# \[BUG\] Performance drop with batch and opt\_level=3

**URL:** <https://discuss.tvm.apache.org/t/bug-performance-drop-with-batch-and-opt-level-3/9193>\
**Category:** Troubleshooting\
**Created:** [February 23, 2021, 8:06am UTC](https://discuss.tvm.apache.org/t/bug-performance-drop-with-batch-and-opt-level-3/9193 "2021-02-23T08:06:57Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![gasgallo](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/gasgallo/32/821_2.png) [@gasgallo](https://discuss.tvm.apache.org/u/gasgallo)\
**Post date:** [March 1, 2021, 4:28am UTC](https://discuss.tvm.apache.org/t/bug-performance-drop-with-batch-and-opt-level-3/9193/2 "2021-03-01T04:28:07Z")

</div>

I’m facing the same issue and I can reproduce it with a retinaface model ([this model](https://drive.google.com/drive/folders/1yGXAKebez7R_ZMjWWxaSBD5ixB68GUyR?usp=sharing)).

When batch size is 1, outputs are correct.

When batch size is 2 or bigger and `opt_level` is 1 or 2, outputs are correct.

When batch size is 2 or bigger and `opt_level` is 3, some outputs are wrong/different when compared to the original model.

Is this a bug? Any idea why this happens? @tqchen

---

_[View the full topic](https://discuss.tvm.apache.org/t/bug-performance-drop-with-batch-and-opt-level-3/9193)._