unsloth/studio/backend/routes
Daniel Han 62d0ccba12 Per-load video cancel event, family-gated image picker, cond cache refusal
A cancelled video load could resume: begin_load cleared the shared cancel
event, and unload() drops _loading without waiting for the worker, so the
next load cleared the very object the cancelled worker was watching and its
multi-gigabyte pull ran on alongside the replacement until the token check
at the end. Each load now gets its own threading.Event, passed down through
_fetch_te_prequant and _predownload_base, so a cancelled worker stays
cancelled.

A cached repo with a model_index.json was advertised as text-to-image on the
trust rule alone, but validate_load_request also requires a detected image
family, so a trusted pipeline of an unsupported class produced a picker row
that deterministically 400s. The picker now applies both gates, mirroring the
video branch.

cond_cache_dir was accepted for sdxl and then ignored: only the DiT trainer
reads it, while the SDXL trainer builds a per-run in-memory latent cache, so
the promised cross-run reuse never happened. The route now refuses it with a
400 that names the families which do support it, checked against the resolved
family so an omitted model_family with an SDXL base is caught too.
2026-07-27 08:14:36 +00:00
..
data_recipe Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
.gitkeep root studio folder 2026-02-02 09:13:49 +00:00
__init__.py Merge branch 'main' of https://github.com/unslothai/unsloth into r6763 2026-07-27 07:15:43 +00:00
auth.py Studio: reject whitespace-only passwords (#7341) 2026-07-23 00:44:37 -07:00
chat_history.py Studio: add Deep Research (#7219) 2026-07-26 23:36:02 -07:00
datasets.py Studio: add configurable model download location (#7274) 2026-07-23 01:34:38 -07:00
export.py Studio: offer the latest transformers release for brand-new architectures (#7056) 2026-07-15 05:25:26 -07:00
inference.py Guard old diffusers, stream video exports, record conditioned recipes 2026-07-27 07:41:19 +00:00
llama.py Studio: add local speech-to-text dictation engine (#7095) 2026-07-23 01:39:03 -07:00
mcp_servers.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
models.py Per-load video cancel event, family-gated image picker, cond cache refusal 2026-07-27 08:14:36 +00:00
preview.py Studio: opt-in OpenAI /v1 model auto-switch and idle keep-warm (#6392) 2026-07-01 06:42:23 -07:00
prompts.py Studio: clean-room compact RAG (knowledge bases, hybrid search, fast indexing) (#5910) 2026-06-09 21:17:04 -07:00
providers.py fix(studio): persist connection model selections for remote clients (#7298) 2026-07-23 19:11:50 -07:00
rag.py Add drag and drop sources to the create project dialog (#7441) 2026-07-25 23:54:48 -07:00
research_runs.py Studio: add Deep Research (#7219) 2026-07-26 23:36:02 -07:00
settings.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
training.py Per-load video cancel event, family-gated image picker, cond cache refusal 2026-07-27 08:14:36 +00:00
training_history.py Studio: require signed capability tokens for /p preview links (#6666) 2026-06-25 21:40:48 -07:00
training_vram.py Add Intel XPU support to Unsloth Studio (#4724) 2026-07-24 02:22:07 -03:00
video.py Guard old diffusers, stream video exports, record conditioned recipes 2026-07-27 07:41:19 +00:00
whisper.py Studio: add local speech-to-text dictation engine (#7095) 2026-07-23 01:39:03 -07:00