Загрузка видео...

Не удалось загрузить видео

На главную

LiteRT is here. The universal framework for on-device AI. 📱💻 ✨ 1.4x faster GPU performance ✨ Unified NPU acceleration ✨ Seamless PyTorch and JAX support ✨ Ready for Gemma and gen AI Build faster, simpler, and everywhere. Read the blog:

194,484 просмотров • 8 месяцев назад •via X (Twitter)

Комментарии: 28

Фото профиля ikan laut
ikan laut8 месяцев назад

This is what I need. To build web, applications, and AI. Then maybe in the future also supercomputers, so that quantum no longer relies on laptops or computers, but only in handheld devices such as smartphones, smart glasses and AR/VR/XR/MR devices.

Фото профиля Ankit Yadav
Ankit Yadav8 месяцев назад

Can't wait to try it in the development

Фото профиля Senior CRUD Monkey
Senior CRUD Monkey8 месяцев назад

Define "universal"

Фото профиля Respo
Respo8 месяцев назад

@grok what is this new LiteRThow is this useful is it related to AI

Фото профиля Moon 🎑
Moon 🎑8 месяцев назад

Smartphone can now be automated, ready to take tasks into action.

Фото профиля Adi | Resolved Markets
Adi | Resolved Markets8 месяцев назад

The real win here is unified NPU acceleration across different hardware. Means devs can finally stop writing separate optimization paths for every chipset vendor.

Фото профиля Amit Kairon
Amit Kairon8 месяцев назад

Insane, this is going to shake things up..waiting for devices to get ripped up.

Фото профиля CEO del Socialismo de Mercado🌹🕊️ 市场社会主义CEO
CEO del Socialismo de Mercado🌹🕊️ 市场社会主义CEO8 месяцев назад

@ecuarauz

Фото профиля 10turtle
10turtle8 месяцев назад

On-device AI frameworks like this can be a big win for businesses better performance, lower latency, and more privacy. That combination matters for real-world adoption.

Фото профиля Адам Прокопович
Адам Прокопович7 месяцев назад

Hello. I was banned from Google AI Developers Forum. Can someone review my account and lift the unreasonable suspension?

Фото профиля Aayush Pathak
Aayush Pathak8 месяцев назад

@grok how is this different from google ai edge

Фото профиля sol
sol8 месяцев назад

@CM_CryptoMatrix 变化真的很快

Фото профиля Akshay Bhasme
Akshay Bhasme8 месяцев назад

Hi @googledevs @GoogleIndia @GooglePlay — your partner @BillDesk_India is having a serious connectivity issue. I’ve been unable to complete my onboarding for 3+ days. The form won’t proceed at all. Please look into this.

Фото профиля Sriram Kiron
Sriram Kiron8 месяцев назад

awesome

Фото профиля OOM
OOM8 месяцев назад

I love any advances in on device tech

Фото профиля vivek nakalgaonkar
vivek nakalgaonkar8 месяцев назад

@grok is it lighter than gema?

Фото профиля Kanthipriya Mahale
Kanthipriya Mahale7 месяцев назад

On-device AI is underrated. I built Aiden — a fully offline executive assistant for iOS using Core ML. No cloud. No external servers. Everything runs locally. Privacy-first AI is the future.

Фото профиля 🌊 Sorbus
🌊 Sorbus8 месяцев назад

There will be optimization for others Hexagon NPU?

Фото профиля Saïd Aitmbarek
Saïd Aitmbarek8 месяцев назад

we need more on-device/light frameworks & models, let's go!

Фото профиля ZETIC
ZETIC8 месяцев назад

@grok does LiteRT run ANE on iOS devices?

Фото профиля Sebastian Buzdugan
Sebastian Buzdugan8 месяцев назад

unified npu support with jax is super interesting

Фото профиля Delight Okechukwu
Delight Okechukwu8 месяцев назад

Faster GPUs and NPU support makes this very interesting for production use.

Фото профиля Chathebots
Chathebots8 месяцев назад

@grok comment esseyer ?

Фото профиля Musty
Musty8 месяцев назад

Hey I want to do an internship in your organization

Фото профиля Emma
Emma8 месяцев назад

Is there a way to turn it off?

Фото профиля DreamCode
DreamCode8 месяцев назад

cool, research it.

Фото профиля Peter
Peter7 месяцев назад

How to get these tools more popular to the Google fáns! Vids Stitch Flow Dopple Opal NotebookLM Whisk

Фото профиля Mark Okafor
Mark Okafor8 месяцев назад

AI tip of my fingers 👍🏿

Похожие видео