HyperThought™
Next-generation LPU IP, purpose-built for LLMs and optimized for performance and power efficiency — designed to bring intelligent, multimodal, agentic AI to the edge and on-prem. Build your own AI chip.
Foundation
Driving innovation with LISA v3 and LPU IP
HyperThought is built on the LISA™ (Language Instruction Set Architecture) foundation and an Octa-Core HTX301 LPU processor. It's a compiler-driven, software-hardware co-design that maps modern language models onto efficient silicon — without demanding a cutting-edge process node.
- Multimodal and agentic AI at the edge
- Automotive, industrial, and on-prem inference
- Multi-chip scalability for extreme performance
Performance
Fast where it counts
Why HyperThought
Efficiency by design
Octa-core, multi-chip
Octa-Core HTX301 processor on LISA v3, scalable across chips for extreme performance.
Compression built in
Weight compression beats llama.cpp by 9%–17.8%; KV-cache compression with 0.06%–3.52% perplexity loss.
Mature-node ready
T28nm with standard LPDDR4/5 — optimized for lower DRAM bandwidth.
Secure & scalable
Security-focused instruction architecture with a compact, balanced compute footprint.