venturebeat
IndexCache, a new sparse attention optimizer, delivers 1.82x faster inference on long-context AI models

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 [...]

Rating

Innovation

Pricing

Technology

Usability

We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.

venturebeat
Baseten takes on hyperscalers with new AI training platform that lets you own your model weights

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 [...]

Match Score: 137.69

venturebeat
Attention ISN'T all you need?! New Qwen3 variant Brumby-14B-Base leverages Power Retention technique

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 [...]

Match Score: 128.70

venturebeat
New ‘Test-Time Training’ method lets AI keep learning without exploding inference costs

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 [...]

Match Score: 123.37

venturebeat
GAM takes aim at “context rot”: A dual-agent memory architecture that outperforms long-context LLMs

For all their superhuman power, today’s AI models suffer from a surprisingly human flaw: They forget. Give an AI assistant a sprawling conversation, a multi-step reasoning task or a project spanning [...]

Match Score: 112.26

venturebeat
DeepSeek's new V3.2-Exp model cuts API pricing in half to less than 3 cents per 1M input tokens

DeepSeek continues to push the frontier of generative AI...in this case, in terms of affordability.The company has unveiled its latest experimental large language model (LLM), DeepSeek-V3.2-Exp, that [...]

Match Score: 109.28

venturebeat
Together AI's ATLAS adaptive speculator delivers 400% inference speedup by learning from workloads in real-time

Enterprises expanding AI deployments are hitting an invisible performance wall. The culprit? Static speculators that can't keep up with shifting workloads.Speculators are smaller AI models that w [...]

Match Score: 106.92

venturebeat
AI inference costs dropped up to 10x on Nvidia's Blackwell — but hardware is only half the equation

Lowering the cost of inference is typically a combination of hardware and software. A new analysis released Thursday by Nvidia details how four leading inference providers are reporting 4x to 10x redu [...]

Match Score: 102.37

venturebeat
ACE prevents context collapse with ‘evolving playbooks’ for self-improving AI agents

A new framework from Stanford University and SambaNova addresses a critical challenge in building robust AI agents: context engineering. Called Agentic Context Engineering (ACE), the framework automat [...]

Match Score: 101.69

venturebeat
New KV cache compaction technique cuts LLM memory 50x without accuracy loss

Enterprise AI applications that handle large documents or long-horizon tasks face a severe memory bottleneck. As the context grows longer, so does the KV cache, the area where the model’s working me [...]

Match Score: 95.72