Skip to content

Add animated gif for 3B SpinQuant #5763

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

Add animated gif for 3B SpinQuant #5763

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added examples/models/llama2/Android3_2_3B_SpinQuant.gif
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
20 changes: 16 additions & 4 deletions examples/models/llama2/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,18 @@ To improve accuracy, we can use [SpinQuant](https://github.com/facebookresearch/

SpinQuant can generate quantized weights that are [compatible with ExecuTorch](https://github.com/facebookresearch/SpinQuant/tree/main?tab=readme-ov-file#3-export-to-executorch), specifically, it can be integrated with the existing optimized XNNPACK kernels (e.g., group-wise 4bit weight and 8bit dynamic activation). This allows developers to benefit from the higher accuracy of SpinQuant while also taking advantage of the strong performance of ExecuTorch acceleration. We enabled SpinQuant for Llama3.2 1B/3B models on ExecuTorch.

<p align="center">
<img src="./Android3_2_3B_SpinQuant.gif" width=300>
<br>
<em>
Running Llama3.2 3B on Android phone.
</em>
<br>
<em>
4bit quantization using SpinQuant
</em>
</p>

## Enablement

For Llama 3 8B and Llama3.1 8B, we have verified so far on iPhone 15 Pro, iPhone 15 Pro Max, Samsung Galaxy S24+ and OnePlus 12 (with 16GB RAM).
Expand All @@ -73,10 +85,10 @@ We have verified running Llama 2 7B [mobile applications](#step-6-build-mobile-a
### Llama 3.2 1B and 3B
Llama 3.2 1B and 3B performance was measured on the OnePlus 12 device. The performance measurement is expressed in terms of tokens per second using an [adb binary-based approach](#step-5-run-benchmark-on) for generating 128 tokens.

|Model | bf16 | 4bit(*) via SpinQuant
|--------| ---------------------- | ---------------
|1B | 19.4 tokens/second | 53.41 tokens/second |
|3B | 7.76 tokens/second | 22.98 tokens/second |
|Model | 4bit(*) via SpinQuant
|--------| ---------------
|1B | 53.41 tokens/second |
|3B | 22.98 tokens/second |

(*) With SpinQuant, we currently quantize 4-bit groupwise (with groupsize 32) weight, 8bit dynamic activation of all the linear layers of the model, except embedding and output layers. The embedding and output layers are quantized as 8-bit per-channel weight and 8-bit dynamic activation.

Expand Down
Loading