From a4cb96d4ae82741be9f0d072a37af3ae39521379 Mon Sep 17 00:00:00 2001 From: brkirch Date: Sat, 11 Mar 2023 17:35:17 -0500 Subject: Remove test, use bool tensor fix by default The test isn't working correctly on macOS 13.3 and the bool tensor fix for cumsum is currently always needed anyway, so enable the fix by default. --- modules/mac_specific.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'modules/mac_specific.py') diff --git a/modules/mac_specific.py b/modules/mac_specific.py index ddcea53b..18e6ff72 100644 --- a/modules/mac_specific.py +++ b/modules/mac_specific.py @@ -23,7 +23,7 @@ def cumsum_fix(input, cumsum_func, *args, **kwargs): output_dtype = kwargs.get('dtype', input.dtype) if output_dtype == torch.int64: return cumsum_func(input.cpu(), *args, **kwargs).to(input.device) - elif cumsum_needs_bool_fix and output_dtype == torch.bool or cumsum_needs_int_fix and (output_dtype == torch.int8 or output_dtype == torch.int16): + elif output_dtype == torch.bool or cumsum_needs_int_fix and (output_dtype == torch.int8 or output_dtype == torch.int16): return cumsum_func(input.to(torch.int32), *args, **kwargs).to(torch.int64) return cumsum_func(input, *args, **kwargs) @@ -45,7 +45,6 @@ if has_mps: CondFunc('torch.Tensor.numpy', lambda orig_func, self, *args, **kwargs: orig_func(self.detach(), *args, **kwargs), lambda _, self, *args, **kwargs: self.requires_grad) elif version.parse(torch.__version__) > version.parse("1.13.1"): cumsum_needs_int_fix = not torch.Tensor([1,2]).to(torch.device("mps")).equal(torch.ShortTensor([1,1]).to(torch.device("mps")).cumsum(0)) - cumsum_needs_bool_fix = not torch.BoolTensor([True,True]).to(device=torch.device("mps"), dtype=torch.int64).equal(torch.BoolTensor([True,False]).to(torch.device("mps")).cumsum(0)) cumsum_fix_func = lambda orig_func, input, *args, **kwargs: cumsum_fix(input, orig_func, *args, **kwargs) CondFunc('torch.cumsum', cumsum_fix_func, None) CondFunc('torch.Tensor.cumsum', cumsum_fix_func, None) -- cgit v1.2.1 From c5142e2fbecb50531a55aa804ea132c5d870858c Mon Sep 17 00:00:00 2001 From: brkirch Date: Fri, 24 Mar 2023 02:58:18 -0400 Subject: Add workaround for broken nn.Linear on macOS 13.2 Credit to danieldk (https://github.com/explosion/curated-transformers/pull/124) for the workaround this is based on. --- modules/mac_specific.py | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'modules/mac_specific.py') diff --git a/modules/mac_specific.py b/modules/mac_specific.py index 18e6ff72..3a170f60 100644 --- a/modules/mac_specific.py +++ b/modules/mac_specific.py @@ -1,4 +1,5 @@ import torch +import platform from modules import paths from modules.sd_hijack_utils import CondFunc from packaging import version @@ -32,6 +33,10 @@ if has_mps: # MPS fix for randn in torchsde CondFunc('torchsde._brownian.brownian_interval._randn', lambda _, size, dtype, device, seed: torch.randn(size, dtype=dtype, device=torch.device("cpu"), generator=torch.Generator(torch.device("cpu")).manual_seed(int(seed))).to(device), lambda _, size, dtype, device, seed: device.type == 'mps') + if platform.mac_ver()[0].startswith("13.2."): + # MPS workaround for https://github.com/pytorch/pytorch/issues/95188, thanks to danieldk (https://github.com/explosion/curated-transformers/pull/124) + CondFunc('torch.nn.functional.linear', lambda _, input, weight, bias: (torch.matmul(input, weight.t()) + bias) if bias is not None else torch.matmul(input, weight.t()), lambda _, input, weight, bias: input.numel() > 10485760) + if version.parse(torch.__version__) < version.parse("1.13"): # PyTorch 1.13 doesn't need these fixes but unfortunately is slower and has regressions that prevent training from working -- cgit v1.2.1 From 27fe3eb6a9d8f866af8b90dff18f4445124702da Mon Sep 17 00:00:00 2001 From: brkirch Date: Fri, 24 Mar 2023 03:04:47 -0400 Subject: Add workaround for MPS layer_norm on PyTorch 2.0 On PyTorch 2.0, with MPS layer_norm only accepts float32 inputs. This was fixed shortly after 2.0 was finalized so the workaround can be applied with an exact version match. --- modules/mac_specific.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'modules/mac_specific.py') diff --git a/modules/mac_specific.py b/modules/mac_specific.py index 3a170f60..6fe8dea0 100644 --- a/modules/mac_specific.py +++ b/modules/mac_specific.py @@ -54,4 +54,6 @@ if has_mps: CondFunc('torch.cumsum', cumsum_fix_func, None) CondFunc('torch.Tensor.cumsum', cumsum_fix_func, None) CondFunc('torch.narrow', lambda orig_func, *args, **kwargs: orig_func(*args, **kwargs).clone(), None) - + if version.parse(torch.__version__) == version.parse("2.0"): + # MPS workaround for https://github.com/pytorch/pytorch/issues/96113 + CondFunc('torch.nn.functional.layer_norm', lambda orig_func, x, normalized_shape, weight, bias, eps, **kwargs: orig_func(x.float(), normalized_shape, weight.float() if weight is not None else None, bias.float() if bias is not None else bias, eps).to(x.dtype), lambda *args, **kwargs: len(args) == 6) -- cgit v1.2.1