Update performance numbers (100-clip RTX 6000 benchmark)

README.md

@@ -28,7 +28,7 @@ tags:
 [![Blog](https://img.shields.io/badge/Blog-FlashDrive-blue)](https://z-lab.ai/projects/flashdrive/)
 [![Models](https://img.shields.io/badge/%F0%9F%A4%97-Models-yellow)](https://huggingface.co/collections/z-lab/flashdrive)
 
-[FlashDrive](https://github.com/z-lab/flashdrive) accelerates [Alpamayo 1 (R1)](https://huggingface.co/nvidia/Alpamayo-R1-10B) — one of NVIDIA's 10B-parameter vision-language-action models for autonomous driving — by **4.3× with no loss in accuracy**, through streaming inference, [DFlash](https://github.com/z-lab/dflash) speculative reasoning, [ParoQuant](https://github.com/z-lab/paroquant) W4A8 quantization, adaptive action caching, and `torch.compile`.
+[FlashDrive](https://github.com/z-lab/flashdrive) accelerates [Alpamayo 1 (R1)](https://huggingface.co/nvidia/Alpamayo-R1-10B) — one of NVIDIA's 10B-parameter vision-language-action models for autonomous driving — by **4.5× with no loss in accuracy**, through streaming inference, [DFlash](https://github.com/z-lab/dflash) speculative reasoning, [ParoQuant](https://github.com/z-lab/paroquant) W4A8 quantization, adaptive action caching, and `torch.compile`.
 
 This repository mirrors the weights of [nvidia/Alpamayo-R1-10B](https://huggingface.co/nvidia/Alpamayo-R1-10B) and is the **base checkpoint** of the FlashDrive stack. Loading it pulls the derived companions automatically:
 
@@ -57,7 +57,7 @@ python scripts/infer.py --model-path z-lab/Alpamayo-R1-10B
 
 ## Performance
 
-On a single RTX PRO 6000, averaged over 100 PhysicalAI-AV clips, FlashDrive runs Alpamayo 1 (R1) at **4.3× lower latency** (826 → 194 ms per window) while minADE improves from 1.838 to 1.662. See the [repository](https://github.com/z-lab/flashdrive#performance) for the full benchmark.
+On a single RTX PRO 6000, averaged over 100 PhysicalAI-AV clips, FlashDrive runs Alpamayo 1 (R1) at **4.5× lower latency** (704 → 155 ms per window) while minADE improves from 1.869 to 1.662. See the [repository](https://github.com/z-lab/flashdrive#performance) for the full benchmark.
 
 ## License