mirrors/tabby
1
0
Fork 0
mirror of https://github.com/TabbyML/tabby synced 2024-11-22 08:21:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: update windows installation (#2449)

Browse Source
This commit is contained in:
Wang Zixiao 2024-06-21 20:44:23 +08:00 committed by GitHub
parent 1613bc9341
commit 64a4df227a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 31 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
website/docs/quick-start/installation/windows/assets.png (Stored with Git LFS) vendored
View File

Binary file not shown.

32
website/docs/quick-start/installation/windows/index.mdx vendored
View File

@ -2,17 +2,22 @@
sidebar_position: 3
---
import releaseImage from './assets.png';
import successImage from './success.png';
# Windows
Running Tabby on Windows using Tabby's exe distribution.
## Find the Windows release
* Go to the Tabby release page: https://github.com/TabbyML/tabby/releases
* Click on the **Assets** dropdown for a specific release to find the Windows executable (exe) files.
![Windows release](./assets.png)
* Click on the **Assets** dropdown for a specific release to find the Windows zip files.
<div align="left">
<img src={releaseImage} alt="Windows release" style={{ width: 800 }} />
</div>
## Download the release
* If you are using a CPU-only system, download the **tabby_x86_64-windows-msvc.exe file**.
* If you are using a GPU-enabled system, download the **tabby_x86_64-windows-msvc-cuda117.exe** file, In this example, we assume you are using CUDA 11.7.
* If you are using a CPU-only system, download the **tabby_x86_64-windows-msvc.zip**.
* If you are using a GPU-enabled system, download the **tabby_x86_64-windows-msvc-cuda117.zip**, In this example, we assume you are using CUDA 11.7.
**Tips:**
* Download the CUDA Toolkit from Nvidia: https://developer.nvidia.com/cuda-toolkit
@ -22,12 +27,25 @@ Running Tabby on Windows using Tabby's exe distribution.
nvcc --version
```
## Find the Windows executable file
* Unzip the file `tabby_x86_64-windows-msvc-cuda117.zip`.
* Navigate to the extracted folder named `tabby_x86_64-windows-msvc-cuda117`.
* Inside this folder, go to `dist` -> `tabby_x86_64-windows-msvc-cuda117`.
* In this directory, you'll find an executable file named `tabby.exe`.
## Running Tabby
Open a command prompt or PowerShell window in the directory where you downloaded the Tabby executable. Run the following command:
Open a command prompt or PowerShell window in the directory where the `tabby.exe` is located (from the previous step).
Run the following command:
```
# For CPU-only environments
.\tabby_x86_64-windows-msvc.exe serve --model StarCoder-1B
.\tabby.exe serve --model StarCoder-1B
# For CUDA-enabled environments
.\tabby_x86_64-windows-msvc-cuda117.exe serve --model StarCoder-1B --device cuda
.\tabby.exe serve --model StarCoder-1B --device cuda
```
You should see a success message similar to the one in the screenshot below. After that, you can visit http://localhost:8080 to access your Tabby instance.
<div align="left">
<img src={successImage} alt="Windows running success" style={{ width: 800 }} />
</div>

BIN
website/docs/quick-start/installation/windows/success.png (Stored with Git LFS) vendored Normal file
View File

Binary file not shown.