pytorch-triton           3.4.0+git11ec6354torch                    2.9.0.dev20250723+cu128torchaudio               2.8.0.dev20250723+cu128torchvision              0.24.0.dev20250723+cu128

 CUDA_VISIBLE_DEVICES=1 python generate.py  --checkpoint_path checkpoints/$MODEL_REPO/model.pth --prompt "The capital of France is:"  --num_samples=1 --compile

RuntimeError: Error: accessing tensor output of CUDAGraphs that has been overwritten by a subsequent run. Stack trace: File "/home/rzou/dev/lab/gpt-fast/mixtral-moe/generate.py", line 68, in decode_one_token    return sample(logits, **sampling_kwargs)  File "/home/rzou/dev/lab/gpt-fast/mixtral-moe/generate.py", line 56, in sample    idx_next = multinomial_sample_one_no_sync(probs)  File "/home/rzou/dev/lab/gpt-fast/mixtral-moe/generate.py", line 42, in multinomial_sample_one_no_sync    return torch.argmax(probs_sort / q, dim=-1, keepdim=True).to(dtype=torch.int). To prevent overwriting, clone the tensor outside of torch.compile() or call torch.compiler.cudagraph_mark_step_begin() before each model invocation.