1
Fast Llama 2 on CPUs with Sparse Fine-Tuning and DeepSparse
From live events to hands-on product demos to deep technical research, see what we're doing with AI at Red Hat.
Neural Magic Blog
From live events to hands-on product demos to deep technical research, see what we're doing with AI at Red Hat.
- Popular posts
- 3
- Total points
- 590
- HN comments
- 211
- Rank
- #2,312 company
Visit neuralmagic.com → On Hacker News Sep 2021 – Nov 2024
AI & Machine Learning 3Systems & Performance 2Databases & Data 1
2
What happens if we remove 50 percent of Llama?
Discover Sparse Llama: A 50% pruned, GPU-optimized Llama 3.1 model with 2:4 sparsity, enabling faster, cost-effective inference without sacrificing accuracy.
3
YOLOv5 on CPUs: Sparsifying to Achieve GPU-Level Performance
From live events to hands-on product demos to deep technical research, see what we're doing with AI at Red Hat.