🐛 Describe the bug

The following script works fine if I switch to CPU, or change the tensor dtypes to float32. Otherwise, see the error below.

import torch

device = torch.device("cuda")         # works fine with "cpu"
print(f"Using device: {device}")

# works fine if both are float32
input  = torch.randint(low=0, high=2, size=(1, 1, 6, 6), dtype=torch.int8).to(device)
kernel = torch.randint(low=0, high=2, size=(1, 1, 3, 3), dtype=torch.int8).to(device)

output = torch.nn.functional.conv2d(input, kernel, padding=1)
print("Convolution successful. Output shape:", output.shape)

Traceback:

Using device: cuda
Traceback (most recent call last):
  File "C:\Users\Clemens\prog\cuda-conv-int8.py", line 10, in <module>
    output = torch.nn.functional.conv2d(input, kernel, padding=1)
RuntimeError: GET was unable to find an engine to execute this computation

Versions

PyTorch version: 2.7.0+cu128
Is debug build: False
CUDA used to build PyTorch: 12.8
ROCM used to build PyTorch: N/A

OS: Microsoft Windows 10 Home (10.0.19045 64-bit)
GCC version: Could not collect
Clang version: Could not collect
CMake version: Could not collect
Libc version: N/A

Python version: 3.13.3 (tags/v3.13.3:6280bb5, Apr 8 2025, 14:47:33) [MSC v.1943 64 bit (AMD64)] (64-bit runtime)
Python platform: Windows-10-10.0.19045-SP0
Is CUDA available: True
CUDA runtime version: 12.8.93
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA GeForce GTX 1060 6GB
Nvidia driver version: 572.83
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Name: Intel(R) Core(TM) i5-4460 CPU @ 3.20GHz
Manufacturer: GenuineIntel
Family: 1
Architecture: 9
ProcessorType: 3
DeviceID: CPU0
CurrentClockSpeed: 3201
MaxClockSpeed: 3201
L2CacheSize: 1024
L2CacheSpeed: None
Revision: 15363

Versions of relevant libraries:
[pip3] numpy==2.1.2
[pip3] torch==2.7.0+cu128
[pip3] torchaudio==2.7.0+cu128
[pip3] torchvision==0.22.0+cu128
[conda] Could not collect

cc @ptrblck @msaroufim @eqy @jerryzh168