Commit Graph
885 Commits
Author SHA1 Message Date
Wagner Bruna b8248a869c fix: avoid passing ggml logs as format strings (#2002) master-885-b8248a8 2026-09-21 00:50:52 +08:00
Wagner Bruna 008ca5b492 feat: restore legacy fp8 handling when building with upstream ggml (#2001) master-884-008ca5b 2026-09-21 00:48:30 +08:00
leejet 137f7409bb feat: add Qwen Image 2.1 support (#1994) master-883-137f740 2026-09-20 22:51:21 +08:00
leejet 1330cebae8 feat: support building with upstream ggml (#1999) 2026-09-19 22:25:01 +08:00
leejet 17860c0e45 perf: parallelize host tensor elementwise and broadcast ops (#1998) master-881-17860c0 2026-09-19 21:46:16 +08:00
leejet 275ab58e01 perf: reduce CPU overhead in graph execution and sampling (#1997) 2026-09-19 18:32:58 +08:00
Fabrice Aneche d32b4e893b fix: prevent clip_preprocess center crop from exceeding the resized image (#1995) master-879-d32b4e8 2026-09-19 18:08:34 +08:00
leejet 9982c9caae fix: propagate CUDA driver dependency to shared library consumers 2026-09-19 18:04:59 +08:00
leejet 3e037a81e4 perf: accelerate VAE direct 3D convolutions (#1996) 2026-09-19 17:50:01 +08:00
leejet 2ea8aff7ef perf: update ggml for faster direct convolutions (#1993) 2026-09-19 00:32:24 +08:00
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) master-874-656a135 2026-09-18 23:41:37 +08:00
Lin Xuhao 269e726015 fix: honor flash attention flag in LLM text encoder attention (#1987) 2026-09-18 23:41:24 +08:00
leejet cc515a01f9 perf: eliminate temporary allocations in Philox rounds (#1982) master-872-cc515a0 2026-09-17 02:09:12 +08:00
leejet 3161505fe8 fix: remove vision_model. from ununsed tensors (#1983) master-871-3161505 2026-09-17 02:08:24 +08:00
leejet 59c23bce0d fix: use tokenizer-specific pre-tokenization rules (#1975) 2026-09-15 02:37:52 +08:00
Wagner Bruna 07a85c74cb feat: support Brownian tree noise in all noise injection samplers (#1899) master-869-07a85c7 2026-09-15 02:37:31 +08:00
leejet f9ddc0f388 refactor: require external Gemma 2 and GPT-OSS tokenizers (#1974) master-868-f9ddc0f 2026-09-15 01:25:13 +08:00
leejet 4964abdfc5 feat: support external Hugging Face tokenizer JSON files (#1973) master-867-4964abd 2026-09-15 00:27:39 +08:00
Санька Четвёртыйandleejet 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
Georgeandleejet 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
assouanandleejet 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
vmobilisandleejet 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