ADAS (Advanced Driver Assistance Systems)
We Enable:
• High performance compute of all functional blocks• Real-time perception with latest high performing CNN and transformer models
• Sensor fusion of all modalities
• Reasoning and path planning
• Application of latest GenAI technology
Why SiMa:
• Low Latency• Best-in-class performance / Watt enabling significant cost savings on ECU level
• Ultra-low development effort
IVI (In Vehicle Infotainment)
We Enable:
• On-edge and hybrid conversational assist systems• Consistently high performance without interruptions
• Better security and reduced cloud costs
Why SiMa:
• Best-in-class performance for LLMs, VLMs, and VLAs• Low latency (TTFT) and high throughput (token/s)
• Push-button deployment that saves development time and cost
ADAS: Perception Enrichment Using GenAI
Conversational Assist Systems
In-Vehicle Infotainment
Transforming mobility
SiMa.ai Solution Detail
Products
- Low Power SiMa GenAI ECU and MLSoC Modalix
- Palette Llima Toolchain for GenAI deployment
Services
- Support in selection and deployment of latest GenAI models
- Enable customer application on Modalix
- E/E integration support
Solution Overview
- Lowest latency and high performance
- Multimodal capabilities
- Fast introduction into existing E/E architectures
- Low-Power enables fanless design
Challenges
- Consistent performance independent from connectivity
- Easy integration into the vehicle (e.g. power dissipation)
Solution
- Local inferencing of SLM on Modalix
- Easy deployment with Llima toolchain
Results
- Best-in-class edge conversational assist functionality
“Our partnership with SiMa.ai represents a major leap forward in deploying efficient on-device AI for current and next-generation vehicles. Within Cerence xUI, CaLLM Edge delivers advanced reasoning, multi-turn conversation, and proactive engagement, all running seamlessly on the MLSoC Modalix. With cross-platform compatibility and hardware flexibility, we empower OEMs to adapt quickly, reduce complexity, and deploy bespoke in-car assistants across different vehicle platforms.”
Nils Schanz
EVP, Product & Technology, Cerence AI