IPEX fix torch.cuda.synchronize

This commit is contained in:
Disty0
2025-01-31 18:46:07 +03:00
parent 92dbcd72a0
commit e193a92fe1
3 changed files with 17 additions and 11 deletions
-1
View File
@@ -37,7 +37,6 @@ def ipex_init(): # pylint: disable=too-many-statements
torch.cuda.is_current_stream_capturing = lambda: False
torch.cuda.set_device = torch.xpu.set_device
torch.cuda.stream = torch.xpu.stream
torch.cuda.synchronize = torch.xpu.synchronize
torch.cuda.Event = torch.xpu.Event
torch.cuda.Stream = torch.xpu.Stream
torch.Tensor.cuda = torch.Tensor.xpu
-1
View File
@@ -1,5 +1,4 @@
import os
import math
import torch
from functools import cache, wraps
+17 -9
View File
@@ -300,14 +300,6 @@ def torch_linspace(*args, device=None, **kwargs):
else:
return original_torch_linspace(*args, device=device, **kwargs)
original_torch_Generator = torch.Generator
@wraps(torch.Generator)
def torch_Generator(device=None):
if check_device(device):
return original_torch_Generator(return_xpu(device))
else:
return original_torch_Generator(device)
original_torch_load = torch.load
@wraps(torch.load)
def torch_load(f, map_location=None, *args, **kwargs):
@@ -318,6 +310,21 @@ def torch_load(f, map_location=None, *args, **kwargs):
else:
return original_torch_load(f, *args, map_location=map_location, **kwargs)
original_torch_Generator = torch.Generator
@wraps(torch.Generator)
def torch_Generator(device=None):
if check_device(device):
return original_torch_Generator(return_xpu(device))
else:
return original_torch_Generator(device)
@wraps(torch.cuda.synchronize)
def torch_cuda_synchronize(device=None):
if check_device(device):
return torch.xpu.synchronize(return_xpu(device))
else:
return torch.xpu.synchronize(device)
# Hijack Functions:
def ipex_hijacks(legacy=True):
@@ -336,8 +343,9 @@ def ipex_hijacks(legacy=True):
torch.zeros = torch_zeros
torch.full = torch_full
torch.linspace = torch_linspace
torch.Generator = torch_Generator
torch.load = torch_load
torch.Generator = torch_Generator
torch.cuda.synchronize = torch_cuda_synchronize
torch.backends.cuda.sdp_kernel = return_null_context
torch.nn.DataParallel = DummyDataParallel