Semidynamics Inferencing Tools Accelerate AI App Deployment on Cervell NPU
From trained model to running product—faster, with ONNX Runtime integration and production-grade samples
Santa Clara, USA — October 22, 2025 — Semidynamics today announced the Semidynamics Inferencing Tools, a new software suite that lets developers deploy AI applications on the Cervell RISC-V NPU in a fraction of the time.
Sitting above the Aliado SDK and leveraging Semidynamics’ ONNX Runtime Execution Provider, the suite streamlines everything from session setup to tensor management, so teams can move from a trained model to a running product quickly and confidently.
“Developers want results,” said Pedro Almada, lead software developer, Semidynamics. “With the Inferencing Tools, you point to an ONNX model, choose your configuration, and you’re running on Cervell—prototype in hours, then harden for production.”
Organizations building AI features—assistants, agents, vision pipelines—can now target Cervell with less integration overhead, shorter development cycles, and a clearer path from prototype to production. The Inferencing Tools focus teams on application logic and user value while maintaining a clean, maintainable codebase.
Highlights
- Faster time-to-production: High-level library on top of Semidynamics’ ONNX Runtime Execution Provider for Cervell—no model conversion required.
- Built-in guidance: Clean APIs handle session setup, tensor management, and inference orchestration, reducing repetitive code and integration risk.
- Production-grade examples: Ready-to-adapt samples for LLM chatbots (e.g., Llama, Qwen), object detection (YOLO family), and image classification (ResNet, MobileNet, AlexNet).
- Validated at scale: Tested by Semidynamics across a wide range of ONNX models to help ensure predictable performance and robust deployment.
- One ecosystem, two lanes:
- Aliado SDK for kernel-level control and peak performance.
-
Inferencing Tools for rapid iteration, cleaner app code, and faster shipping.
The Semidynamics Inferencing Tools are available today in the Software Centre to Semidynamics customers and partners.
About Semidynamics
Semidynamics is the only company offering fully customizable RISC-V processor IP. With expertise in high-bandwidth architectures, vector/tensor extensions, and groundbreaking memory systems, Semidynamics enables customers to design exactly the core they need for AI, HPC, and other performance-critical workloads. Based in Barcelona, Semidynamics is redefining what’s possible with RISC-V.
Related Semiconductor IP
- NPU
- NPU IP Core for Mobile
- NPU IP Core for Edge
- Specialized Video Processing NPU IP
- NPU IP Core for Data Center
Related News
- Semidynamics Announces Cervell™ All-in-One RISC-V NPU Delivering Scalable AI Compute for Edge and Datacenter Applications
- Cadence Expands Digital Twin Platform Library with NVIDIA DGX SuperPOD Model to Accelerate AI Data Center Deployment and Operations
- Ceva Appoints Former Microsoft AI and Hardware Leader Yaron Galitzky to Accelerate Ceva’s AI Strategy and Innovation at the Smart Edge
- GlobalFoundries and Navitas Semiconductor Partner to Accelerate U.S. GaN Technology and Manufacturing for AI Datacenters and Critical Power Applications
Latest News
- Mixel MIPI IP Integrated into Automotive Radar Processors Supporting Safety-critical Applications
- GlobalFoundries and Navitas Semiconductor Partner to Accelerate U.S. GaN Technology and Manufacturing for AI Datacenters and Critical Power Applications
- VLSI EXPERT selects Innatera Spiking Neural Processors to build industry-led neuromorphic talent pool
- SkyWater Technology and Silicon Quantum Computing Team to Advance Hybrid Quantum-Classical Computing
- Dnotitia Revolutionizes AI Storage at SC25: New VDPU Accelerator Delivers Up to 9x Performance Boost