Can 'torch.profiler' support GB20X NVIDIA GPU architectures?

1

For more details, please see the open issue #174195.

I use torch.profiler like this:

prof = torch.profiler.profile(
activities=[torch.profiler.ProfilerActivity.CPU, torch.profiler.ProfilerActivity.CUDA],
schedule=torch.profiler.schedule(wait=3, warmup=3, active=3, repeat=1),
on_trace_ready=torch.profiler.tensorboard_trace_handler(f’./xxx’),
record_shapes=True,
with_stack=True,
acc_events=True,)

But I got an error:

WARNING:2026-02-03 20:37:18 334947:334947 init.cpp:115] function cbapi->getCuptiStatus() failed with error CUPTI_ERROR_INVALID_DEVICE (2)
WARNING:2026-02-03 20:37:18 334947:334947 init.cpp:116] CUPTI initialization failed - CUDA profiler activities will be missing
INFO:2026-02-03 20:37:18 334947:334947 init.cpp:118] If you see CUPTI_ERROR_INSUFFICIENT_PRIVILEGES, refer to NVIDIA Development Tools Solutions - CUPTI_ERROR_INSUFFICIENT_PRIVILEGES: CUPTI Permission issue with Performance Counters | NVIDIA Developer

My env:

PyTorch version: 2.10.0+cu128
Is debug build: False
CUDA used to build PyTorch: 12.8
ROCM used to build PyTorch: N/A

OS: Ubuntu 24.04.3 LTS (x86_64)
GCC version: (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
Clang version: Could not collect
CMake version: version 3.28.3
Libc version: glibc-2.39

Python version: 3.12.3 (main, Jan 8 2026, 11:30:50) [GCC 13.3.0] (64-bit runtime)
Python platform: Linux-6.14.0-37-generic-x86_64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: 12.8.93
CUDA_MODULE_LOADING set to:
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 5060 Laptop GPU
Nvidia driver version: 590.48.01
cuDNN version: Could not collect
Is XPU available: False
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
Caching allocator config: N/A

2
3

Use CUDA 13, and new driver can solve this.