The load tail re-ran the already-filtered speed_optims tuple through
.items() as if it were still the raw applied dict from apply_speed_optims.
An empty tuple short-circuited to {} so CPU test runs passed, but on a real
GPU at least channels_last engages, the tuple is truthy, and every load
failed with 'tuple' object has no attribute 'items'. Store the filtered
tuple directly and add a regression test that forces one optimisation to
engage.
The run detail route built DiffusionTrainingRunDetail(**rec) unguarded, so a
valid-JSON-but-wrong-shape record (hand-edited or an older schema) would 500
instead of reading as absent. Catch ValidationError and 404, matching how the
list route skips malformed records.
tokenizer/chat_template.jinja ships as its own file in the LTX-2 and
HunyuanVideo-1.5 repos and apply_chat_template reads it at generation
time, so a scoped snapshot without it loads fine and then crashes the
first generation.
A dual-DiT pipeline (Ideogram 4's unconditional tower) placed its second
denoiser resident under the group tier, which defeats the tier since the
pair rarely fits where one alone did not. Stream transformer_2 and
unconditional_transformer alongside the transformer and keep only the
smaller companions resident.
The trusted-repo allowlist admitted the 720p t2v repack while the only
Hunyuan family entry carried 480p presets, so a 720p load silently
defaulted to 832x480. It now resolves a dedicated entry whose repo-id
alias outranks the generic token (same guider config, verified: both
repos ship guidance 6.0).
A scheduler-wrapped cancel unwinds pipe call by exception and skips the
pipeline's end-of-call maybe_free_model_hooks, leaving onloaded offload
modules on the GPU until the next request; generate() now frees them
before surfacing the cancelled sentinel.
The perf rewrite dropped the bf16 capability guard, so a pre-Ampere CUDA
device (T4/V100/RTX 20xx) would die deep in model load with an opaque dtype
error instead of a clear message. Restores parity with the SDXL trainer.
A warm-cache predownload sweep never consults the cancel event (each cached
file returns instantly), so an unload during it was ignored until a cold
file hit the network. The 2.3 detection also only probed bare-file local
repos; resolve directory repos through the same child resolver the loader
uses so their base pull is scoped too.
