Commit Graph
837 Commits
Author SHA1 Message Date
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)andleejet 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
leejet bcc7e29568 feat: support INT8 ConvRot safetensors (#1857) master-817-bcc7e29 2026-08-11 23:45:02 +08:00
Daniel Han 487de75c96 fix: fail with a message when MiniMax-H3 is run in img_gen mode (#1863) master-816-487de75 2026-08-11 23:22:20 +08:00
stduhpf b4f1fd6d7f fix: preserve "token_refiner" token for MiniMax H3 LoRAs (#1864) master-815-b4f1fd6 2026-08-11 22:57:05 +08:00
leejet c6beeef355 fix: map Qwen3-VL DeepStack GGUF tensor names (#1858) 2026-08-06 01:50:55 +08:00
stduhpf bfbef5b7e6 feat: trained Minimax VAE Latent2rgb proj (#1856) master-813-bfbef5b 2026-08-06 01:39:10 +08:00
leejet ea7f0c87cf feat: add minimax-h3 support (#1854) master-812-ea7f0c8 2026-08-04 23:14:18 +08:00
Huang, Hong-Chang b4e67d1221 fix(cmake): only apply /MP to the MSVC compiler, not icx (#1846) master-811-b4e67d1 2026-08-04 22:37:30 +08:00
leejet db99efdd6d refactor: extract model loader initialization (#1844) master-810-db99efd 2026-08-02 17:24:10 +08:00
vmobilis eb7f35ca49 feat: add linear multi-step sampling method (#1843) master-809-eb7f35c 2026-08-02 16:19:47 +08:00
fszontagh 50062a4bba feat: add IP-Adapter Plus (Resampler image projection) support (#1839) master-808-50062a4 2026-08-02 16:15:28 +08:00
stduhpf 8457624101 feat: support more LoRA models (Kroma-v0.1 support) (#1842) master-807-8457624 2026-08-02 16:08:47 +08:00
stduhpfandleejet 10378f42db fix: lora with split qkv compatibility check at runtime (#1836)
Co-authored-by: leejet <leejet714@gmail.com>
master-806-10378f4
2026-08-02 16:08:08 +08:00
leejet e31a86ce91 refactor: centralize CLIP prefix conversion (#1837) master-805-e31a86c 2026-07-30 22:44:31 +08:00
akleine 735a4ef520 fix(PhotoMaker): avoid GGML_ASSERT if trigger word 'img' was not found in prompt (#1835) master-804-735a4ef 2026-07-30 21:26:57 +08:00
Wagner Bruna af92790ffc feat: allow customizing the alpha and beta parameters of the beta scheduler (#1834) master-803-af92790 2026-07-30 21:24:51 +08:00
leejet e92e86fb11 fix: prevent torch checkpoint offset overflow (#1832) master-802-e92e86f 2026-07-29 23:16:29 +08:00
vmobilis 9cfe2af8f9 feat: display number of tokens for SD models (#1831) master-801-9cfe2af 2026-07-29 22:21:54 +08:00
yzyyzyhhh 2993b7fb43 fix: make parameter loading backend-aware (#1828) master-800-2993b7f 2026-07-29 22:18:44 +08:00
Nicky Mouha 53856e7ec8 fix: null pointer dereference when loading malformed LoHa file (#1826) master-799-53856e7 2026-07-29 21:53:26 +08:00
leejet 22516991cb fix: skip incompatible LoRA weights (#1825) 2026-07-28 00:06:46 +08:00
fszontagh 5ef4a7557d feat: expose IP-Adapter in server request schema and capabilities (#1824) master-797-5ef4a75 2026-07-27 23:26:34 +08:00
vmobilis 2d0385ba85 fix: add missing sampler names (#1819) master-796-2d0385b 2026-07-26 22:58:05 +08:00
leejet 87a01773be fix: add frame dimension for Hunyuan IMG2VID encoding (#1816) master-795-87a0177 2026-07-24 22:37:26 +08:00
leejet b0f856804c fix: correct IP-Adapter CFG conditioning and defaults (#1815) master-794-b0f8568 2026-07-24 22:01:54 +08:00
Mario Limonciello 78124b6454 ci: update ROCm releases to 7.14.0 (#1802) master-793-78124b6 2026-07-24 21:25:04 +08:00
Henry Kroll III b338b4b4b9 docs: add Gimp plugins to UIs section (#1799) 2026-07-24 21:21:17 +08:00
Wagner Bruna b8bf67615c fix: correct dangling pointer to empty image reference vector (#1813) master-791-b8bf676 2026-07-24 21:20:33 +08:00
fszontagh 8d377073e3 feat: add IP-Adapter support for SD 1.5 and SDXL (#1803) master-790-8d37707 2026-07-24 21:19:44 +08:00
fszontagh 5114672c48 fix: detect vision patch size for unsplit (HF-format) Qwen3-VL (#1811) master-789-5114672 2026-07-23 22:22:21 +08:00
leejet 8a51eb9284 feat: add Mage-Flow support (#1808) master-788-8a51eb9 2026-07-23 01:23:25 +08:00