Commit Graph

104 Commits (0a49961baaaa594313baffba7a000e4e98712c71)

Author SHA1 Message Date
Disty0 618097dac2 GradScaler patch for IPEX 2023-06-15 01:19:35 +03:00
Vladimir Mandic cb307399dd jumbo merge 2023-06-13 11:59:56 -04:00
Disty0 c9e58c9604 Fix train for IPEX 2023-06-12 00:21:32 +03:00
Disty0 f63dd1c92e Fix torch.linalg.solve with IPEX & Diffusers UniPC 2023-06-10 22:01:09 +03:00
Disty0 3bef3e3eee Train patches for IPEX 2023-06-07 17:25:11 +03:00
Vladimir Mandic efbe364f7d js optimizations 2023-06-05 14:26:01 -04:00
Disty0 c52fb69dde Fix bf16 test 2023-06-05 20:49:18 +03:00
Vladimir Mandic c0a824d8c6 add extra networks to xyz 2023-06-05 10:32:08 -04:00
Disty0 8bef48e501 Fix GroupNorm.forward with IPEX 2023-06-04 12:22:56 +03:00
Disty0 4265692505 Fix GradScaler doesn't exist for XPU 2023-06-03 17:02:44 +03:00
Vladimir Mandic 1f988d1df6 cleanup 2023-06-02 19:39:44 -04:00
Vince Navarro c30eb90aff
Remove stray print 2023-06-01 17:28:13 -04:00
Vince Navarro 523dbaf8dc
Add XPU support for --device-id 2023-06-01 16:42:21 -04:00
Vladimir Mandic 9bf0b1ae1f allow experimental to override precision 2023-05-28 07:46:47 -04:00
Vladimir Mandic f8884bc051 fix hip detection 2023-05-25 09:13:57 -04:00
Vladimir Mandic 9e66d88e21 add mps defaults 2023-05-24 15:21:49 -04:00
Vladimir Mandic 684851ae34 set default optimizer 2023-05-24 13:50:01 -04:00
Vladimir Mandic 0acc7d3b86 fix redirector 2023-05-24 08:49:33 -04:00
Vladimir Mandic ea0780339a fixes 2023-05-21 08:17:36 -04:00
Vladimir Mandic 9033499e08 add manual seed 2023-05-19 08:34:43 -04:00
Vladimir Mandic 0ccda9bc8b jumbo patch 2023-05-17 14:15:55 -04:00
Vladimir Mandic 5250ba4be3 force no-half with directml 2023-05-16 21:20:36 -04:00
Vladimir Mandic 8350b93a5c add force latent sampler 2023-05-15 09:32:20 -04:00
Vladimir Mandic 5134471bc8 dml autocast 2023-05-14 13:24:59 -04:00
Vladimir Mandic 618a1703ae update cudnn benchmark setting 2023-05-14 12:28:37 -04:00
Vladimir Mandic 760f5fb89a add extra debug messages 2023-05-14 12:26:15 -04:00
Vladimir Mandic a652270999 fix 2023-05-13 12:26:00 -04:00
Vladimir Mandic a2923064a5 update cudnn 2023-05-13 11:52:31 -04:00
Vladimir Mandic d96ab6a1ae update directml 2023-05-13 11:21:11 -04:00
Vladimir Mandic a2485cf7ef update 2023-05-12 21:12:24 -04:00
Vladimir Mandic 1921504e64 enable dynamo compile 2023-05-12 15:58:00 -04:00
Vladimir Mandic daf90cb6b4 add performance note 2023-05-12 14:23:51 -04:00
Vladimir Mandic 62dda471a3 process images in threads 2023-05-12 14:21:26 -04:00
Vladimir Mandic 1943bfea88 use cudnn workaround 2023-05-11 22:24:12 -04:00
Vladimir Mandic e038bf1549 aggressive gc 2023-05-10 16:03:55 -04:00
Vladimir Mandic 41182009cb switch some cmdopts to opts 2023-05-08 09:27:50 -04:00
Vladimir Mandic 1360c6422a add fp16 test 2023-05-08 09:27:50 -04:00
Disty0 8171d57c36 Remove unnecessary IPEX imports 2023-05-04 02:34:34 +03:00
Vladimir Mandic 5d8c787a7b restart server redesign 2023-05-03 17:20:22 -04:00
Disty0 53f3567224 Use cmd_args parser instead of launch.py 2023-05-03 21:25:23 +03:00
Disty0 7577a09528 Add IPEX Optimizers and use XPU instead of CPU when using IPEX 2023-05-03 18:12:38 +03:00
Disty0 de8d0bef9f More patches and Import IPEX after Torch 2023-04-30 18:19:37 +03:00
Disty0 a720a670e8 More patches and less import shared 2023-04-30 16:01:17 +03:00
Disty0 b075d3c8fd Intel ARC Support 2023-04-30 15:13:56 +03:00
Seunghoon Lee d2d5011bd3
Implement memory estimation for AMDGPUs.
Stable.
2023-04-26 17:44:32 +09:00
Seunghoon Lee a49a8f8b46
First DirectML implementation.
Unstable and not tested.
2023-04-25 01:43:19 +09:00
Vladimir Mandic 61e9a1970c add exception around torch properties 2023-04-22 08:35:17 -04:00
Vladimir Mandic cf277e7326 fix dtype logic 2023-04-21 15:04:05 -04:00
Vladimir Mandic 57204b3d70 disable xformers/sdp if cannot be used 2023-04-21 11:32:19 -04:00
Vladimir Mandic 7939a1649d parse model preload 2023-04-20 23:19:25 -04:00