Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@ license: cc
|
|
| 3 |
tags:
|
| 4 |
- multimodal
|
| 5 |
---
|
| 6 |
-
# **OmniNeural** — World’s First
|
| 7 |
|
| 8 |
## **Overview**
|
| 9 |
**OmniNeural** is the first multimodal model designed specifically for Neural Processing Units (NPUs). It natively understands **text, images, and audio**, and runs across PCs, mobile devices, vehicles, IoT, and robotics.
|
|
@@ -13,7 +13,7 @@ By co-designing the software and model architecture with NPU hardware, OmniNeura
|
|
| 13 |
- **2–4× better efficiency than CPU and 4–8× better than GPU** in battery usage .
|
| 14 |
- **Smooth multitasking**, running large generative AI models without slowing other applications .
|
| 15 |
|
| 16 |
-
This combination of speed, efficiency, and NPU support makes OmniNeural the most practical multimodal foundation for edge intelligence.
|
| 17 |
|
| 18 |
---
|
| 19 |
|
|
@@ -23,7 +23,7 @@ This combination of speed, efficiency, and NPU support makes OmniNeural the most
|
|
| 23 |
- **Hardware-Aware Attention** – Attention patterns tuned for NPU, lowering compute and memory demand .
|
| 24 |
- **Native Static Graph** – Supports variable-length multimodal inputs with stable, predictable latency .
|
| 25 |
- **Performance Gains** – **9× faster audio processing** and **3.5× faster image processing** on NPUs compared to baseline encoders .
|
| 26 |
-
- **Privacy-First Inference** – All computation stays local: private, offline-capable, and cost-efficient.
|
| 27 |
|
| 28 |
---
|
| 29 |
|
|
@@ -50,20 +50,13 @@ This combination of speed, efficiency, and NPU support makes OmniNeural the most
|
|
| 50 |
- **Text**: Matches or outperforms leading multimodal baselines.
|
| 51 |
|
| 52 |
|
| 53 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
|
| 61 |
### Nexa Attention Speedups
|
| 62 |
- **9× faster** audio encoding (vs Whisper).
|
| 63 |
- **3.5× faster** image encoding (vs SigLIP).
|
| 64 |
|
| 65 |
-
|
| 66 |
-
|
| 67 |
|
| 68 |
---
|
| 69 |
|
|
|
|
| 3 |
tags:
|
| 4 |
- multimodal
|
| 5 |
---
|
| 6 |
+
# **OmniNeural** — World’s First Multimodal Model Designed for NPU
|
| 7 |
|
| 8 |
## **Overview**
|
| 9 |
**OmniNeural** is the first multimodal model designed specifically for Neural Processing Units (NPUs). It natively understands **text, images, and audio**, and runs across PCs, mobile devices, vehicles, IoT, and robotics.
|
|
|
|
| 13 |
- **2–4× better efficiency than CPU and 4–8× better than GPU** in battery usage .
|
| 14 |
- **Smooth multitasking**, running large generative AI models without slowing other applications .
|
| 15 |
|
| 16 |
+
This combination of speed, efficiency, and NPU support makes OmniNeural the most practical multimodal foundation for edge intelligence.
|
| 17 |
|
| 18 |
---
|
| 19 |
|
|
|
|
| 23 |
- **Hardware-Aware Attention** – Attention patterns tuned for NPU, lowering compute and memory demand .
|
| 24 |
- **Native Static Graph** – Supports variable-length multimodal inputs with stable, predictable latency .
|
| 25 |
- **Performance Gains** – **9× faster audio processing** and **3.5× faster image processing** on NPUs compared to baseline encoders .
|
| 26 |
+
- **Privacy-First Inference** – All computation stays local: private, offline-capable, and cost-efficient.
|
| 27 |
|
| 28 |
---
|
| 29 |
|
|
|
|
| 50 |
- **Text**: Matches or outperforms leading multimodal baselines.
|
| 51 |
|
| 52 |
|
| 53 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
|
| 55 |
### Nexa Attention Speedups
|
| 56 |
- **9× faster** audio encoding (vs Whisper).
|
| 57 |
- **3.5× faster** image encoding (vs SigLIP).
|
| 58 |
|
| 59 |
+
|
|
|
|
| 60 |
|
| 61 |
---
|
| 62 |
|