inference

inference, newest first

1. 

   AI

   OpenAI’s Jalapeño Chip Shows Strong AI Inference Performance in Early Benchmarks

   OpenAI reveals Jalapeño chip benchmarks showing improved AI inference speed, efficiency, and scalability compared with current systems.

   By Shivangi Yadav25 August 20262 min read
2. 

   AI

   Runware Unveils Portable AI Data Centre to Expand Inference Capacity

   Runware has introduced the Sonic Inference Pod, a modular AI data centre designed to deliver scalable inference closer to users with lower infrastructure costs.

   By Shivangi Yadav5 August 20263 min read
3. 

   AI

   Luminal raises $5.3 million to build a better GPU code framework

   Luminal secures $5.3M to develop a next-gen GPU code framework that boosts performance through compiler optimisation and smarter compute efficiency.

   By TechAmerica.ai Staff17 November 20253 min read
4. 

   AI

   DeepSeek releases ‘sparse attention’ model that cuts API costs in half

   DeepSeek unveils its experimental V3.2-exp model featuring Sparse Attention — a breakthrough that halves API inference costs in long-context operations and boosts transformer efficiency.

   By TechAmerica.ai Staff4 October 20252 min read