leejet b4d6b83af6 fix: support integer LoRA scalar conversion to FP32 (#2263)

2026-11-03 00:07:40 +08:00

..

conditioning

feat: return generation metadata with core results (#2206)

2026-10-25 03:18:03 +08:00

core

fix: layer split across cuda (#2262)

2026-11-03 00:03:43 +08:00

extensions

chore: format code

2026-10-24 01:23:42 +08:00

model

feat: add custom modulate operator and ConvRot fusion (#2258)

2026-11-02 01:19:28 +08:00

model_io

fix: avoid repeated seeks when skipping small GGUF metadata values (#2223)

2026-10-27 00:24:43 +08:00

pipeline

refactor: make_hires_sigma_schedule() simplification (#2244)

2026-10-29 23:21:20 +08:00

runtime

feat(server): add recipe constraints and update generation workspace (#2217)

2026-10-26 01:01:43 +08:00

tokenizers

fix: open model files with UTF-8 paths on Windows (#2144)

2026-10-17 00:50:09 +08:00

convert.cpp

fix: open model files with UTF-8 paths on Windows (#2144)

2026-10-17 00:50:09 +08:00

detailer.cpp

feat: return generation metadata with core results (#2206)

2026-10-25 03:18:03 +08:00

detailer.h

feat(server): add ADetailer support to image generation (#2164)

2026-10-21 23:11:36 +08:00

device_residency_manager.h

perf: optimize H3 inference and segmented weight prefetch (#2240)

2026-10-30 00:38:14 +08:00

generation_info.cpp

feat: return generation metadata with core results (#2206)

2026-10-25 03:18:03 +08:00

generation_info.h

feat: return generation metadata with core results (#2206)

2026-10-25 03:18:03 +08:00

model_component.h

feat: add Wan2.2 S2V (audio+img-to-video) support (#1925)

2026-09-13 23:33:50 +08:00

model_definition.h

refactor: centralize model factories and defaults (#2198)

2026-10-24 01:03:05 +08:00

model_loader_files.cpp

feat: support Diffusers-format MiniMax-H3 LoRAs (#2159)

2026-10-18 14:50:36 +08:00

model_loader.cpp

fix: support integer LoRA scalar conversion to FP32 (#2263)

2026-11-03 00:07:40 +08:00

model_loader.h

feat: support Diffusers-format MiniMax-H3 LoRAs (#2159)

2026-10-18 14:50:36 +08:00

model_manager_files.cpp

refactor: align PixArt weights with upstream layout (#2061)

2026-09-26 02:03:05 +08:00

model_manager_prefetch.cpp

perf: optimize H3 inference and segmented weight prefetch (#2240)

2026-10-30 00:38:14 +08:00

model_manager.cpp

fix: retry Vulkan capacity checks after memory reclamation (#2256)

2026-11-01 22:55:56 +08:00

model_manager.h

perf: optimize H3 inference and segmented weight prefetch (#2240)

2026-10-30 00:38:14 +08:00

model_registry.cpp

refactor: centralize model factories and defaults (#2198)

2026-10-24 01:03:05 +08:00

model.h

refactor: use a distinct version id for Chroma (#2237)

2026-10-28 22:02:18 +08:00

name_conversion.cpp

feat: support FLUX.3 Diffusers LoRA tensor names (#2214)

2026-10-25 16:55:45 +08:00

name_conversion.h

refactor: reorganize the file structure (#1266)

2026-02-10 23:13:35 +08:00

stable-diffusion.cpp

feat: return generation metadata with core results (#2206)

2026-10-25 03:18:03 +08:00

upscaler.cpp

feat: return generation metadata with core results (#2206)

2026-10-25 03:18:03 +08:00

upscaler.h

feat: add MoSR upscaler support (#2128)

2026-10-12 22:38:38 +08:00

version.cpp

refactor: reorganize the file structure (#1266)

2026-02-10 23:13:35 +08:00