867 Commits

Author SHA1 Message Date
leejet
4964abdfc5
feat: support external Hugging Face tokenizer JSON files (#1973) master-867-4964abd 2026-09-15 00:27:39 +08:00
Санька Четвёртый
42d6c0ab92
feat: Add generation parameters into video metadata (#1901)
Co-authored-by: leejet <leejet714@gmail.com>
master-866-42d6c0a
2026-09-14 00:01:09 +08:00
leejet
5a5400bf0c
fix: resolve MSVC narrowing conversion warnings (#1969) master-865-5a5400b 2026-09-13 23:45:54 +08:00
fszontagh
ca37fad89a
fix: validate vision projector output dim against LLM hidden size (#1918) master-864-ca37fad 2026-09-13 23:42:46 +08:00
George
0bd72f075a
feat: add Wan2.2 S2V (audio+img-to-video) support (#1925)
Co-authored-by: leejet <leejet714@gmail.com>
master-863-0bd72f0
2026-09-13 23:33:50 +08:00
fszontagh
4a7da26b73
fix: bound plain-text runs in parse_prompt_attention regex (#1919) master-862-4a7da26 2026-09-13 23:29:19 +08:00
leejet
9a977388a8
fix: guard GPU memory capacity and propagate encoding failures (#1958) master-861-9a97738 2026-09-13 21:35:46 +08:00
leejet
44dd13716d
feat: preserve explicit backend assignments during auto-fit (#1967) master-860-44dd137 2026-09-13 17:40:38 +08:00
leejet
7f410a3793
feat: add linear and attention scale overrides (#1964) master-859-7f410a3 2026-09-12 01:41:28 +08:00
leejet
5ebce93342
fix: reuse graph plans when scale parameters change (#1963) master-858-5ebce93 2026-09-12 01:04:25 +08:00
Maphist0
7f986a9d73
feat: add SenseNova U1.5 support (#1935) master-857-7f986a9 2026-09-12 00:39:59 +08:00
fszontagh
e06b205384
feat: expose the loaded model version name through the public API (#1962) master-856-e06b205 2026-09-11 23:39:56 +08:00
vmobilis
3191b23d4b
fix: handle invalid option numbers (#1961) master-855-3191b23 2026-09-11 23:16:39 +08:00
LED-M
e95ab96997
fix: preserve BF16 embedding weights for get_rows (#1959) master-854-e95ab96 2026-09-11 23:09:45 +08:00
Hmission
b68d58624d
fix: enable VAE decode tiling fallback without auto-fit (#1932) master-853-b68d586 2026-09-11 01:34:56 +08:00
leejet
14eddb32b1
refactor: split generation pipeline out of stable-diffusion.cpp (#1957) master-852-14eddb3 2026-09-11 00:57:14 +08:00
stduhpf
469fc49bb7
docs: reflect GGML_MAX_NAME value change in rpc docs (and in ggml_extend assert) (#1950) master-851-469fc49 2026-09-10 23:55:02 +08:00
leejet
6b47fec013
refactor: unify model source and weight lifecycle management (#1956) master-850-6b47fec 2026-09-10 23:53:48 +08:00
Wagner Bruna
d04e8950c1
fix: correct SDXL embeddings loading (#1939) master-849-d04e895 2026-09-08 00:23:08 +08:00
nan
9cdb6b6fc0
fix: preserve K-quantized embedding weights (#1936) master-848-9cdb6b6 2026-09-07 23:50:16 +08:00
leejet
31ab2b2e08
refactor: split ggml extensions and move implementations to cpp files (#1945) 2026-09-07 23:34:45 +08:00
leejet
d8fb10c029
fix: reuse graph cut plans across CFG passes (#1943) master-846-d8fb10c 2026-09-07 00:39:49 +08:00
leejet
80bac2d5fc
feat: enable single-GPU auto-fit with tiered parameter placement (#1942) master-845-80bac2d 2026-09-07 00:18:42 +08:00
leejet
dbb611264e
feat: add verbose logging and log-level selection (#1941) master-844-dbb6112 2026-09-06 23:14:03 +08:00
leejet
462d675018
refactor: unify runner lifecycles and weight residency (#1940) master-843-462d675 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) master-841-6b3edaa 2026-08-31 00:11:38 +08:00
leejet
40e605f3f1
fix: use carrier sampling for MiniMax H3 audio (#1924) 2026-08-30 21:57:02 +08:00
vmobilis
9029655a54
feat: support numbering for preview images (#1895) master-839-9029655 2026-08-30 21:56:31 +08:00
vmobilis
d9b6e27e9f
feat: additional --preview-interval values (#1915)
Co-authored-by: leejet <leejet714@gmail.com>
master-838-d9b6e27
2026-08-30 21:47:11 +08:00
leejet
134c8212de sync: update ggml master-837-134c821 2026-08-30 20:21:46 +08:00
leejet
2540a4fc25
feat: use backend-native FP8 matmul when supported (#1916) master-836-2540a4f 2026-08-30 20:19:56 +08:00
jk212h20
dc4000d9f8
fix: correct MiniMax H3 audio Euler steps (#1908) master-835-dc4000d 2026-08-30 20:19:28 +08:00
jk212h20
c797899732
fix: correct MiniMax H3 reference audio encoding (#1886) 2026-08-30 19:33:59 +08:00
Piotr Wilkin (ilintar)
afd5306d88
feat: add LTX-2.5 support (#1893)
Co-authored-by: leejet <leejet714@gmail.com>
master-833-afd5306
2026-08-30 19:13:06 +08:00
leejet
2c929495ab
fix: match exact weights in LLM config detection (#1923) master-832-2c92949 2026-08-30 17:43:41 +08:00
leejet
be0e34480d
feat: load scaled FP8 weights without upfront conversion (#1913) 2026-08-27 20:50:47 +08:00
leejet
50d6405683
feat: support standard Qwen3-VL weights for MiniMax-H3 (#1910) master-830-50d6405 2026-08-26 00:13:33 +08:00
vmobilis
0a565f2950
feat: configurable image / video compression (#1909) master-829-0a565f2 2026-08-26 00:07:48 +08:00
vmobilis
12ee60dc02
fix: use sd_get_preview_interval() (#1907) master-828-12ee60d 2026-08-26 00:05:46 +08:00
leejet
97d2990807 chore: format code master-827-97d2990 2026-08-19 23:06:07 +08:00
vmobilis
16304cc3fd
fix: guard against missing sampler/scheduler names (#1887) master-826-16304cc 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
Wagner Bruna
88b044be7f
fix: mark graph cuts with both a prefix and a suffix (#1883) 2026-08-19 22:27:48 +08:00
fszontagh
1706b32813
fix: re-clamp streaming VRAM budget to currently free memory (#1878) master-823-1706b32 2026-08-19 22:21:21 +08:00
fszontagh
58b6cb6b0c
fix: prevent gallocr hash overflow in tiny graph-cut segments (#1880) master-822-58b6cb6 2026-08-19 22:20:21 +08:00
stduhpf
6100d8339b
feat: add taeh3 support (#1874) master-821-6100d83 2026-08-19 22:18:19 +08:00
leejet
de298c225b fix(ci): trigger builds for ggml updates master-820-de298c2 2026-08-12 23:43:42 +08:00
leejet
fabe481212
sync: update ggml (#1873) 2026-08-12 23:40:28 +08:00
LostRuins Concedo
06c359f17a
fix: replace free_compute_buffer with runner_done in vae (#1872) 2026-08-12 23:39:57 +08:00