digital-garbageandClaude Opus 5.5 837a4215a4 fix: v4 regressions before the rental: taste judge trains under inference mode; LoRA keys unwrapped, misfits dropped, no-match said; unsupported dtype said; missed run finish read from history; prompt nudge no longer holds the model ...

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-06 03:08:29 +03:00

..

checkpoint

feat: assign category to every remaining module

2026-09-15 09:46:58 +03:00

clip

feat: assign category to every remaining module

2026-09-15 09:46:58 +03:00

diffusion_model

fix: v4 regressions before the rental: taste judge trains under inference mode; LoRA keys unwrapped, misfits dropped, no-match said; unsupported dtype said; missed run finish read from history; prompt nudge no longer holds the model

2026-10-06 03:08:29 +03:00

lora

fix: v4 regressions before the rental: taste judge trains under inference mode; LoRA keys unwrapped, misfits dropped, no-match said; unsupported dtype said; missed run finish read from history; prompt nudge no longer holds the model

2026-10-06 03:08:29 +03:00

tests

fix: v4 regressions before the rental: taste judge trains under inference mode; LoRA keys unwrapped, misfits dropped, no-match said; unsupported dtype said; missed run finish read from history; prompt nudge no longer holds the model

2026-10-06 03:08:29 +03:00

vae

feat: assign category to every remaining module

2026-09-15 09:46:58 +03:00

__init__.py

core: nodes are announced by modules, like everything else

2026-08-29 03:03:19 +03:00

common.py

fix: v4 regressions before the rental: taste judge trains under inference mode; LoRA keys unwrapped, misfits dropped, no-match said; unsupported dtype said; missed run finish read from history; prompt nudge no longer holds the model

2026-10-06 03:08:29 +03:00

gguf_support.py

feat: GGUF loader support, and fix silent pipeline-editor state loss

2026-09-11 18:14:46 +03:00

int8_convrot.py

feat: int8_convrot option on the diffusion model loader (H3 bf16 file -> int8 + rotation at load)

2026-10-04 14:09:24 +03:00

sla_attention.py

fix: LTX temporal styles scaled nothing (core hands the wrapper a bare frame_rate); identity transfer on guided latents; context-window overlap cut below the window; fault record survives model clones

2026-10-03 11:08:28 +03:00

sla_block_map.py

feat: SLA block-sparse attention for MiniMax H3, ported from v4

2026-09-15 15:13:05 +03:00

sla_kernel.py

feat: SLA block-sparse attention for MiniMax H3, ported from v4

2026-09-15 15:13:05 +03:00