mirror of
https://github.com/vladmandic/automatic
synced 2026-09-18 16:54:33 +02:00
Move ipex fixes into it's own folder
This commit is contained in:
Disty0
+2
-85
@@ -168,6 +168,8 @@ def set_cuda_params():
|
||||
args = cmd_args.parser.parse_args()
|
||||
if args.use_ipex or (hasattr(torch, 'xpu') and torch.xpu.is_available()):
|
||||
backend = 'ipex'
|
||||
from modules.ipex_specific import ipex_init
|
||||
ipex_init()
|
||||
elif args.use_directml:
|
||||
backend = 'directml'
|
||||
elif torch.cuda.is_available() and torch.version.cuda:
|
||||
@@ -179,91 +181,6 @@ elif sys.platform == 'darwin':
|
||||
else:
|
||||
backend = 'cpu'
|
||||
|
||||
if backend == 'ipex':
|
||||
import os
|
||||
def ipex_no_cuda(orig_func, *args, **kwargs): # pylint: disable=redefined-outer-name
|
||||
torch.cuda.is_available = lambda: False
|
||||
orig_func(*args, **kwargs)
|
||||
torch.cuda.is_available = torch.xpu.is_available
|
||||
|
||||
#Fix functions with ipex
|
||||
torch.cuda.is_available = torch.xpu.is_available
|
||||
torch.cuda.device = torch.xpu.device
|
||||
torch.cuda.device_count = torch.xpu.device_count
|
||||
torch.cuda.current_device = torch.xpu.current_device
|
||||
torch.cuda.get_device_name = torch.xpu.get_device_name
|
||||
torch.cuda.get_device_properties = torch.xpu.get_device_properties
|
||||
torch._utils._get_available_device_type = lambda: "xpu" # pylint: disable=protected-access
|
||||
torch.cuda.set_device = torch.xpu.set_device
|
||||
torch.Tensor.cuda = torch.Tensor.xpu
|
||||
|
||||
torch.cuda.empty_cache = torch.xpu.empty_cache if "WSL2" not in os.popen("uname -a").read() else lambda: None
|
||||
torch.cuda.ipc_collect = lambda: None
|
||||
torch.cuda.memory_stats = torch.xpu.memory_stats
|
||||
torch.cuda.mem_get_info = lambda device=None: [(torch.xpu.get_device_properties(device).total_memory - torch.xpu.memory_allocated(device)), torch.xpu.get_device_properties(device).total_memory]
|
||||
torch.cuda.memory_allocated = torch.xpu.memory_allocated
|
||||
torch.cuda.max_memory_allocated = torch.xpu.max_memory_allocated
|
||||
torch.cuda.reset_peak_memory_stats = torch.xpu.reset_peak_memory_stats
|
||||
torch.cuda.utilization = lambda: 0
|
||||
|
||||
torch.cuda.get_rng_state_all = torch.xpu.get_rng_state_all
|
||||
torch.cuda.set_rng_state_all = torch.xpu.set_rng_state_all
|
||||
try:
|
||||
torch.cuda.amp.GradScaler = torch.xpu.amp.GradScaler
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
from modules.sd_hijack_utils import CondFunc
|
||||
#Broken functions when torch.cuda.is_available is True:
|
||||
CondFunc('torch.utils.data.dataloader._BaseDataLoaderIter.__init__',
|
||||
lambda orig_func, *args, **kwargs: ipex_no_cuda(orig_func, *args, **kwargs),
|
||||
lambda orig_func, *args, **kwargs: True)
|
||||
|
||||
#Functions with dtype errors:
|
||||
CondFunc('torch.nn.modules.GroupNorm.forward',
|
||||
lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
|
||||
lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
|
||||
CondFunc('torch.nn.modules.Linear.forward',
|
||||
lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
|
||||
lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
|
||||
#Diffusers bfloat16:
|
||||
CondFunc('torch.nn.modules.Conv2d._conv_forward',
|
||||
lambda orig_func, self, input, weight, bias=None: orig_func(self, input.to(weight.data.dtype), weight, bias=bias),
|
||||
lambda orig_func, self, input, weight, bias=None: input.dtype != weight.data.dtype)
|
||||
|
||||
#Functions that does not work with the XPU:
|
||||
#UniPC:
|
||||
CondFunc('torch.linalg.solve',
|
||||
lambda orig_func, A, B, *args, left=True, out=None: orig_func(A.to("cpu"), B.to("cpu"), *args, left=left, out=out).to(get_cuda_device_string()),
|
||||
lambda orig_func, A, B, *args, left=True, out=None: A.device != torch.device("cpu") or B.device != torch.device("cpu"))
|
||||
#SDE Samplers:
|
||||
CondFunc('torch.Generator',
|
||||
lambda orig_func, device: torch.xpu.Generator(device),
|
||||
lambda orig_func, device: device != torch.device("cpu") and device != "cpu")
|
||||
#Latent antialias:
|
||||
CondFunc('torch.nn.functional.interpolate',
|
||||
lambda orig_func, input, size=None, scale_factor=None, mode='nearest', align_corners=None, recompute_scale_factor=None, antialias=False: orig_func(input.to("cpu"), size=size, scale_factor=scale_factor, mode=mode, align_corners=align_corners, recompute_scale_factor=recompute_scale_factor, antialias=antialias).to(get_cuda_device_string()),
|
||||
lambda orig_func, input, size=None, scale_factor=None, mode='nearest', align_corners=None, recompute_scale_factor=None, antialias=False: antialias)
|
||||
#Diffusers Float64 (ARC GPUs doesn't support double or Float64):
|
||||
if not torch.xpu.has_fp64_dtype():
|
||||
CondFunc('torch.from_numpy',
|
||||
lambda orig_func, ndarray: orig_func(ndarray.astype('float32')),
|
||||
lambda orig_func, ndarray: ndarray.dtype == float)
|
||||
#ControlNet and TiledVAE:
|
||||
CondFunc('torch.batch_norm',
|
||||
lambda orig_func, input, running_mean=None, running_var=None, weight=None, bias=None, training=False, momentum=0.1, eps=1e-5, cudnn_enabled=True: orig_func(input,
|
||||
running_mean if running_mean is not None else torch.ones(input.size()[1], device=get_cuda_device_string()),
|
||||
running_var if running_var is not None else torch.zeros(input.size()[1], device=get_cuda_device_string()),
|
||||
weight, bias, training, momentum, eps, cudnn_enabled),
|
||||
lambda orig_func, input, running_mean=None, running_var=None, weight=None, bias=None, training=False, momentum=0.1, eps=1e-5, cudnn_enabled=True: input.device != torch.device("cpu"))
|
||||
#ControlNet
|
||||
CondFunc('torch.instance_norm',
|
||||
lambda orig_func, input, running_mean=None, running_var=None, weight=None, bias=None, use_input_stats=True, momentum=0.1, eps=1e-5, cudnn_enabled=True: orig_func(input,
|
||||
running_mean if running_mean is not None else torch.ones(input.size()[1], device=get_cuda_device_string()),
|
||||
running_var if running_var is not None else torch.zeros(input.size()[1], device=get_cuda_device_string()),
|
||||
weight, bias, use_input_stats, momentum, eps, cudnn_enabled),
|
||||
lambda orig_func, input, running_mean=None, running_var=None, weight=None, bias=None, use_input_stats=True, momentum=0.1, eps=1e-5, cudnn_enabled=True: input.device != torch.device("cpu"))
|
||||
|
||||
if backend == "directml":
|
||||
directml_init()
|
||||
|
||||
|
||||
@@ -0,0 +1,89 @@
|
||||
import os
|
||||
import torch
|
||||
import intel_extension_for_pytorch as ipex
|
||||
from modules import shared
|
||||
from modules.sd_hijack_utils import CondFunc
|
||||
|
||||
def ipex_no_cuda(orig_func, *args, **kwargs): # pylint: disable=redefined-outer-name
|
||||
torch.cuda.is_available = lambda: False
|
||||
orig_func(*args, **kwargs)
|
||||
torch.cuda.is_available = torch.xpu.is_available
|
||||
|
||||
def ipex_init():
|
||||
#Fix functions with ipex
|
||||
torch.cuda.is_available = torch.xpu.is_available
|
||||
torch.cuda.device = torch.xpu.device
|
||||
torch.cuda.device_count = torch.xpu.device_count
|
||||
torch.cuda.current_device = torch.xpu.current_device
|
||||
torch.cuda.get_device_name = torch.xpu.get_device_name
|
||||
torch.cuda.get_device_properties = torch.xpu.get_device_properties
|
||||
torch._utils._get_available_device_type = lambda: "xpu" # pylint: disable=protected-access
|
||||
torch.cuda.set_device = torch.xpu.set_device
|
||||
torch.Tensor.cuda = torch.Tensor.xpu
|
||||
|
||||
torch.xpu.empty_cache = torch.xpu.empty_cache if "WSL2" not in os.popen("uname -a").read() else lambda: None
|
||||
torch.cuda.empty_cache = torch.xpu.empty_cache
|
||||
torch.cuda.ipc_collect = lambda: None
|
||||
torch.cuda.memory_stats = torch.xpu.memory_stats
|
||||
torch.cuda.mem_get_info = lambda device=None: [(torch.xpu.get_device_properties(device).total_memory - torch.xpu.memory_allocated(device)), torch.xpu.get_device_properties(device).total_memory]
|
||||
torch.cuda.memory_allocated = torch.xpu.memory_allocated
|
||||
torch.cuda.max_memory_allocated = torch.xpu.max_memory_allocated
|
||||
torch.cuda.reset_peak_memory_stats = torch.xpu.reset_peak_memory_stats
|
||||
torch.cuda.utilization = lambda: 0
|
||||
|
||||
torch.cuda.get_rng_state_all = torch.xpu.get_rng_state_all
|
||||
torch.cuda.set_rng_state_all = torch.xpu.set_rng_state_all
|
||||
try:
|
||||
torch.cuda.amp.GradScaler = torch.xpu.amp.GradScaler
|
||||
except Exception:
|
||||
torch.cuda.amp.GradScaler = ipex.cpu.autocast._grad_scaler.GradScaler
|
||||
|
||||
#Broken functions when torch.cuda.is_available is True:
|
||||
CondFunc('torch.utils.data.dataloader._BaseDataLoaderIter.__init__',
|
||||
lambda orig_func, *args, **kwargs: ipex_no_cuda(orig_func, *args, **kwargs),
|
||||
lambda orig_func, *args, **kwargs: True)
|
||||
|
||||
#Functions with dtype errors:
|
||||
CondFunc('torch.nn.modules.GroupNorm.forward',
|
||||
lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
|
||||
lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
|
||||
CondFunc('torch.nn.modules.Linear.forward',
|
||||
lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
|
||||
lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
|
||||
#Diffusers bfloat16:
|
||||
CondFunc('torch.nn.modules.Conv2d._conv_forward',
|
||||
lambda orig_func, self, input, weight, bias=None: orig_func(self, input.to(weight.data.dtype), weight, bias=bias),
|
||||
lambda orig_func, self, input, weight, bias=None: input.dtype != weight.data.dtype)
|
||||
|
||||
#Functions that does not work with the XPU:
|
||||
#UniPC:
|
||||
CondFunc('torch.linalg.solve',
|
||||
lambda orig_func, A, B, *args, left=True, out=None: orig_func(A.to("cpu"), B.to("cpu"), *args, left=left, out=out).to(shared.device),
|
||||
lambda orig_func, A, B, *args, left=True, out=None: A.device != torch.device("cpu") or B.device != torch.device("cpu"))
|
||||
#SDE Samplers:
|
||||
CondFunc('torch.Generator',
|
||||
lambda orig_func, device: torch.xpu.Generator(device),
|
||||
lambda orig_func, device: device != torch.device("cpu") and device != "cpu")
|
||||
#Latent antialias:
|
||||
CondFunc('torch.nn.functional.interpolate',
|
||||
lambda orig_func, input, size=None, scale_factor=None, mode='nearest', align_corners=None, recompute_scale_factor=None, antialias=False: orig_func(input.to("cpu"), size=size, scale_factor=scale_factor, mode=mode, align_corners=align_corners, recompute_scale_factor=recompute_scale_factor, antialias=antialias).to(shared.device),
|
||||
lambda orig_func, input, size=None, scale_factor=None, mode='nearest', align_corners=None, recompute_scale_factor=None, antialias=False: antialias)
|
||||
#Diffusers Float64 (ARC GPUs doesn't support double or Float64):
|
||||
if not torch.xpu.has_fp64_dtype():
|
||||
CondFunc('torch.from_numpy',
|
||||
lambda orig_func, ndarray: orig_func(ndarray.astype('float32')),
|
||||
lambda orig_func, ndarray: ndarray.dtype == float)
|
||||
#ControlNet and TiledVAE:
|
||||
CondFunc('torch.batch_norm',
|
||||
lambda orig_func, input, weight=None, bias=None, running_mean=None, running_var=None, training=False, momentum=0.1, eps=1e-5, cudnn_enabled=True: orig_func(input,
|
||||
weight if weight is not None else torch.ones(input.size()[1], device=shared.device),
|
||||
bias if bias is not None else torch.zeros(input.size()[1], device=shared.device),
|
||||
running_mean, running_var, training, momentum, eps, cudnn_enabled),
|
||||
lambda orig_func, input, weight=None, bias=None, running_mean=None, running_var=None, training=False, momentum=0.1, eps=1e-5, cudnn_enabled=True: input.device != torch.device("cpu"))
|
||||
#ControlNet
|
||||
CondFunc('torch.instance_norm',
|
||||
lambda orig_func, input, weight=None, bias=None, running_mean=None, running_var=None, use_input_stats=True, momentum=0.1, eps=1e-5, cudnn_enabled=True: orig_func(input,
|
||||
weight if weight is not None else torch.ones(input.size()[1], device=shared.device),
|
||||
bias if bias is not None else torch.zeros(input.size()[1], device=shared.device),
|
||||
running_mean, running_var, use_input_stats, momentum, eps, cudnn_enabled),
|
||||
lambda orig_func, input, weight=None, bias=None, running_mean=None, running_var=None, use_input_stats=True, momentum=0.1, eps=1e-5, cudnn_enabled=True: input.device != torch.device("cpu"))
|
||||
Reference in New Issue
Block a user