Update README.md
Browse files
README.md
CHANGED
|
@@ -1,29 +1,26 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
emoji: 🤖
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: yellow
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
#
|
| 11 |
|
| 12 |
We optimize and deploy **LLMs, ASR, VLM and VLA (Vision-Language-Action) models** on real-world systems.
|
| 13 |
|
| 14 |
-
##
|
| 15 |
- Optimization: quantization (INT8/INT4/FP8/NVFP4), pruning, distillation, ...
|
| 16 |
- Deployment: VLLM, TensorRT, ONNX Runtime, edge runtimes
|
| 17 |
- Systems: real-time pipelines (vision, audio, language, action)
|
| 18 |
|
| 19 |
-
##
|
| 20 |
- Edge devices (Jetson, SoCs)
|
| 21 |
- Robotics & VLA systems
|
| 22 |
- Latency, stability, deployability
|
| 23 |
|
| 24 |
-
##
|
| 25 |
-
Optimization = **model + runtime + system**
|
| 26 |
-
|
| 27 |
-
---
|
| 28 |
-
|
| 29 |
-
**VRFAI — making AI models fast, efficient, and real**
|
|
|
|
| 1 |
---
|
| 2 |
+
title: VinRobotics
|
| 3 |
emoji: 🤖
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: yellow
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
+
license: apache-2.0
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# VinRobotics - Edge AI & Model Optimization
|
| 12 |
|
| 13 |
We optimize and deploy **LLMs, ASR, VLM and VLA (Vision-Language-Action) models** on real-world systems.
|
| 14 |
|
| 15 |
+
## What we do
|
| 16 |
- Optimization: quantization (INT8/INT4/FP8/NVFP4), pruning, distillation, ...
|
| 17 |
- Deployment: VLLM, TensorRT, ONNX Runtime, edge runtimes
|
| 18 |
- Systems: real-time pipelines (vision, audio, language, action)
|
| 19 |
|
| 20 |
+
## Focus
|
| 21 |
- Edge devices (Jetson, SoCs)
|
| 22 |
- Robotics & VLA systems
|
| 23 |
- Latency, stability, deployability
|
| 24 |
|
| 25 |
+
## Philosophy
|
| 26 |
+
Optimization = **model + runtime + system**
|
|
|
|
|
|
|
|
|
|
|
|