Processing 200,000 tokens through a large language model is expensive and slow: the longer the context, the faster the costs spiral. Researchers at Tsinghua University and Z.ai have built a technique called IndexCache that cuts up to 75% of the redundant computation in sparse attention models, delivering up to 1.82x faster time-to-first-token and 1.48x faster generation throughput at that context length.The technique applies to models using the DeepSeek Sparse Attention architecture, including the latest DeepSeek and GLM families. It can help enterprises provide faster user experiences for production-scale, long-context models, a capability already proven in preliminary tests on the 744-billion-parameter GLM-5 model.The DSA bottleneckLarge language models rely on the self-attention mechani [...]
A little-known Miami-based startup called Subquadratic emerged from stealth on Tuesday with a sweeping claim: that it has built the first large language model to fully escape the mathematical constrai [...]
Cerebras Systems, the Silicon Valley chipmaker that built the world's largest commercial AI processor, erupted onto the Nasdaq on Wednesday, opening at $350 per share — nearly double its $185 I [...]
Across 101 enterprises, the context feeding AI agents is failing often and repeatedly. Sixty-eight percent have traced a confident but wrong agent answer to missing or inconsistent business context in [...]
Among the many Chinese AI companies and laboratories vying for market share and attention (no pun intended) on the global marketplace, MiniMax stands out for its commitment to providing frontier-level [...]
For the last 24 months, one narrative justified every over-provisioned data center and bloated IT budget: the GPU scramble. Silicon was the new oil, and H100s traded like contraband. Reserve capacity [...]
When the transformer architecture was introduced in 2017 in the now seminal Google paper "Attention Is All You Need," it became an instant cornerstone of modern artificial intelligence. Ever [...]
When an agentic AI system hands a task from a small model to a larger one — or back down again — it pays a steep tax: the receiving model has to recompute the entire conversation from scratch, dri [...]
Baseten, the AI infrastructure company recently valued at $2.15 billion, is making its most significant product pivot yet: a full-scale push into model training that could reshape how enterprises wean [...]
A new study from researchers at Stanford University and Nvidia proposes a way for AI models to keep learning after deployment — without increasing inference costs. For enterprise agents that have to [...]