Nvidia
@nvidia·2.2M subscribers·2.7K videos
Pruning AI Models for Peak Performance - NVIDIA DRIVE Labs Ep. 31
Posted
September 19, 2023
Views
10,540
Likes
190
Engagement
1.80%
September 19, 2023
10,540
190
1.80%
Every word spoken in this episode is indexed. Type any phrase to jump straight to the moment it was said.
Type any word or phrase that may have been spoken. Click a result to seek the player to that exact moment.
Try a name, a topic, or a quoted line
3:16Now PlayingCheck out HALP (Hardware-Aware Latency Pruning), a new method designed to adapt convolutional neural networks (CNNs) and #transformer-based architectures for real-time performance. HALP optimizes pre-trained models to maximize compute utilization. In testing with NVIDIA DRIVE Orin™ on the road, it consistently outperformed alternative approaches.
Product page
Watch the full series here
Learn more about DRIVE Labs
Follow us on social:
#NVIDIADRIVE
Sentinel Indexing in Progress
Metadata and chapters are available. Claim extraction for this episode is pending.
All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel provides research tools that promote discovery and accountability across political media.
