WebAssembly and WebGPU enhancements for faster Web AI
5 880
14.1
Google Chrome Developers770 тыс
Следующее
224 дня – 6 59446:30Популярные
18 дней – 1 7470:15
85 дней – 22 582 0280:59Опубликовано 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
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
9 дней – 119 77114:24
10 дней – 4001:58
11 дней – 1 5964:14
12 дней – 5 8800:31
13 дней – 6253:32
Случайные видео
261 день – 205 44718:45
354 дня – 549 6730:55
08.08.23 – 19 9471:29
01.12.22 – 2362:32
19.05.22 – 24 9615:46
31.12.12 – 25 0977:25
3 дня – 1 036 36614:56
6 дней – 3702:45
6 дней – 4 69318:52
8 дней – 144 03947:55
8 дней – 45 5792:42
9 дней – 18 62428:48
4 дня – 6 0830:24