unsloth/studio/backend/core/inference
Daniel Han 973532786a Fix studio crash on Mac by deferring unsloth_zoo import
Move `from unsloth_zoo.rl_environments import check_signal_escape_patterns`
from module-level to inside `_check_code_safety()` and wrap it in a
try/except for NotImplementedError. The top-level import triggers
`unsloth_zoo.__init__` which calls `get_device_type()` at module scope,
raising NotImplementedError on Apple Silicon. On Mac the safety check
gracefully skips since unsloth_zoo is unavailable, while GGUF inference
via llama.cpp continues to work.
2026-03-18 15:58:21 +00:00
..
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
audio_codecs.py studio: per-model inference defaults, GGUF slider fix, reasoning toggle (#4325) 2026-03-16 06:37:55 -07:00
defaults.py studio: web search, KV cache dtype, training progress, inference fixes 2026-03-17 00:30:01 -07:00
inference.py studio: improve onboarding UX, tooltips, and training defaults (#4355) 2026-03-17 07:46:07 -07:00
llama_cpp.py Fix tool call parsing, add tool outputs panel and UI improvements (#4416) 2026-03-18 08:28:02 -07:00
orchestrator.py feat(studio): infinite scroll for recommended models list (#4414) 2026-03-18 03:17:01 -07:00
tools.py Fix studio crash on Mac by deferring unsloth_zoo import 2026-03-18 15:58:21 +00:00
worker.py Combine studio setup fixes: frontend caching, venv isolation, Windows CPU support (#4413) 2026-03-18 03:52:25 -07:00