Exhibition category
Contact address
| Address | 6-10-1 GINZA SIX 13F, Ginza, Chuo, Tokyo, Japan |
|---|---|
| Telephone | 0364179661 |
| URL | https://www.edgecortix.com/en/ |
| info@edgecortix.com |
Main exhibits 1
SAKURA-II Edge AI Accelerator
High-performance, 60 TOPS, edge AI accelerator architected to run the latest vision and Generative AI models with market-leading energy efficiency and low latency.
Optimized for Generative AI: Supports multi-billion parameter Generative AI models within a typical power envelope of 8W
Efficient AI Compute: Achieves very high AI compute utilization, resulting in exceptional energy efficiency
Enhanced Memory Bandwidth: High performance DRAM bandwidth, ensuring superior performance for LLMs and LVMs
Large DRAM Capacity: Support for up to 32GB of DRAM, enabling efficient processing of complex vision and Generative AI workloads
Real-Time Data Streaming: Optimized for low-latency operations with Batch=1
Arbitrary Activation Function Support: Hardware-accelerated approximation provides enhanced adaptability
Advanced Precision: Software-enabled mixed-precision provides near FP32 accuracy
Efficient Data Handling: Integrated tensor reshaper engine minimizes host CPU load
Sparse Computation: Reduces memory footprint and optimizes DRAM bandwidth
Power Management: Advanced power management enables ultra-high efficiency modes
EdgeCortix-SAKURA-II-AI-Accelerator-ENG- （PDF file - 1,927KB）
Main exhibits 2
SAKURA-II Edge AI PCIe Cards
High-performance, up to 120 TOPS, PCIe Cards architected to run the latest vision and Generative AI models with market-leading energy efficiency and low latency.
Optimized for Generative AI: Supports multi-billion parameter Generative AI models within a typical power envelope of 10W
Efficient AI Compute: Very high AI compute utilization, resulting in exceptional energy efficiency
Enhanced Memory Bandwidth: High performance DRAM bandwidth, ensuring superior performance for LLMs and LVMs
Large DRAM Capacity: Up to 32GB of DRAM, enabling efficient processing of complex Generative AI workloads
Real-Time Data Streaming: Optimized for low-latency operations with Batch=1
Arbitrary Activation Function Support: Hardware-accelerated approximation provides enhanced adaptability
Advanced Precision: Software-enabled mixed-precision provides near FP32 accuracy
Sparse Computation: Reduces memory footprint and optimizes DRAM bandwidth
Power Management: Advanced power management enables ultra-high efficiency modes
Low Profile PCIe Cards: Best choice high performance edge AI servers and appliances
EdgeCortix-SAKURA-II-PCIe-ENG- （PDF file - 1,919KB）
Main exhibits 3
SAKURA-II Edge AI M.2 Modules
High-performance, up to 120 TOPS, PCIe Cards architected to run the latest vision and Generative AI models with market-leading energy efficiency and low latency.
Optimized for Generative AI: Supports multi-billion parameter Generative AI models within a typical power envelope of 10W
Efficient AI Compute: Very high AI compute utilization, resulting in exceptional energy efficiency
Enhanced Memory Bandwidth: High performance DRAM bandwidth, ensuring superior performance for LLMs and LVMs
Large DRAM Capacity: Up to 32GB of DRAM, enabling efficient processing of complex Generative AI workloads
Real-Time Data Streaming: Optimized for low-latency operations with Batch=1
Arbitrary Activation Function Support: Hardware-accelerated approximation provides enhanced adaptability
Advanced Precision: Software-enabled mixed-precision provides near FP32 accuracy
Sparse Computation: Reduces memory footprint and optimizes DRAM bandwidth
Power Management: Advanced power management enables ultra-high efficiency modes
Small Form Factor: M.2 is the ideal size for space-constrained designs
