aboutsummaryrefslogtreecommitdiffstats
path: root/modules/devices.py
AgeCommit message (Collapse)AuthorLines
2024-01-31Updatewangshuai09-0/+7
2024-01-30Merge branch 'dev' into npu_supportwangshuai09-3/+95
2024-01-29Revert "Try to reverse the dtype checking mechanism"Kohaku-Blueleaf-2/+5
This reverts commit d243e24f539d717b221992e894a5db5a321bf3cd.
2024-01-29Try to reverse the dtype checking mechanismKohaku-Blueleaf-5/+2
2024-01-29lintingKohaku-Blueleaf-1/+0
2024-01-29Fix potential bugsKohaku-Blueleaf-2/+7
2024-01-29Add NPU Supportwangshuai09-2/+7
2024-01-20Avoid exceptions to be silencedKohaku-Blueleaf-6/+5
2024-01-20Avoid early disableKohaku-Blueleaf-0/+4
2024-01-19Fix nested manual castKohaku-Blueleaf-1/+5
2024-01-09rearrange if-statements for cpuKohaku-Blueleaf-3/+3
2024-01-09Apply the correct behavior of precision='full'Kohaku-Blueleaf-4/+7
2024-01-09Revert "Apply correct inference precision implementation"Kohaku-Blueleaf-33/+9
This reverts commit e00365962b17550a42235d1fbe2ad2c7cc4b8961.
2024-01-09Apply correct inference precision implementationKohaku-Blueleaf-9/+33
2024-01-09linting and debugsKohaku-Blueleaf-6/+6
2024-01-09Fix bugs when arg dtype doesn't matchKohakuBlueleaf-15/+10
2024-01-09improve efficiency and support more deviceKohaku-Blueleaf-17/+43
2023-12-31change import statements for #14478AUTOMATIC1111-2/+2
2023-12-31Add utility to inspect a model's parameters (to get dtype/device)Aarni Koskela-1/+2
2023-12-03Merge branch 'dev' into test-fp8Kohaku-Blueleaf-0/+13
2023-12-02Merge pull request #14171 from Nuullll/ipexAUTOMATIC1111-0/+13
Initial IPEX support for Intel Arc GPU
2023-12-02Merge branch 'dev' into test-fp8Kohaku-Blueleaf-1/+1
2023-12-02Merge pull request #14131 from read-0nly/patch-1AUTOMATIC1111-1/+1
Update devices.py - Make 'use-cpu all' actually apply to 'all'
2023-12-02Disable ipex autocast due to its bad perfNuullll-7/+13
2023-11-30Initial IPEX supportNuullll-2/+9
2023-11-27Update devices.pyobsol-1/+1
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
2023-11-19Better namingKohaku-Blueleaf-3/+3
2023-11-19Use options instead of cmd_argsKohaku-Blueleaf-11/+14
2023-10-28Add MPS manual castKohakuBlueleaf-1/+5
2023-10-28ManualCast for 10/16 series gpuKohaku-Blueleaf-6/+51
2023-10-24Add CPU fp8 supportKohaku-Blueleaf-1/+5
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.
2023-09-09fix for crash when running #12924 without --device-idAUTOMATIC1111-1/+1
2023-08-31More accurate check for enabling cuDNN benchmark on 16XX cardscatboxanon-1/+2
2023-08-09split shared.py into multiple files; should resolve all circular reference ↵AUTOMATIC1111-9/+1
import errors related to shared.py
2023-08-09rework RNG to use generators instead of generating noises beforehandAUTOMATIC1111-79/+2
2023-08-03rework torchsde._brownian.brownian_interval replacement to use ↵AUTOMATIC1111-6/+38
device.randn_local and respect the NV setting.
2023-08-03add NV option for Random number generator source setting, which allows to ↵AUTOMATIC1111-2/+37
generate same pictures on CPU/AMD/Mac as on NVidia videocards.
2023-07-11Fix MPS cache cleanupAarni Koskela-2/+3
Importing torch does not import torch.mps so the call failed.
2023-07-08added torch.mps.empty_cache() to torch_gc()AUTOMATIC1111-0/+3
changed a bunch of places that use torch.cuda.empty_cache() to use torch_gc() instead
2023-06-05Remove a bunch of unused/vestigial codeAarni Koskela-7/+0
As found by Vulture and some eyes
2023-05-21run basic torch calculation at startup in parallel to reduce the performance ↵AUTOMATIC-0/+18
impact of first generation
2023-05-10ruff auto fixesAUTOMATIC-1/+1
2023-04-29rename CPU RNG to RNG source in settings, add infotext and parameters ↵AUTOMATIC-2/+2
copypaste support to RNG source
2023-04-18Option to use CPU for random number generation.Deciare-2/+6
Makes a given manual seed generate the same images across different platforms, independently of the GPU architecture in use. Fixes #9613.
2023-02-01Refactor Mac specific code to a separate filebrkirch-45/+7
Move most Mac related code to a separate file, don't even load it unless web UI is run under macOS.
2023-02-01Refactor MPS fixes to CondFuncbrkirch-36/+14
2023-02-01MPS fix is still needed :(brkirch-0/+3
Apparently I did not test with large enough images to trigger the bug with torch.narrow on MPS
2023-01-28Merge pull request #7309 from brkirch/fix-embeddingsAUTOMATIC1111-3/+8
Fix embeddings, upscalers, and refactor `--upcast-sampling`
2023-01-28Remove MPS fix no longer needed for PyTorchbrkirch-3/+0
The torch.narrow fix was required for nightly PyTorch builds for a while to prevent a hard crash, but newer nightly builds don't have this issue.
2023-01-28Refactor conditional casting, fix upscalersbrkirch-0/+8
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-07 17:43:16 +0000