# Large CPU file size

**URL:** <https://discuss.pytorch.org/t/large-cpu-file-size/112709>\
**Category:** Uncategorized\
**Created:** [February 23, 2021, 12:41pm UTC](https://discuss.pytorch.org/t/large-cpu-file-size/112709 "2021-02-23T12:41:49Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![juliusbk](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/juliusbk/32/11612_2.png) [@juliusbk](https://discuss.pytorch.org/u/juliusbk)\
**Post date:** [February 23, 2021, 12:41pm UTC](https://discuss.pytorch.org/t/large-cpu-file-size/112709/1 "2021-02-23T12:41:49Z")

</div>

The CPU-only version of pytorch used be \< 200 MB (see e.g. [heroku - Where do I get a CPU-only version of PyTorch? - Stack Overflow](https://stackoverflow.com/questions/51730880/where-do-i-get-a-cpu-only-version-of-pytorch)). Now it is \> 1 GB.

This seems to mainly be due to the inclusion of `dnnl.lib` and `mkldnn.lib` (Windows). Are these needed for inference? It seems I can just delete them.

Anyone have any good ideas for further reducing the file size of the torch library?

Thanks!

---

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [February 24, 2021, 5:10am UTC](https://discuss.pytorch.org/t/large-cpu-file-size/112709/2 "2021-02-24T05:10:56Z")

</div>

The CPU conda binaries seems still be be \<200MB for the [stable release](https://anaconda.org/pytorch/pytorch/files) as well as the [nitghtlies](https://anaconda.org/pytorch-nightly/pytorch/files). Could you show a log where the \>1GB CPU binary is installed?

---

<div class="post-metadata">

**Author:** ![juliusbk](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/juliusbk/32/11612_2.png) [@juliusbk](https://discuss.pytorch.org/u/juliusbk)\
**Post date:** [February 24, 2021, 7:26am UTC](https://discuss.pytorch.org/t/large-cpu-file-size/112709/3 "2021-02-24T07:26:59Z")

</div>

The wheel file is only 184.2 MB, but unpacked (i.e. the folder in site-packages) is 936 MB. But this is perhaps to be expeced?

```auto
(venv) λ pip install torch==1.7.1+cpu -f https://download.pytorch.org/whl/torch_stable.html
Looking in links: https://download.pytorch.org/whl/torch_stable.html
Collecting torch==1.7.1+cpu
  Using cached https://download.pytorch.org/whl/cpu/torch-1.7.1%2Bcpu-cp39-cp39-win_amd64.whl (184.2 MB)
Collecting numpy
  Using cached numpy-1.20.1-cp39-cp39-win_amd64.whl (13.7 MB)
Collecting typing-extensions
  Using cached typing_extensions-3.7.4.3-py3-none-any.whl (22 kB)
Installing collected packages: numpy, typing-extensions, torch
Successfully installed numpy-1.20.1 torch-1.7.1+cpu typing-extensions-3.7.4.3

```

---

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [February 24, 2021, 7:28am UTC](https://discuss.pytorch.org/t/large-cpu-file-size/112709/4 "2021-02-24T07:28:51Z")

</div>

Ah OK, thanks for the explanation.  
It seems you’ve already narrowed it down to the CPU acceleration libs. I’m not completely sure, if `dnnl` and `mkldnn` is packed into the `pip` wheels, you you might give it a try.