2a8a60c2c5
Add --precision half cmd option
2024-05-16 19:50:06 -04:00
e3fa46f26f
Fix various typos with crate-ci/typos
2024-03-04 08:42:07 +02:00
cc3f604310
Update
2024-01-31 12:29:58 +08:00
74ff85a1a1
Merge branch 'dev' into npu_support
2024-01-30 19:15:41 +08:00
f9ba7e648a
Revert "Try to reverse the dtype checking mechanism"
...
This reverts commit d243e24f53
2024-01-29 22:54:12 +08:00
d243e24f53
Try to reverse the dtype checking mechanism
2024-01-29 22:49:45 +08:00
6e7f0860f7
linting
2024-01-29 22:46:43 +08:00
750dd6014a
Fix potential bugs
2024-01-29 22:27:53 +08:00
ec124607f4
Add NPU Support
2024-01-29 19:25:06 +08:00
4a66d2fb22
Avoid exceptions to be silenced
2024-01-20 16:33:59 +08:00
81126027f5
Avoid early disable
2024-01-20 16:31:12 +08:00
0181c1f76b
Fix nested manual cast
2024-01-19 00:14:03 +08:00
ca671e5d7b
rearrange if-statements for cpu
2024-01-09 23:30:55 +08:00
58d5b042cd
Apply the correct behavior of precision='full'
2024-01-09 23:23:40 +08:00
1fd69655fe
Revert "Apply correct inference precision implementation"
...
This reverts commit e00365962b
2024-01-09 23:15:05 +08:00
e00365962b
Apply correct inference precision implementation
2024-01-09 23:13:34 +08:00
c2c05fcca8
linting and debugs
2024-01-09 22:53:58 +08:00
42e6df723c
Fix bugs when arg dtype doesn't match
2024-01-09 22:39:39 +08:00
209c26a1cb
improve efficiency and support more device
2024-01-09 22:11:44 +08:00
a70dfb64a8
change import statements for #14478
2023-12-31 22:38:30 +03:00
5768afc776
Add utility to inspect a model's parameters (to get dtype/device)
2023-12-31 13:22:43 +02:00
9a15ae2a92
Merge branch 'dev' into test-fp8
2023-12-03 10:54:54 +08:00
af5f0734c9
Merge pull request #14171 from Nuullll/ipex
...
Initial IPEX support for Intel Arc GPU
2023-12-02 19:22:32 +03:00
110485d5bb
Merge branch 'dev' into test-fp8
2023-12-02 17:00:09 +08:00
88736b5557
Merge pull request #14131 from read-0nly/patch-1
...
Update devices.py - Make 'use-cpu all' actually apply to 'all'
2023-12-02 09:46:19 +03:00
7499148ad4
Disable ipex autocast due to its bad perf
2023-12-02 14:00:46 +08:00
8b40f475a3
Initial IPEX support
2023-11-30 20:22:46 +08:00
3cd6e1d0a0
Update devices.py
...
fixes issue where "--use-cpu" all properly makes SD run on CPU but leaves ControlNet (and other extensions, I presume) pointed at GPU, causing a crash in ControlNet caused by a mismatch between devices between SD and CN
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/14097
2023-11-27 19:21:43 -05:00
043d2edcf6
Better naming
2023-11-19 15:56:31 +08:00
598da5cd49
Use options instead of cmd_args
2023-11-19 15:50:06 +08:00
ddc2a3499b
Add MPS manual cast
2023-10-28 16:52:35 +08:00
d4d3134f6d
ManualCast for 10/16 series gpu
2023-10-28 15:24:26 +08:00
eaa9f5162f
Add CPU fp8 support
...
Since norm layer need fp32, I only convert the linear operation layer(conv2d/linear)
And TE have some pytorch function not support bf16 amp in CPU. I add a condition to indicate if the autocast is for unet.
2023-10-24 01:49:05 +08:00
46375f0592
fix for crash when running #12924 without --device-id
2023-09-09 09:39:37 +03:00
5681bf8016
More accurate check for enabling cuDNN benchmark on 16XX cards
2023-08-31 14:57:16 -04:00
386245a264
split shared.py into multiple files; should resolve all circular reference import errors related to shared.py
2023-08-09 10:25:35 +03:00
0d5dc9a6e7
rework RNG to use generators instead of generating noises beforehand
2023-08-09 08:43:31 +03:00
fca42949a3
rework torchsde._brownian.brownian_interval replacement to use device.randn_local and respect the NV setting.
2023-08-03 07:18:55 +03:00
84b6fcd02c
add NV option for Random number generator source setting, which allows to generate same pictures on CPU/AMD/Mac as on NVidia videocards.
2023-08-03 00:00:23 +03:00
b85fc7187d
Fix MPS cache cleanup
...
Importing torch does not import torch.mps so the call failed.
2023-07-11 12:51:05 +03:00
da8916f926
added torch.mps.empty_cache() to torch_gc()
...
changed a bunch of places that use torch.cuda.empty_cache() to use torch_gc() instead
2023-07-08 17:13:18 +03:00
ba70a220e3
Remove a bunch of unused/vestigial code
...
As found by Vulture and some eyes
2023-06-05 22:43:57 +03:00
8faac8b963
run basic torch calculation at startup in parallel to reduce the performance impact of first generation
2023-05-21 21:55:14 +03:00
028d3f6425
ruff auto fixes
2023-05-10 11:05:02 +03:00
5fe0dd79be
rename CPU RNG to RNG source in settings, add infotext and parameters copypaste support to RNG source
2023-04-29 11:29:37 +03:00
d40e44ade4
Option to use CPU for random number generation.
...
Makes a given manual seed generate the same images across different
platforms, independently of the GPU architecture in use.
Fixes #9613 .
2023-04-18 23:27:46 -04:00
1b8af15f13
Refactor Mac specific code to a separate file
...
Move most Mac related code to a separate file, don't even load it unless web UI is run under macOS.
2023-02-01 14:05:56 -05:00
2217331cd1
Refactor MPS fixes to CondFunc
2023-02-01 06:36:22 -05:00
7738c057ce
MPS fix is still needed :(
...
Apparently I did not test with large enough images to trigger the bug with torch.narrow on MPS
2023-02-01 05:23:58 -05:00
fecb990deb
Merge pull request #7309 from brkirch/fix-embeddings
...
Fix embeddings, upscalers, and refactor `--upcast-sampling`
2023-01-28 18:44:36 +03:00
huchenlei