# Why TorchScript module does not take less GPU memory than Pytorch model?

**URL:** <https://discuss.pytorch.org/t/why-torchscript-module-does-not-take-less-gpu-memory-than-pytorch-model/157560>\
**Category:** Uncategorized\
**Created:** [July 26, 2022, 11:14pm UTC](https://discuss.pytorch.org/t/why-torchscript-module-does-not-take-less-gpu-memory-than-pytorch-model/157560 "2022-07-26T23:14:32Z")\
**Posts on this page:** 1\
**Showing post:** 4

<div class="post-metadata">

**Author:** ![JuanFMontesinos](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/juanfmontesinos/32/76115_2.png) [@JuanFMontesinos](https://discuss.pytorch.org/u/JuanFMontesinos)\
**Post date:** [July 27, 2022, 7:43am UTC](https://discuss.pytorch.org/t/why-torchscript-module-does-not-take-less-gpu-memory-than-pytorch-model/157560/4 "2022-07-27T07:43:50Z")

</div>

I didn’t know about it.  
Most of my attempts to use torchscript to speed up the forward pass showed no improvement at all.

Are there other kind of situations besides pointwise ops?

---

_[View the full topic](https://discuss.pytorch.org/t/why-torchscript-module-does-not-take-less-gpu-memory-than-pytorch-model/157560)._