Contact_

Request a
Business Customized Quotation

Phone

+886 2 8797 8337

HQ

12F-2, No.408, Ruiguang Rd., Neihu Dist., Taipei City 11492, Taiwan

BR

Center of Innovative Incubator R819, No. 101, Section 2, Kuang-Fu Road, Hsinchu, Taiwan

Submit

The Industrialization of AI

Skymizer’s system software solutions enable AI-on-Chip design houses to automate AI application development,
improve system performance, and optimize inference accuracy.
01_

Our Key Values

Automate Application Development

Enable AI SoC to be easily adopted in frequently evolved applications by automatically compiling AI algorithms into chip’s machine code.

Analyze System Bottlenecks

Leverage virtual platforms to conduct Performance-Guided Optimizations (PGO) to improve speed and reduce memory requirements by utilizing all available computing/memory resources in the complex heterogeneous multicore systems.

Enhance Accuracy and Performance through Hardware/Software Co-optimization

Align software development at a much earlier stage during SoC architecture exploration stage. Provide architecture-aware calibrations to maintain precision even in Int8 mode.

02_

Our Belief

LLM as Essential Interface

LLM will become a crucial interface for human-to-machine and machine-to-machine communication.

Edge Inference and Fine-Tuning Growth

Inference and fine-tuning are transitioning to the edge and are poised for much greater growth than training.


Key benefits include security, privacy, personalization, response time, and cost-effectiveness.

Dedicated Language Processor Unit (LPU)

LPUs offer superior performance, power efficiency, and cost-effectiveness compared to CPU/GPU/NPU solutions.

03_

EdgeThought

High Performance and Low Cost

High memory bandwidth utilization.

Shortest response time with minimal MAC requirement.

Programmable and Model-flexible

Minimal yet efficient LLM-specific instruction set supports diverse decoder-only transformers, including LLaMA2, LLaMA3, Mistral, Phi-2, Phi-3, Gemma, etc.


Currently focusing on 7-13B models. Larger models require more DRAM capacities.

Ecosystem Ready

LLM Frameworks: HuggingFace Transformers, Nvidia Triton Inference Server, OpenAI API, and LangChain API.


Fine-Tuning and RAG Toolkits: HuggingFace PEFT, QLoRA, LlamaIndex, and LangChain.

05_

Products

ONNC

Commercial
Learn More

ONNC

Commercial
Learn More

ONNC compiler is a bundle of C++ libraries and tools to boost your development of compiler for deep learning accelerators (DLAs). ONNC compiler targets on diverse SoC architectures from a simply single core system to a heterogeneous system with multi-level memory hierarchy and bus connection.

Forest
Runtime

Commerical
Learn More

Forest
Runtime

Commerical
Learn More

Forest Runtime executes compiled neural network models on the hardware platform of your choice. It provides common C++ APIs with C and Python bindings for various AI application doing inference. Forest Runtime is '''retargetable'''. It has modular architecture and we've ported it on diverse hardware platforms, including ''datacenter'', ''mobile'' and ''TinyML''.

Calibrator

Commerical
Learn More

Calibrator

Commerical
Learn More

ONNC Calibrator leverages hardware architecture information to keep AI System-on-Chips in high precision through the post-training quantization (PTQ) technique. The key indicator to validate a quantization technique is its precision drop.