# torchchat

**URL:** https://discuss.pytorch.org/c/torchchat/43.md

[Latest](https://discuss.pytorch.org/latest.md) · [Categories](https://discuss.pytorch.org/categories.md)

---

## [About the torchchat category](https://discuss.pytorch.org/t/about-the-torchchat-category/208671)

<div class="topic-metadata">

**Author:** [@albanD](https://discuss.pytorch.org/u/albanD)\
**Replies:** 0\
**Last updated:** [August 26, 2024, 4:43pm UTC](https://discuss.pytorch.org/t/about-the-torchchat-category/208671 "2024-08-26T16:43:46Z")

</div>

torchchat - Running LLMs locally With torchchat, you can run LLMs using Python You will find the project organized into three areas: Python: Torchchat provides a REST API that is called via a Python CLI or can be acc…

---

## [Installation Candidates](https://discuss.pytorch.org/t/installation-candidates/223104)

<div class="topic-metadata">

**Author:** [@mutineering](https://discuss.pytorch.org/u/mutineering)\
**Replies:** 2\
**Last updated:** [September 16, 2025, 6:33pm UTC](https://discuss.pytorch.org/t/installation-candidates/223104 "2025-09-16T18:33:28Z")

</div>

Hello.. I am on ubuntu noble 24.04 with python 3.12 on a desktop machine which has a working installation of CUDA13 and a couple of graphics cards. I can’t use pip to install torch without the ‘externally-managed-envi…