Skip to content
AI Lehel Briefing
← Back to latest
Infrastructure OpenAI

Block-sparse GPU kernels

We’re releasing highly-optimized GPU kernels for an underexplored class of neural network architectures: networks with block-sparse weights. Depending on the chosen sparsity, these kernels can run orders of magnitude faster than cuBLAS or cuSPARSE. We’ve used them to attain state-of-the-art results in text sentiment analysis and generative modeling of text and images.

Excerpt supplied by the publisher’s feed

Read the original article at OpenAI Opens in a new tab

More in Infrastructure

Infrastructure AWS Machine Learning

Rethinking access control for RAG with Amazon Quick and Amazon Bedrock

Enterprise RAG unlocks insights from knowledge sources like SharePoint, Google Drive, and Confluence, but those sources carry complex permissions. Learn how Amazon Quick and Amazon Bedrock Knowledge Bases enforce document-level access controls in real time, verifying permissions directly with authoritative sources at query time.

Read brief Original at AWS Machine Learning (opens in a new tab) ↗
Infrastructure AWS Machine Learning

Beyond hours saved: Building the business case for agentic automation

The RPA-era ROI model misses most of the value agentic automation creates. This post gives AI center of excellence leaders a framework to size the full value of agents across time savings, exception handling, decision quality, and maintenance economics, and to prioritize which workflows to automate first.

Read brief Original at AWS Machine Learning (opens in a new tab) ↗