83 Commits

Author SHA1 Message Date
leejet
740c7ae193
feat: add configurable Qwen cache types and early cache scheduling (#2045) 2026-09-25 01:51:01 +08:00
leejet
2dc7f5408a
feat: add Qwen Image 2.1 prefix KV cache (#2035) 2026-09-23 23:08:21 +08:00
leejet
e6281b6318
feat: add configurable conditioning cache for all models (#2034) 2026-09-23 22:25:42 +08:00
leejet
28b454bda1
feat: add configurable image input preprocessing (#2028) 2026-09-23 02:12:49 +08:00
Weiqi Gao
e112ab5a50
fix: add alpha channel input for Qwen Image 2.1 and relative docs (#2021) 2026-09-22 21:45:06 +08:00
leejet
97d932b8f8
fix: restrict VAE tiling retries to allocation failures (#2019) 2026-09-21 23:40:05 +08:00
Aziz Muminov
78557f88d9
fix: honor reference image resize opt-out in server requests (#2011) 2026-09-21 23:39:24 +08:00
leejet
187b2561ea
feat: add native CUDA SageAttention support (#2005) 2026-09-21 01:16:59 +08:00
fszontagh
15f335daa5
feat: add LLaDA-Image support (#1968)
Co-authored-by: leejet <leejet714@gmail.com>
2026-09-21 01:14:20 +08:00
leejet
3e037a81e4
perf: accelerate VAE direct 3D convolutions (#1996) 2026-09-19 17:50:01 +08:00
Wagner Bruna
07a85c74cb
feat: support Brownian tree noise in all noise injection samplers (#1899) 2026-09-15 02:37:31 +08:00
leejet
f9ddc0f388
refactor: require external Gemma 2 and GPT-OSS tokenizers (#1974) 2026-09-15 01:25:13 +08:00
leejet
4964abdfc5
feat: support external Hugging Face tokenizer JSON files (#1973) 2026-09-15 00:27:39 +08:00
George
0bd72f075a
feat: add Wan2.2 S2V (audio+img-to-video) support (#1925)
Co-authored-by: leejet <leejet714@gmail.com>
2026-09-13 23:33:50 +08:00
leejet
44dd13716d
feat: preserve explicit backend assignments during auto-fit (#1967) 2026-09-13 17:40:38 +08:00
leejet
7f410a3793
feat: add linear and attention scale overrides (#1964) 2026-09-12 01:41:28 +08:00
vmobilis
3191b23d4b
fix: handle invalid option numbers (#1961) 2026-09-11 23:16:39 +08:00
leejet
80bac2d5fc
feat: enable single-GPU auto-fit with tiered parameter placement (#1942) 2026-09-07 00:18:42 +08:00
leejet
dbb611264e
feat: add verbose logging and log-level selection (#1941) 2026-09-06 23:14:03 +08:00
leejet
462d675018
refactor: unify runner lifecycles and weight residency (#1940) 2026-09-06 22:30:45 +08:00
assouan
6c57cc3b38
feat: prefetch streamed layers during compute (#1905)
Co-authored-by: leejet <leejet714@gmail.com>
2026-09-06 16:35:30 +08:00
leejet
6b3edaaf32
feat: generalize temporal tiling across video VAEs (#1926) 2026-08-31 00:11:38 +08:00
leejet
97d2990807 chore: format code 2026-08-19 23:06:07 +08:00
vmobilis
16304cc3fd
fix: guard against missing sampler/scheduler names (#1887) 2026-08-19 22:31:19 +08:00
vmobilis
760717a060
fix: make max_order of lms sampler configurable (#1885) 2026-08-19 22:29:29 +08:00
leejet
ea7f0c87cf
feat: add minimax-h3 support (#1854) 2026-08-04 23:14:18 +08:00
vmobilis
eb7f35ca49
feat: add linear multi-step sampling method (#1843) 2026-08-02 16:19:47 +08:00
Wagner Bruna
af92790ffc
feat: allow customizing the alpha and beta parameters of the beta scheduler (#1834) 2026-07-30 21:24:51 +08:00
fszontagh
5ef4a7557d
feat: expose IP-Adapter in server request schema and capabilities (#1824) 2026-07-27 23:26:34 +08:00
fszontagh
8d377073e3
feat: add IP-Adapter support for SD 1.5 and SDXL (#1803) 2026-07-24 21:19:44 +08:00
leejet
b290693977
feat: add PiD 1.5 support (#1790) 2026-07-17 01:35:18 +08:00
leejet
a8a91b24cd
feat: add ADetailer support (#1785) 2026-07-14 23:59:11 +08:00
fszontagh
c00a9e956d
feat: AnimateDiff SD 1.5 motion modules (v2 + v3) (#1784) 2026-07-14 23:58:03 +08:00
stduhpf
74bce049d0
feat: add configurable reference image processing for edit models (#1780) 2026-07-14 22:58:22 +08:00
leejet
bb84971129
refactor: move model-specific args into model parsers (#1757) 2026-07-06 23:13:18 +08:00
fszontagh
e071aa390b
feat: move circular padding from context to per-generation params (#1748) 2026-07-06 22:04:20 +08:00
fszontagh
e9dee542c4
feat: add DPM++ 2M SDE (Brownian tree) sampler (#1743) 2026-07-05 17:32:43 +08:00
fszontagh
38a51f8105
feat: add DPM++ 2M SDE sampler (#1742) 2026-07-05 16:13:25 +08:00
Piotr Wilkin (ilintar)
b11c95a41c
feat: auto fit tensors across devices to guarantee optimal load (#1736) 2026-07-05 00:48:10 +08:00
Piotr Wilkin (ilintar)
68f3d6df9f
feat: support for cross-device row split (#1735) 2026-07-04 16:31:18 +08:00
Piotr Wilkin (ilintar)
7bcd189639
feat: add multi-device layer split (--backend "diffusion=cuda0&cuda1") (#1734) 2026-07-04 16:06:33 +08:00
leejet
556f04bb3f
feat: add qwen image layered support (#1119) 2026-07-03 00:21:22 +08:00
stduhpf
1a13107bac
feat: add imatrix support (#633) 2026-07-01 23:26:37 +08:00
Erik Scholz
484baa41e5
feat: add beta scheduler (#811)
Co-authored-by: phil2sat <phil2sat@users.noreply.github.com>
2026-07-01 01:40:22 +08:00
leejet
3b6c9ca97c
feat: add normal alias for discrete scheduler (#1724) 2026-06-30 00:19:21 +08:00
leejet
57e19fa954
feat: add Flux scheduler (#1723) 2026-06-29 23:49:56 +08:00
leejet
61a637bfd5
feat: add Flux2 scheduler (#1722) 2026-06-29 23:17:31 +08:00
stduhpf
2938272d82
feat: add logit-normal scheduler (#1669) 2026-06-25 00:06:11 +08:00
leejet
f440ad9c29
fix: avoid writable mmap for read-only weights (#1698) 2026-06-23 00:39:31 +08:00
stduhpf
41f7acbfb0
feat: support guidance_schedule (#1684) 2026-06-23 00:05:55 +08:00