-load messages (#6532) 2026-06-21 22:43:31 -07:00
research_runs.py Studio: add Deep Research (#7219) 2026-07-26 23:36:02 -07:00
tool_healing.py Studio: Inkling support fixes (#7153) 2026-07-15 11:22:38 -07:00