Demo: Optimizing Gemma inference on NVIDIA GPUs with TensorRT-LLM
2 972
12.5
Google Developers2.39 млн
Следующее
218 дней – 2 9350:42Популярные
24 дня – 1 4490:59
83 дня – 3 0660:23Опубликовано 2 апреля 2024, 4:00
Even the smallest of Large Language Models are compute intensive significantly affecting the cost of your Generative AI application. Your ability to increase the throughput and reduce latency can make or break many business cases. NVIDIA TensorRT-LLM is an open-source tool that allows you to considerably speed up execution of your models and in this talk we will demonstrate its application to Gemma.
Checkout more videos of Gemma Developer Day 2024 → goo.gle/440EAIV
Subscribe to Google for Developers → goo.gle/developers
#Gemma #GemmaDeveloperDay
Event: Gemma Developer Day 2024
Products Mentioned: Gemma
Checkout more videos of Gemma Developer Day 2024 → goo.gle/440EAIV
Subscribe to Google for Developers → goo.gle/developers
#Gemma #GemmaDeveloperDay
Event: Gemma Developer Day 2024
Products Mentioned: Gemma
Свежие видео
3 дня – 1 761 45325:35
6 дней – 012:17
8 дней – 216 67150:16
8 дней – 10 4511:18
9 дней – 125 2741:03Случайные видео
92 дня – 2 0820:23
03.04.23 – 326 06718:06
26.02.22 – 278 23112:49
29.01.22 – 8553:01
14.10.21 – 8000:48
18.10.08 – 104 3366:40
3 дня – 3195:11
6 дней – 8 4243:14
10 дней – 7190:23
15 дней – 255 9759:52
18 дней – 11 8482:47
23 дня – 3 1602:18
2 часа – 2991:16