- Free reserved VRAM in the diffusion load worker's failure path: a load-time OOM
never commits _state and the next load's _unload_locked early-returns, so nothing
else reclaimed the half-built pipeline's memory
- Use a monotonic clock for the denoise ETA rate
- Sync _GENERATION_DEFAULTS with the UI table: kontext, flux.2-dev, sdxl-turbo and
SDXL base rows so /v1/images/generations stops falling back to 9 steps / CFG 0
- 400 (not sanitized 500) when /v1/images/generations hits an edit-only model
- Fail fast on pre-Ampere CUDA in the DiT trainer instead of dying in model load
- Run the trainer trust gate in the diffusion training route before freeing GPU
residents so an untrusted base cannot tear down loaded chat/Images models
- Protect native sd.cpp companion VAE/text-encoder repos from cache deletion while
a load is downloading them
- Exempt the task-scoped Images picker from the chat-only GGUF/MLX format gate so
local diffusers pipelines stay selectable on no-GPU hosts
Tag the ltxv and wan GGUF archs text-to-video so cached video checkpoints
actually surface in the Video picker (they were classed unsupported and
hidden everywhere). Adopt the loaded family's default clip length instead
of silently keeping the 25-frame pre-load fallback, and derive steps and
guidance from the picked GGUF filename so a distilled variant gets its
few-step schedule. Suppress the error toast for the user's own Cancel and
disable the Video nav item on chat-only hosts with a hint, matching Train.
Re-plan memory with the quant steady factor when the bf16 table forces
offload a quantised DiT would not need, mirroring the image dense-quant
path, and fall back to the bf16 plan when quant does not engage. Stream
the second expert under group offload (model and sequential already hook
every module). Fail the load cleanly when quant engages on only one
expert instead of running mixed precision with quant reported off.
Persist guidance_2 in the gallery recipe so A14B clips are reproducible.
Review round on the video backend:
- the resident memory check now budgets transformer plus companions like the
image backend, instead of letting auto pick a resident placement that OOMs
while the LTX text encoder and VAEs load
- a new load waits for the signalled in flight generation to exit before
tearing down the old pipeline, so two models never share VRAM during a swap
- the load worker rechecks its token right before placement, narrowing the
window where a cancelled load could put weights on a GPU the arbiter
already handed to another backend
- the step cache installs before the speed profile and compile now keys
fullgraph off an active cache, matching the image order; compiling
fullgraph first crashed the first cached generation
- teardown uninstalls the process wide compiled GGUF dequantizer so a later
speed off load gets the bit identical path
- explicit base_repo goes through the same trust gate as non GGUF repo ids,
and local checkpoint paths are verified during validation, before the
route evicts a resident model
- status reports only the speed optimisations that actually engaged
- the gallery file route streams via FileResponse with range support instead
of buffering whole clips
- the build step reuses the checkpoint path resolved during planning
Review follow ups on the more-families branch: the per channel scale now
broadcasts rank aware instead of assuming 2D (all shipped tensors are 2D,
verified across all three fp8 components, but a future non 2D quantized
tensor would have mis broadcast silently), the fused qkv split asserts the
expected 3x hidden row count so a GQA style export fails loudly, fp8
detection scans every shard header rather than the first, and the excluded
model match uses the segment aware token helper with a hunyuanimage-3
token so a future HunyuanImage 2.x is not blocked with a 3.0 reason.
