Nvidia shrinks LLM memory 20x without changing model weights

Nvidia's KV Cache Transform Coding (KVTC) compresses LLM key-value cache by 20x without model changes, cutting GPU memory costs and time-to-first-token by up to 8x for multi-turn AI applications.

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

MIT researchers developed Attention Matching, a KV cache compaction technique that compresses LLM memory by 50x in seconds — ...
News-Press NOW

Penguin Solutions Introduces Industry's First Production-Ready CXL-Based KV Cache Server

Penguin Solutions, Inc. (Nasdaq: PENG ), the AI factory platform company, today announced the industry's first ...
TMCnet

Penguin Solutions' OriginAI Factory Platform Delivers Optimized Performance for AI Inference

OriginAI inference solutions are designed leveraging Penguin Solutions 3.3+ billion hours of GPU runtime experience and more ...
Semiconductor Engineering

Dynamic KV Cache Scheduling in Heterogeneous Memory Systems for LLM Inference (Rensselaer Polytechnic Institute, IBM)

A new technical paper titled “Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System” was published by researchers at Rensselaer Polytechnic Institute and IBM. “Large ...

New memory architecture targets AI inference bottlenecks

Lightbits Labs Ltd. today is introducing a new architecture aimed at addressing one of the most stubborn bottlenecks in large ...