Commit Graph

7327 Commits (10bbbed218458b8a899aac2140ec738d8d716f05)

Author SHA1 Message Date
Disty0 9c16e2234a cleanup 2025-10-08 01:18:12 +03:00
Disty0 25303bb182 cleanup 2025-10-08 01:16:25 +03:00
Disty0 bdcd07f713 Add add_module_skip_keys to pre-load quant too 2025-10-08 01:11:40 +03:00
Disty0 7fdf400e8b cleanup 2025-10-08 00:41:04 +03:00
Disty0 df03ea9ba8 SDNQ add sdnq_post_load_quant and update Qwen keys 2025-10-08 00:29:36 +03:00
Vladimir Mandic 962cb7115d infra for full-model load/save with quant
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-07 14:30:45 -04:00
Vladimir Mandic e4120bd4d6 detect sdnq saved model
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-07 10:57:17 -04:00
Vladimir Mandic 0092a8b86b add quantization_config for post-load
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-07 10:14:31 -04:00
Vladimir Mandic 7fdc880a73 sdnq patches
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-07 09:43:34 -04:00
Vladimir Mandic 25e28050c3 update swagger docs
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-07 08:21:05 -04:00
Vladimir Mandic fe41d7da2a use shared llama
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-07 08:14:11 -04:00
Vladimir Mandic 3fe1d090e4 add configurable layers to taehv
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-06 19:13:30 -04:00
Disty0 1cd7b6d63a fix upcast scale check 2025-10-07 01:27:54 +03:00
Disty0 aa0c10440f SDNQ make the loader don't touch the model options by default 2025-10-07 00:15:23 +03:00
Disty0 5306376b2a improve contiguous mm performance 2025-10-06 19:05:46 +03:00
Disty0 be91bbff75 SDNQ add SVD support for Convs 2025-10-06 18:26:42 +03:00
Disty0 c931bf9efa SDNQ add dtype casting to loader 2025-10-06 17:44:52 +03:00
Disty0 5c042c5fb8 cleanup 2025-10-06 11:30:26 +03:00
Vladimir Mandic a315a004e9 linting
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-05 20:25:33 -04:00
Vladimir Mandic 28e3ae0480 experimental xomni
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-05 20:17:32 -04:00
Vladimir Mandic 3e47f3dd9a video prompt enhance
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-05 20:17:32 -04:00
Vladimir Mandic 58b0ab9da6 unified video save
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-05 20:17:32 -04:00
Vladimir Mandic d7d86ed286 ltx job tracking
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-05 20:17:32 -04:00
Vladimir Mandic 7dad90b385 video use shared t5
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-05 20:17:32 -04:00
Vladimir Mandic 50c3385cf9 fix ltx model selection
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-05 20:17:32 -04:00
Disty0 23f2deaa58 fix enable_quantized_mamtul 2025-10-06 02:04:28 +03:00
Disty0 1f81a37e8e Set the default svd rank to 32 2025-10-06 01:27:29 +03:00
Disty0 ebb26ac123 SDNQ make load file name configurable 2025-10-06 01:04:00 +03:00
Disty0 0acb571472 SDNQ ass load and save model funcs 2025-10-06 00:57:23 +03:00
Disty0 9e52d0c1fb SDNQ add SVDQuant quantization method 2025-10-05 22:50:30 +03:00
Vladimir Mandic 268798a24e add framepack granular job tracking
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-05 10:39:55 -04:00
Disty0 428600613a SDNQ fix new transformers again 2025-10-05 15:30:15 +03:00
Disty0 a164f3e0c2 SDNQ Improve UINT3 and below quant speed 2025-10-05 03:12:05 +03:00
Vladimir Mandic 8325e886c7 add typo to legacy compatibility options
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-04 18:11:52 -04:00
Vladimir Mandic c530167cbe qwen multi-image edits
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-04 18:06:50 -04:00
Vladimir Mandic 8b698ed67f upadte qwen pruning and allow hf models in subfolders
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-04 15:49:20 -04:00
Disty0 f2e12a682f SDNQ remove use_contiguous_mm path in re_quant 2025-10-04 19:17:05 +03:00
Disty0 df142afe81 don't use triton mm for nvidia 2025-10-04 18:48:03 +03:00
Disty0 5c5d7d5a86 cleanup 2025-10-04 18:38:18 +03:00
Disty0 99113947bf SDNQ add RDNA2 INT8 support via Triton 2025-10-04 18:31:25 +03:00
Vladimir Mandic 54ae18a611 update nunchaku
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-03 12:23:24 -04:00
Disty0 95a7da7e75 SDNQ use non-contiguous re-quantize 2025-10-03 18:54:58 +03:00
Vladimir Mandic a6108dd6df add qwen pruning variants
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-03 11:36:14 -04:00
Disty0 54acf1760b Make SDNQ scales compatible with balanced offload 2025-10-03 18:13:55 +03:00
Disty0 c5cab96223 SDNQ simplify check_mats 2025-10-03 02:58:17 +03:00
Vladimir Mandic 7325f9dbae dont import guiders until needed
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-02 16:28:34 -04:00
Disty0 34c2a624aa SDNQ autodetect fp8 tw fallback and disable dynamic compile 2025-10-02 19:40:07 +03:00
Vladimir Mandic f245506bf2 cleanup hf login
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-02 08:17:35 -04:00
CalamitousFelicitousness 78711fb1d4
Merge branch 'dev' into patch-2 2025-10-01 20:58:58 +01:00
CalamitousFelicitousness 78820a14dc
Allow VLM temp setting temperature to 0
Allow VLM temp setting temperature to 0
2025-10-01 20:52:04 +01:00
Disty0 81bb2b99ef update florence promptgen repo ids 2025-10-01 21:43:02 +03:00
Vladimir Mandic 22074f4727 cleanup vqa
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-01 12:02:55 -04:00
Vladimir Mandic 5d0a3e5e8a fix microsoft-florence
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-01 10:58:52 -04:00
Disty0 03382bdd4c SDNQ simplify check_mats 2025-10-01 01:35:51 +03:00
Vladimir Mandic 8c2b76a8da add buffers and cache info
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-30 14:36:55 -04:00
Vladimir Mandic 201ca28300 improve ram monitor
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-30 14:27:43 -04:00
Disty0 0c1d34721c SDNQ use contiguous for intel 2025-09-30 02:37:58 +03:00
Vladimir Mandic 2621aecacc interrrupt will now show last known preview image
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-29 19:25:50 -04:00
Disty0 6b67a9d0c4 SDNQ add check_mats to matmul 2025-09-30 01:58:13 +03:00
Vladimir Mandic 93bdca0670 fix image str decode and update requirements
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-29 10:56:03 -04:00
Vladimir Mandic 5d1bfc2bfc cleanup
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 21:36:16 -04:00
Vladimir Mandic c03a6928e4 reference models add size and release date info
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 21:19:36 -04:00
Vladimir Mandic 70a2c209b1 cleanup
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 20:22:25 -04:00
Vladimir Mandic 8cc9c23f98 add directml and rocm note to changelog
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 18:44:42 -04:00
Vladimir Mandic c661497b87 linting
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 18:09:09 -04:00
Vladimir Mandic eb025eaf31 remove split-attention and add attention slicing option
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 18:01:34 -04:00
Disty0 1b45c145e9 SDNQ re-enable dynamic compile 2025-09-28 20:40:24 +03:00
Disty0 6f2145fa57 revert offload_buffers 2025-09-28 16:47:31 +03:00
Vladimir Mandic 749878289f document vae changes
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 09:25:38 -04:00
Vladimir Mandic 9e6fdaa5cc vae slicing and tiling enabled on low and med vram, off otherwise
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-28 09:24:07 -04:00
Disty0 02f03d56a7 set offload_buffers to true on balanced offload 2025-09-28 16:23:29 +03:00
Disty0 4a70e82b0c ROCm always use numpy on cholesky 2025-09-28 14:05:20 +03:00
Disty0 a47959b114 move ROCm Windows hijacks outside of torch install 2025-09-28 13:33:15 +03:00
Seunghoon Lee 06b14b070b
hijack torch.linalg.cholesky() 2025-09-28 18:43:37 +09:00
Seunghoon Lee 9c19e8a9b8
return correct item 2025-09-28 18:34:10 +09:00
Seunghoon Lee 6e8abf8dc3
hijack cholesky decomposition for therock pytorch 2025-09-28 18:03:02 +09:00
Seunghoon Lee 95ee0ed29c
load amdhip64_6.dll instead of amdhip64.dll 2025-09-28 17:15:12 +09:00
Seunghoon Lee 0de3732884
prioritize python pacakage check over PATH 2025-09-28 11:31:43 +09:00
Disty0 587db51e9e Cleanup env vars and set TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL to 1 2025-09-28 00:22:00 +03:00
Seunghoon Lee 35b1c6b07d
windows install rocm if not installed 2025-09-28 05:39:41 +09:00
Seunghoon Lee 059392afc7
clean up 2025-09-27 17:51:59 +09:00
Disty0 503a178794 Don't load rocm hsa on non wsl envs and remove unused lib hijacks 2025-09-27 11:39:24 +03:00
Disty0 71fde8a897 ROCm and Zluda don't fallback to CPU and clenup strings 2025-09-27 11:32:46 +03:00
Seunghoon Lee 579b1f3175
do not load global amdhip64, let pytorch load it 2025-09-27 17:01:14 +09:00
Seunghoon Lee d52d84eda5
clean up 2025-09-27 16:49:29 +09:00
Luca Beltrame f00486c8f3
Fix HIP library detection
The code unconditionally checked `lib`, but on modern Linux distributions, 64-bit binaries are under `lib64` instead. 

Note that this might be slightly different on Debian-based distributions, but as I don't have one I can't test it.
2025-09-27 09:23:32 +02:00
Seunghoon Lee e3e41298d9
remove unused import 2025-09-27 11:29:55 +09:00
Seunghoon Lee 8d2aedd924
hotfix 2025-09-27 11:17:15 +09:00
Seunghoon Lee d63bc05b6c
update rocm.py to detect rocm-sdk packages 2025-09-27 11:12:13 +09:00
Vladimir Mandic bd048e8efc framepack: patch solver for unsupported gpus
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-26 12:28:52 -04:00
Vladimir Mandic c254835351 fix lora strength
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-26 10:14:02 -04:00
Vladimir Mandic ae25cb8880 linting
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-25 14:33:21 -04:00
Vladimir Mandic 01e8211d4b cleanup
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-25 14:17:40 -04:00
Vladimir Mandic ab82c172d5 handle nunchaku lora with unsupported models
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-25 14:02:21 -04:00
Vladimir Mandic 9cee2cd1ed fix metadata on batched images
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-25 13:45:23 -04:00
Vladimir Mandic 7a3001170b add daam script
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-24 20:16:07 -04:00
Disty0 a776c7c615 SDNQ fix new transformers 2025-09-24 21:32:30 +03:00
Vladimir Mandic 0d2579302e cleanup modular init
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-24 13:03:18 -04:00
Vladimir Mandic c96af0d428 fix lora filter by model type
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-24 12:55:11 -04:00
Vladimir Mandic 6f409deedf ui separate guidance and detail sections
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-24 12:33:57 -04:00
Vladimir Mandic 91dab5703a modular pipeline prototype
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-24 11:40:20 -04:00
Vladimir Mandic 35c319578d auto uninstall pynvml
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-24 09:38:35 -04:00
Vladimir Mandic a9a39cb64b ltx model selector
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-24 09:31:36 -04:00
Vladimir Mandic d71d540a62 allow lora specifier to select model component. see changelog/wiki for docs on how to.
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-23 15:25:13 -04:00
Vladimir Mandic a502cc2ae1 cache-dit support
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-23 10:13:32 -04:00
Vladimir Mandic 93659dff4d add qwen-image-edit-2509 and update requirements
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-23 10:13:32 -04:00
Disty0 41e297ba2c SDNQ fix new transformers 2025-09-23 16:17:09 +03:00
Vladimir Mandic 4130c6cc8b experimental cache-dit
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-22 15:55:26 -04:00
Vladimir Mandic 41bb446697 support configurable multi-stage models in video tab
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-22 13:18:39 -04:00
Vladimir Mandic d41bf3d673 add api to trigger civitai metadata update
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-21 20:06:45 -04:00
Vladimir Mandic 27846fe97d styles and wildcards use main seed
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-21 19:43:55 -04:00
Vladimir Mandic 82504e96d0 nunchaku flux.1-ipadapter
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-21 13:26:18 -04:00
Vladimir Mandic 5b43c66a92 nunchaku sdxl and sdxl-turbo support
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-20 21:01:21 -04:00
Vladimir Mandic 9667fffd3a fix download for sd15/sdxl reference models
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-20 19:39:43 -04:00
Disty0 e6715ba8d3 Cleanup SDNQ compile 2025-09-19 19:29:36 +03:00
Vladimir Mandic cd79f92dff add opts models_not_to_offload
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-19 11:21:54 -04:00
Vladimir Mandic 5606519085 wan init image fix
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-18 11:40:01 -04:00
Vladimir Mandic 94cb993e99 framepack add hf auth check
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-18 10:22:06 -04:00
Disty0 6f969958ae remove sdp_kernel hijack 2025-09-17 20:15:00 +03:00
Disty0 2842f5e3aa cleanup 2025-09-17 19:58:21 +03:00
Disty0 cc51f79508 IPEX remove outdated hijacks 2025-09-17 19:53:05 +03:00
Disty0 e83df50717 IPEX fix missing dtype from randn 2025-09-17 19:40:27 +03:00
Vladimir Mandic cc6101ecb2 jumbo update: add wan22-vace, improve offloading, add offloading-using-streams, change logging-levels, refactor some default packages
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-17 12:32:30 -04:00
Disty0 6a021e7743 ipex cleanup tensor_to hijack 2025-09-17 14:44:44 +03:00
Vladimir Mandic f8f958244f use new pydantic/albumentations/insightface
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-16 10:17:33 -04:00
Disty0 39027ccfea SDNQ fix conv matmul 2025-09-16 17:12:04 +03:00
Vladimir Mandic ad9d56f49e offload clean logging
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-16 09:03:03 -04:00
Vladimir Mandic 2aa503be55 report zluda-on-windows error, but do not exit
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-16 08:57:32 -04:00
Disty0 a12edc1e90 SDNQ use nan_to_num_ with fp8 quantization in case of zeros 2025-09-15 20:22:39 +03:00
Vladimir Mandic 0d1275972c update changelog/todo
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-15 09:26:46 -04:00
Vladimir Mandic 0f7d2e95ca fix state interrupted checks
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-14 13:03:03 -04:00
Vladimir Mandic e54065c3b3 update nvml
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-14 11:17:03 -04:00
Vladimir Mandic f09ccf35a6 zero-out loader time
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-14 11:13:38 -04:00
Vladimir Mandic 6f2adf3fde reference models indicate if ready or requires download
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-14 10:30:21 -04:00
Vladimir Mandic f976ed223d fix wan22-i2v
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-14 09:14:52 -04:00
Vladimir Mandic d351fdb98f add more job state updates and update history tab
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-13 10:54:04 -04:00
Vladimir Mandic 4e74172f3a fix typo
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-13 09:17:42 -04:00
Vladimir Mandic e529fcc546 fix exception
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-13 09:13:48 -04:00
Vladimir Mandic 1c5b3a47e2 job history
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-12 22:14:07 -04:00
Vladimir Mandic 8cd5fbc926 lint
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-12 16:28:53 -04:00
Vladimir Mandic 175e9cbe29 cleanup/refactor state history
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-12 16:12:45 -04:00
Disty0 a8b850adf4 move hf quantizer hijacks to sdnq 2025-09-12 20:54:44 +03:00
Vladimir Mandic 4956d94b97 allow denoise 0
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-12 13:10:52 -04:00
Vladimir Mandic 9bed503ce6 control handle override settings
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-11 16:06:03 -04:00
Disty0 ba7d76eb41 update gfpgan and basicsr commits 2025-09-11 21:18:24 +03:00
Vladimir Mandic 8ed04fb9a6 cleanup
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-11 13:02:52 -04:00
Vladimir Mandic 7940217764 add models_not_to_quant option
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-11 12:31:07 -04:00
Vladimir Mandic 2bb96e6926 fix wan i2i
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-11 09:50:20 -04:00
Vladimir Mandic 16670636d7 fix lora with nested pipeline
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-09-11 09:03:02 -04:00
Disty0 4f2b829450 cleanup 2025-09-11 15:42:36 +03:00