- Semiconductor BusinessHOME
- Products and Services of Macnica,Inc.
-
technical information
-
Events and Seminars
- Handling Manufacturer
- Support
- Inquiry
- Click here to purchase products
- Semiconductor business e-mail magazine registration
Narrow down by specifying conditions
現在2147件がヒットしています。check
A series on Tenstorrent web content essential for realizing local LLM
If you would like to view the article you will need to register for an account. Please contact us for more information.
|
Software |
TT-NN™ + VSCode + Gemini Code Assist |
|---|---|
|
1 -Gemini Code Assist: A VS Code extension that supports the first step of Tenstorrent development |
Tenstorrent's software stack is available as open source on GitHub, but developers new to it may find it a bit difficult to understand and implement the code. In this article and video, we introduce Gemini Code Assist to Visual Studio Code and share our experience using it to support software development at Tenstorrent. Please take a look at the video. |
|
Hardware |
Wormhole™ n300 x 1 |
|
1 -I tried out Tenstorrent's AI accelerator card, Wormhole™ N300 |
We tried out Tenstornet's Wormhole™ N300 accelerator card, which specializes in image and generative AI. This product offers superior performance per watt and cost performance compared to existing GPU cards, so if you're interested, please take a look. It supports various network models, but this time we used Llama 3.2 11B. |
|
|
|
|
Hardware |
TT-LoudBox ( Wormhole™ n300s x 4) |
| We tried out Tenstornet's Wormhole™ N300 accelerator card, which specializes in image and generative AI. This product offers superior performance per watt and cost performance compared to existing GPU cards, so if you're interested, please take a look. It supports various network models, but this time we used Llama 3.3 70B. |
|
|
3 -Running vLLM on Tenstorrent's AI accelerator card Wormhole™ N300 |
We ran vLLM on Tenstornet's Wormhole™ N300 accelerator card, which specializes in image and generative AI. This product offers superior performance per watt and cost performance compared to existing GPU cards, so if you're interested, please take a look. It supports various network models, but this time we used Llama3.1 70B. |
|
4 -Running vLLM on Tenstorrent's AI accelerator card, Wormhole™ N300 |
We ran vLLM on Tenstornet's Wormhole™ N300 accelerator card, which specializes in image and generative AI. |
|
5 -Running vLLM on Tenstorrent's AI accelerator card Wormhole™ N300 |
We ran Llama 3.3 Swallow 70B with vLLM on Tenstornet's Wormhole™ N300 accelerator card, which specializes in image and generative AI. This product offers superior performance per watt and cost performance compared to existing GPU cards, so if you're interested, please take a look. It supports various network models, but this time we used Llama 3.3 Swallow 70B Instruct v0.4. |
|
6 -I tried running vLLM on Tenstorrent's desktop workstation (TT-LoudBox) |
We ran vLLM on Tenstornet's TT-LoudBox, a desktop workstation specialized for image and generative AI. This product offers superior performance per watt and cost performance compared to existing GPU cards, so if you're interested, please take a look. It supports various network models, but this time we used Llama3.3 70B. |
Inquiry
If you have any questions about this article, please contact us using the form below.
Tenstorrent Manufacturer Information Top
Tenstorrent Manufacturer Information If you would like to return to the top page, please click below.