aboutsummaryrefslogtreecommitdiff
path: root/modules/devices.py
AgeCommit message (Expand)Author
2023-12-31Add utility to inspect a model's parameters (to get dtype/device)Aarni Koskela
2023-12-03Merge branch 'dev' into test-fp8Kohaku-Blueleaf
2023-12-02Merge pull request #14171 from Nuullll/ipexAUTOMATIC1111
2023-12-02Merge branch 'dev' into test-fp8Kohaku-Blueleaf
2023-12-02Merge pull request #14131 from read-0nly/patch-1AUTOMATIC1111
2023-12-02Disable ipex autocast due to its bad perfNuullll
2023-11-30Initial IPEX supportNuullll
2023-11-27Update devices.pyobsol
2023-11-19Better namingKohaku-Blueleaf
2023-11-19Use options instead of cmd_argsKohaku-Blueleaf
2023-10-28Add MPS manual castKohakuBlueleaf
2023-10-28ManualCast for 10/16 series gpuKohaku-Blueleaf
2023-10-24Add CPU fp8 supportKohaku-Blueleaf
2023-09-09fix for crash when running #12924 without --device-idAUTOMATIC1111
2023-08-31More accurate check for enabling cuDNN benchmark on 16XX cardscatboxanon
2023-08-09split shared.py into multiple files; should resolve all circular reference im...AUTOMATIC1111
2023-08-09rework RNG to use generators instead of generating noises beforehandAUTOMATIC1111
2023-08-03rework torchsde._brownian.brownian_interval replacement to use device.randn_l...AUTOMATIC1111
2023-08-03add NV option for Random number generator source setting, which allows to gen...AUTOMATIC1111
2023-07-11Fix MPS cache cleanupAarni Koskela
2023-07-08added torch.mps.empty_cache() to torch_gc()AUTOMATIC1111
2023-06-05Remove a bunch of unused/vestigial codeAarni Koskela
2023-05-21run basic torch calculation at startup in parallel to reduce the performance ...AUTOMATIC
2023-05-10ruff auto fixesAUTOMATIC
2023-04-29rename CPU RNG to RNG source in settings, add infotext and parameters copypas...AUTOMATIC
2023-04-18Option to use CPU for random number generation.Deciare
2023-02-01Refactor Mac specific code to a separate filebrkirch
2023-02-01Refactor MPS fixes to CondFuncbrkirch
2023-02-01MPS fix is still needed :(brkirch
2023-01-28Merge pull request #7309 from brkirch/fix-embeddingsAUTOMATIC1111
2023-01-28Remove MPS fix no longer needed for PyTorchbrkirch
2023-01-28Refactor conditional casting, fix upscalersbrkirch
2023-01-27clarify the option to disable NaN check.AUTOMATIC
2023-01-27remove the need to place configs near modelsAUTOMATIC
2023-01-25Add UI setting for upcasting attention to float32brkirch
2023-01-25Add option for float32 sampling with float16 UNetbrkirch
2023-01-19Merge pull request #6922 from brkirch/cumsum-fixAUTOMATIC1111
2023-01-17Fix cumsum for MPS in newer torchbrkirch
2023-01-17disable the new NaN check for the CIAUTOMATIC
2023-01-16Add a check and explanation for tensor with all NaNs.AUTOMATIC
2023-01-05Add support for PyTorch nightly and local buildsbrkirch
2022-12-17Add numpy fix for MPS on PyTorch 1.12.1brkirch
2022-12-03add built-in extension systemAUTOMATIC
2022-12-03add comment for #4407 and remove seemingly unnecessary cudnn.enabledAUTOMATIC
2022-12-03fix #4407 breaking UI entirely for card other than ones related to the PRAUTOMATIC
2022-12-03Merge pull request #4407 from yoinked-h/patch-1AUTOMATIC1111
2022-11-30Rework MPS randn fix, add randn_like fixbrkirch
2022-11-27Merge pull request #4918 from brkirch/pytorch-fixesAUTOMATIC1111
2022-11-27eliminate duplicated code from #5095AUTOMATIC
2022-11-26torch.cuda.empty_cache() defaults to cuda:0 device unless explicitly set othe...Matthew McGoogan
generated by cgit v1.2.1 (git 2.18.0) at 2025-05-29 10:20:53 +0000