> For the complete documentation index, see [llms.txt](https://byte-research.gitbook.io/cryostar/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://byte-research.gitbook.io/cryostar/installation-guide.md).
# Installation guide
Dear users,
We are thrilled to provide you with cryoSTAR, which is based on Python. However, to run this program, you should have the following requirements:
* A high-performance Linux machine equipped with **GPU**
* Knowledge of basic command line operations
Below, we would like to guide you through the steps of installing [Miniconda](https://docs.conda.io/projects/miniconda/en/latest/), cloning the project using `git`, and then installing the project using `pip`. If you are very familiar with Linux, python environment, etc., you can directly jump to [Installation guide](/cryostar/installation-guide.md#install-cryostar).
## Check GPU Availability
Before you start, remember that this program requires you to have a high-performance Linux machine in possession, which is equipped with a GPU. To confirm your machine is equipped with a GPU, you can use the `nvidia-smi` command in your terminal. This produces a detailed snapshot of the current GPU state. Here's how you do it:
```sh
$ nvidia-smi
```
These details include the GPU name, total memory, memory used, and the current active processes utilizing the GPU. Here is an **expected output**:
```
Tue Nov 14 10:53:05 2023
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.129.06 Driver Version: 470.129.06 CUDA Version: 11.4 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 Tesla V100-SXM2... On | 00000000:B1:00.0 Off | 0 |
| N/A 38C P0 71W / 300W | 0MiB / 32510MiB | 0% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
| 1 Tesla V100-SXM2... On | 00000000:B2:00.0 Off | 0 |
| N/A 43C P0 71W / 300W | 0MiB / 32510MiB | 0% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| No running processes found |
+-----------------------------------------------------------------------------+
```
In case you encounter an error message or no useful information coming out after running `nvidia-smi`, it might indicate that no GPU is available on your machine. Here is an example of an **error message**:
```
command not found: nvidia-smi
```
## Install Miniconda3
We strongly recommend using environment management software like `conda` to keep your system environment resilient and organized. In particular, we advocate for the `conda` environment manager. Below is a guide on installing Miniconda on a Linux system.
Go to [Miniconda's official website](https://docs.conda.io/projects/miniconda/en/latest/) to download the installer appropriate for your system. Once you've downloaded the installer, open your terminal, navigate to the location where the installer is saved, and run the following command to install Miniconda:
```bash
$ bash Miniconda3-latest-Linux-x86_64.sh
```
Please replace `Miniconda3-latest-Linux-x86_64.sh` with the name of the file you downloaded. The installer will display a license agreement, which you have to agree to. Then you confirm the install location (or choose your own). You'll need to follow the prompts in the terminal to complete your installation.
After that, it is critical to initialize `conda` to configure your shell to use `conda` without any issues. This configuration will modify your shell scripts (like `.bashrc` ), which might change shell behavior.
If you are using the Bash shell, you can initialize `conda` through the following command:
$ ~/miniconda3/bin/conda init bash
## Install cryoSTAR
### Configure the Conda Environment
Set up a new `conda` environment named `cryostar` using Python 3.9:
```bash
$ conda create -n cryostar python=3.9 -y
```
Activate the environment:
```bash
$ conda activate cryostar
```
### Download cryoSTAR
There are two approaches to downloading the cryoSTAR software. You can [download through browser via this link](https://github.com/bytedance/cryostar/archive/refs/heads/master.zip) and unzip the file to your machine. If your machine has `git` installed, we recommend you download it by cloning the repository:
```bash
$ git clone https://github.com/bytedance/cryostar.git
```
**NOTE:**
* If you encounter an error message such as `git: command not found`, you may need to install the `git` software. We recommend trying this command first as it usually works for most users, particularly if your system is Ubuntu/Debian: `sudo apt install git` . If it does not work, detailed installation guide can be found at [this link](https://github.com/git-guides/install-git).
### Install CryoSTAR
Navigate into the `cryostar` directory (or `cryostar-master` if you download it through the browser) where you can find the file `setup.py` :
```bash
(cryostar)$ cd cryostar
```
Install `cryostar` using `pip`, the python package installer:
```sh
(cryostar)$ pip install .
```
**NOTE:**
* Please note the **dot** at the end of the installation command. It's crucial to input `pip install .` instead of `pip install`! The dot is not a typographical error; it refers to the current directory.
* Make sure you are in the directory where you can find the file `setup.py` !
🎊 Congratulations! You now have `cryostar` installed in your machine. If your internet connection is good, the entire installation process will be completed within 10 minutes. If any issues arise during the installation, feel free to visit the post questions via [github issues](https://github.com/bytedance/cryostar)!
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://byte-research.gitbook.io/cryostar/installation-guide.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.