Error message: XPU out of memory. Tried to allocate 4.00 GiB (GPU 0; 15.11 GiB total capacity; 0 bytes already allocated; 0 bytes reserved in total by PyTorch) #41150
Description
System Info
Soo the problem is simple:
If i only install xpu torch and intel_extension_for_pytorch then all my 16gbvram is ready but if i install transformers its only 4gb vram is aviable.
With this the 16gb vram works:
The code:
import torch
from torch import xpu
import os
import intel_extension_for_pytorch
os.environ['UR_L0_USE_RELAXED_ALLOCATION_LIMITS'] = '1'
os.environ['IGC_ExtraOCLOptions'] = "-cl-intel-greater-than-4GB-buffer-required"
def xpu_memory_test():
if not xpu.is_available():
print("XPU not available!")
return
device = torch.device("xpu")
print(f"\n=== XPU Memory Test ===")
try:
print(f"Device Name: {torch.xpu.get_device_name(device)}")
max_alloc = torch.xpu.max_memory_allocated(device) / (1024**3)
total_mem = torch.xpu.get_device_properties(device).total_memory / (1024**3)
print(f"\nDevice Memory: {total_mem:.2f}GB total")
print(f"Max allocated during session: {max_alloc:.2f}GB")
size_step = 0.1
current_size = 1.0
last_success = 0
while current_size <= total_mem:
tensor_size = int(current_size * (1024**3 / 4))
print(f"\nAttempting to allocate {current_size}GB tensor...")
try:
test_tensor = torch.empty(tensor_size, dtype=torch.float32, device=device)
torch.xpu.synchronize(device)
allocated = torch.xpu.memory_allocated(device) / (1024**3)
print(f"Success! Current allocated: {allocated:.2f}GB")
os.system("free -h")
del test_tensor
torch.xpu.empty_cache()
last_success = current_size
current_size += size_step
except RuntimeError as e:
print(f"\nAllocation failed at {current_size}GB (last success: {last_success}GB)")
print(f"Error message: {str(e)}")
os.system("free -h")
break
except Exception as e:
print(f"\nError during memory test: {str(e)}")
finally:
allocated = torch.xpu.memory_allocated(device) / (1024**3)
print(f"\n! Final allocated memory: {allocated:.2f}GB")
print("Test completed.")
if __name__ == "__main__":
xpu_memory_test()
torch.xpu.empty_cache()
pip list (no transformers)
Package Version
--------------------------- ----------
accelerate 1.10.1
certifi 2025.8.3
charset-normalizer 3.4.3
dpcpp-cpp-rt 2025.0.4
filelock 3.13.1
fsspec 2024.6.1
hf-xet 1.1.10
huggingface-hub 0.35.1
idna 3.10
impi-devel 2021.14.1
impi-rt 2021.14.1
intel-cmplr-lib-rt 2025.0.4
intel-cmplr-lib-ur 2025.0.4
intel-cmplr-lic-rt 2025.0.4
intel_extension_for_pytorch 2.7.10+xpu
intel-opencl-rt 2025.0.4
intel-openmp 2025.0.4
intel-pti 0.10.1
intel-sycl-rt 2025.0.4
Jinja2 3.1.4
MarkupSafe 2.1.5
mkl 2025.0.1
mkl-dpcpp 2025.0.1
mpmath 1.3.0
networkx 3.3
numpy 2.1.2
oneccl 2021.14.1
oneccl-bind-pt 2.7.0+xpu
oneccl-devel 2021.14.1
onemkl-sycl-blas 2025.0.1
onemkl-sycl-datafitting 2025.0.1
onemkl-sycl-dft 2025.0.1
onemkl-sycl-lapack 2025.0.1
onemkl-sycl-rng 2025.0.1
onemkl-sycl-sparse 2025.0.1
onemkl-sycl-stats 2025.0.1
onemkl-sycl-vm 2025.0.1
packaging 25.0
pillow 11.0.0
pip 24.0
psutil 7.1.0
pytorch-triton-xpu 3.3.0
PyYAML 6.0.2
regex 2025.9.18
requests 2.32.5
ruamel.yaml 0.18.15
ruamel.yaml.clib 0.2.14
safetensors 0.6.2
setuptools 65.5.0
sympy 1.13.3
tbb 2022.2.0
tcmlib 1.2.0
tokenizers 0.22.1
torch 2.7.0+xpu
torchaudio 2.7.0+xpu
torchvision 0.22.0+xpu
tqdm 4.67.1
typing_extensions 4.12.2
umf 0.9.1
urllib3 2.5.0
But if i install transformers its go back to 4gb vram:
pip list (with transformers)
Package Version
--------------------------- ----------
accelerate 1.10.1
certifi 2025.8.3
charset-normalizer 3.4.3
dpcpp-cpp-rt 2025.0.4
filelock 3.13.1
fsspec 2024.6.1
hf-xet 1.1.10
huggingface-hub 0.35.1
idna 3.10
impi-devel 2021.14.1
impi-rt 2021.14.1
intel-cmplr-lib-rt 2025.0.4
intel-cmplr-lib-ur 2025.0.4
intel-cmplr-lic-rt 2025.0.4
intel_extension_for_pytorch 2.7.10+xpu
intel-opencl-rt 2025.0.4
intel-openmp 2025.0.4
intel-pti 0.10.1
intel-sycl-rt 2025.0.4
Jinja2 3.1.4
MarkupSafe 2.1.5
mkl 2025.0.1
mkl-dpcpp 2025.0.1
mpmath 1.3.0
networkx 3.3
numpy 2.1.2
oneccl 2021.14.1
oneccl-bind-pt 2.7.0+xpu
oneccl-devel 2021.14.1
onemkl-sycl-blas 2025.0.1
onemkl-sycl-datafitting 2025.0.1
onemkl-sycl-dft 2025.0.1
onemkl-sycl-lapack 2025.0.1
onemkl-sycl-rng 2025.0.1
onemkl-sycl-sparse 2025.0.1
onemkl-sycl-stats 2025.0.1
onemkl-sycl-vm 2025.0.1
packaging 25.0
pillow 11.0.0
pip 24.0
psutil 7.1.0
pytorch-triton-xpu 3.3.0
PyYAML 6.0.2
regex 2025.9.18
requests 2.32.5
ruamel.yaml 0.18.15
ruamel.yaml.clib 0.2.14
safetensors 0.6.2
setuptools 65.5.0
sympy 1.13.3
tbb 2022.2.0
tcmlib 1.2.0
tokenizers 0.22.1
torch 2.7.0+xpu
torchaudio 2.7.0+xpu
torchvision 0.22.0+xpu
tqdm 4.67.1
transformers 4.56.2
typing_extensions 4.12.2
umf 0.9.1