57 Commits

Author	SHA1	Message	Date
leejet	adcac69650	perf: pad small attention heads to 64 for MMA Flash Attention (#1992)	2026-09-18 23:59:58 +08:00
leejet	656a1354c3	refactor: remove obsolete unused tensor filtering (#1984)	2026-09-18 23:41:37 +08:00
leejet	cc515a01f9	perf: eliminate temporary allocations in Philox rounds (#1982)	2026-09-17 02:09:12 +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	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
fszontagh	4a7da26b73	fix: bound plain-text runs in parse_prompt_attention regex (#1919)	2026-09-13 23:29:19 +08:00
leejet	9a977388a8	fix: guard GPU memory capacity and propagate encoding failures (#1958)	2026-09-13 21:35:46 +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
leejet	5ebce93342	fix: reuse graph plans when scale parameters change (#1963)	2026-09-12 01:04:25 +08:00
Maphist0	7f986a9d73	feat: add SenseNova U1.5 support (#1935)	2026-09-12 00:39:59 +08:00
Hmission	b68d58624d	fix: enable VAE decode tiling fallback without auto-fit (#1932)	2026-09-11 01:34:56 +08:00
stduhpf	469fc49bb7	docs: reflect GGML_MAX_NAME value change in rpc docs (and in ggml_extend assert) (#1950)	2026-09-10 23:55:02 +08:00
leejet	6b47fec013	refactor: unify model source and weight lifecycle management (#1956)	2026-09-10 23:53:48 +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)	2026-09-07 00:39:49 +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	2540a4fc25	feat: use backend-native FP8 matmul when supported (#1916)	2026-08-30 20:19:56 +08:00
leejet	be0e34480d	feat: load scaled FP8 weights without upfront conversion (#1913)	2026-08-27 20:50:47 +08:00
leejet	97d2990807	chore: format code	2026-08-19 23:06:07 +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)	2026-08-19 22:21:21 +08:00
fszontagh	58b6cb6b0c	fix: prevent gallocr hash overflow in tiny graph-cut segments (#1880)	2026-08-19 22:20:21 +08:00
leejet	bcc7e29568	feat: support INT8 ConvRot safetensors (#1857)	2026-08-11 23:45:02 +08:00
yzyyzyhhh	2993b7fb43	fix: make parameter loading backend-aware (#1828)	2026-07-29 22:18:44 +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	8a51eb9284	feat: add Mage-Flow support (#1808)	2026-07-23 01:23:25 +08:00
Wagner Bruna	2961182365	chore: add missing override declarations (#1800)	2026-07-21 22:49:52 +08:00
leejet	a8a91b24cd	feat: add ADetailer support (#1785)	2026-07-14 23:59:11 +08:00
leejet	9ef6e7398f	feat: drive layer split from graph-cut segments (#1762)	2026-07-07 23:16:52 +08:00
leejet	e790073e1c	fix: avoid layer splitting unet block paths (#1741)	2026-07-05 15:43:12 +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	2574f59365	fix: fallback when backend rejects flash attention (#1732)	2026-07-03 00:46:51 +08:00
mmandelker-code	7dab3668d0	fix: enable Wan/TAEHV video generation on the Metal backend (#850) (#1731)	2026-07-03 00:38:13 +08:00
leejet	556f04bb3f	feat: add qwen image layered support (#1119)	2026-07-03 00:21:22 +08:00
KenForever	3590aa8d62	feat: add MiniT2I support (#1683)	2026-07-02 00:46:51 +08:00
stduhpf	1a13107bac	feat: add imatrix support (#633)	2026-07-01 23:26:37 +08:00
leejet	8caa3f908a	feat: add krea2 support (#1705)	2026-06-25 00:25:50 +08:00
Wagner Bruna	710bc91c8f	fix: correct conversion from sd_type_t to ggml_type (#1519)	2026-06-16 23:54:42 +08:00
leejet	bb90bfa00f	feat: support backend-specific max-vram budgets	2026-06-14 22:46:32 +08:00
stduhpf	c2df4e1228	feat: add RPC support (#1629)	2026-06-14 17:30:23 +08:00
leejet	9838264c49	refactor: simplify ControlNet output caching (#1655)	2026-06-14 16:58:37 +08:00
leejet	5db680c2c7	refactor: route cpu placement through backend specs (#1654)	2026-06-14 15:52:24 +08:00