DeepSeek's new model slashes AI inference costs
DeepSeek unveils V3.2-exp, a model designed to significantly reduce inference costs with its innovative sparse attention system.
posted on 09/29/2025News about: Inference
Google's Ironwood: Optimized AI Inference for Cloud Customers
Google unveils Ironwood, its 7th gen TPU, optimized for AI inference, offering enhanced performance and efficiency for Google Cloud customers.
posted on 04/09/2025
Inference-Time Search: A New AI Scaling Law or Just a Workaround?
Exploring the potential of inference-time search as a new AI scaling law, examining its benefits and limitations according to experts.
posted on 03/19/2025