Some questions need to be consulted


1. why batch_stride is 0, not seq_q * head_q * dim in ops/flash_attn_v2.cpp(line 39)
    params.q_batch_stride = 0;
    params.k_batch_stride = 0;
    params.v_batch_stride = 0;

2. After using TensorRT for encapsulation, I found that the values of other nodes were modified. But the result of compute-sanitizer is ok. How to analyze the reasons next.