CUDA error for tutorial

[Jimntu]

I encounter a very weird bug when I run LLaVa_OneVision_Tutorial.ipynb

../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [0,0,0], thread: [63,0,0] Assertion -sizes[i] <= index && index < sizes[i] && "index out of bounds" failed. RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasLtMatmul with transpose_mat1 1 transpose_mat2 0 m 896 n 1 k 896 mat1_ld 896 mat2_ld 896 result_ld 896 abcType 2 computeType 68 scaleType 0

Any idea how can I resolve this bug? Many thanks!