Dnotitia Unveils STAR-KV, Achieving UP to 20x KV Cache Compression, Selected as an ICML 2026 Spotlight Paper
Introduces a low-rank-based approach to KV cache compression, one of the key bottlenecks in long-context AI Speeds up attention computation by up to 6.9x and overall generation throughput by up to 3.1x, moving beyond memory savings to faster...
Dnotitia Releases DNA 3.0, an Enterprise-Ready AI Language Model Family
Built on Qwen 3.5/3.6 and tuned for institutional and enterprise use Dnotitia releases DNA 3.0, a family of AI language models built on Qwen 3.5/3.6 and enhanced through proprietary post-training The model family is designed to help organizations...