Commit Graph

9999 Commits

Author SHA1 Message Date
Disty0 e06cbea7aa Cleanup 2025-05-28 15:55:08 +03:00
Disty0 d8e8f47ce5 SDNQ add an option to toggle quantize with GPU 2025-05-28 15:18:39 +03:00
Disty0 1961e88c13 Set SDPA as the default on all backends and enable Dyn SDPA on ROCm, DML, CPU and MPS 2025-05-28 13:42:29 +03:00
Disty0 569e9099d7 Use torch.amax instead of torch.max 2025-05-28 12:44:07 +03:00
Disty0 0b564e2373 Cleanup 2025-05-28 04:07:45 +03:00
Disty0 1433dfe3de SDNQ fix high RAM usage with pre mode 2025-05-28 03:16:29 +03:00
Disty0 4ed15f5cce SDNQ revert device_map = gpu 2025-05-27 23:32:58 +03:00
Disty0 d3e3fb98b0 Don't override user set device_map 2025-05-27 21:45:52 +03:00
Disty0 b1b29e9001 SDNQ disable device_map = gpu with TE and LLM 2025-05-27 21:32:32 +03:00
Disty0 b724cd7c57 Update changelog 2025-05-27 21:21:42 +03:00
Disty0 5d3c1832b2 SDNQ add FP8 quants 2025-05-27 20:29:15 +03:00
Disty0 3618e39cff SDNQ use device_map = gpu 2025-05-27 19:46:30 +03:00
Disty0 73999ac710 Add soft gc to nncf quant layer 2025-05-27 16:24:04 +03:00
Disty0 e94128a02e SDNQ add force torch_gc to pre load mode 2025-05-27 16:11:04 +03:00
Disty0 dece497f10 Refactor SDNQ to use weights_dtype and rename decompress_int8_matmul to use_quantized_matmul 2025-05-27 15:49:21 +03:00
Disty0 79bb348927 SDNQ sort quant schemes by recommended order 2025-05-27 13:06:17 +03:00
Disty0 dec460e665 SDNQ use torch.bitwise ops instead of python 2025-05-27 03:02:36 +03:00
Disty0 280be31883 SDNQ fix Lora change 2025-05-27 00:08:32 +03:00
Disty0 4d9c2a8608 Cleanup 2025-05-26 22:41:12 +03:00
Disty0 84ddfb2868 SDNQ fix lora apply 2025-05-26 22:39:20 +03:00
Disty0 6dee9f5ac7 Fix HiDream teacache not reseting 2025-05-26 21:21:01 +03:00
Disty0 742cd61d1f Add TeaCache for HiDream 2025-05-26 19:59:43 +03:00
Disty0 687c50dcc8 SDNQ fix Lora 2025-05-26 19:48:45 +03:00
Disty0 ccf9deaf28 Move SDNQ to the top of the settings list 2025-05-26 18:30:50 +03:00
Disty0 02f15b28cc Cleanup 2025-05-26 15:57:17 +03:00
Disty0 91bb07f650 SDNQ remove unused args and simplify decompressors 2025-05-26 15:51:53 +03:00
Disty0 d2159af10e cleanup 2025-05-26 04:24:28 +03:00
Disty0 4ad404182d cleanup 2025-05-26 04:17:22 +03:00
Disty0 3f8ae754a0 Update readme 2025-05-26 03:35:25 +03:00
Disty0 46e9a9a631 IPEX disable Dynamic Attention by default on PyTorch 2.7 2025-05-26 03:03:17 +03:00
Disty0 5fcd0be79c Update changelog 2025-05-26 02:50:05 +03:00
Disty0 e314a7ca19 Update changelog 2025-05-26 02:49:12 +03:00
Disty0 17df7ba83b Cleanup whitespace 2025-05-26 02:41:29 +03:00
Disty0 4453efee76 Rename NNCF to SDNQ and rename quant schemes 2025-05-26 02:39:51 +03:00
Disty0 9c2e15433e NNCF set required_packages to None 2025-05-26 01:39:09 +03:00
Disty0 cbc1bfe710 Cleanup 2025-05-26 01:24:06 +03:00
Disty0 2d79380bd7 NNCF implement better layer hijacks and remove all NNCF imports 2025-05-26 01:12:28 +03:00
Vladimir Mandic af3a44ccbe optional skimage
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-05-24 08:58:04 +02:00
Vladimir Mandic bfc5c7c457 installer version check
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-05-24 08:42:13 +02:00
Disty0 85f00f9edb Enable dyn atten by default for ROCm 2025-05-23 18:24:50 +03:00
Vladimir Mandic 50e3a134ca Merge pull request #3941 from hypercryptoman/patch-1
Fix: Correct arguments for prompt_enhance.py apply method
2025-05-23 10:31:01 +02:00
Vladimir Mandic abc081d242 Merge branch 'dev' into patch-1 2025-05-23 10:30:33 +02:00
hypercryptoman ac05b96838 Update prompt_enhance.py 2025-05-19 13:55:16 +10:00
hypercryptoman 05fced7395 Update prompt_enhance.py 2025-05-19 13:53:24 +10:00
hypercryptoman ba2eaaf295 Fix: Correct model_file parameter usage for custom load button 2025-05-19 13:45:05 +10:00
Disty0 2b824daf64 Revert MIOPEN_FIND_ENFORCE 2025-05-18 21:28:44 +03:00
Disty0 7f2d77e956 ROCm set MIOPEN_FIND_ENFORCE to SEARCH 2025-05-18 16:36:27 +03:00
hypercryptoman b23162a36b Fix: Correct arguments for prompt_enhance.py apply method 2025-05-18 23:35:55 +10:00
Disty0 3d8390de9b IPEX return devices.dtype instead of bf16 2025-05-18 04:44:51 +03:00
Disty0 d0e6f01286 IPEX remove GradScaler and use torch.amp instead 2025-05-18 04:39:48 +03:00