leejet 2540a4fc25 feat: use backend-native FP8 matmul when supported (#1916)

2026-08-30 20:19:56 +08:00

..

conditioning

feat: add LTX-2.5 support (#1893)

2026-08-30 19:13:06 +08:00

core

feat: use backend-native FP8 matmul when supported (#1916)

2026-08-30 20:19:56 +08:00

extensions

fix(PhotoMaker): avoid GGML_ASSERT if trigger word 'img' was not found in prompt (#1835)

2026-07-30 21:26:57 +08:00

model

fix: correct MiniMax H3 audio Euler steps (#1908)

2026-08-30 20:19:28 +08:00

model_io

feat: load scaled FP8 weights without upfront conversion (#1913)

2026-08-27 20:50:47 +08:00

runtime

chore: format code

2026-08-19 23:06:07 +08:00

tokenizers

…

convert.cpp

…

detailer.cpp

…

detailer.h

…

model_loader.cpp

feat: load scaled FP8 weights without upfront conversion (#1913)

2026-08-27 20:50:47 +08:00

model_loader.h

…

model_manager.cpp

…

model_manager.h

…

model.h

feat: add minimax-h3 support (#1854)

2026-08-04 23:14:18 +08:00

name_conversion.cpp

feat: add LTX-2.5 support (#1893)

2026-08-30 19:13:06 +08:00

name_conversion.h

…

stable-diffusion.cpp

fix: correct MiniMax H3 audio Euler steps (#1908)

2026-08-30 20:19:28 +08:00

upscaler.cpp

…

upscaler.h

…

version.cpp

…

weight_manager.h

…