WebAssembly and WebGPU enhancements for faster Web AI

2 768
14
Следующее
Популярные
34 дня – 17 3114:27
The Pile Mini Web Machine
Опубликовано 16 мая 2024, 14:04
Running AI inference directly on client machines reduces latency, improves privacy by keeping all data on the client, and saves server costs. To accelerate these workloads, WebAssembly and WebGPU are evolving to incorporate new low-level primitives. Learn how these new additions unlock fast hardware capabilities to significantly speed up AI inference and enable highly tuned inference libraries and frameworks to efficiently run large AI models.

Speakers: Deepti Gandluri, Austin Eng

Watch more:
Check out all the Web videos at Google I/O 2024 → goo.gle/io24-web-yt
Check out all the AI videos at Google I/O 2024 → goo.gle/io24-ai-yt

Subscribe to Google Chrome Developers → goo.gle/ChromeDevs

#GoogleIO

Event: Google I/O 2024
Свежие видео
2 дня – 9 423 8111:43:37
WWDC 2024 — June 10 | Apple
5 дней – 415 6640:39
iPhone + Apple Watch | Big Fish | Apple
7 дней – 56 4949:40
Adam Savage vs. His Peers?
автотехномузыкадетское