FFI-SDK
FlowforestDeveloper Toolchain

FFI-SDK

End-to-End CIM AI Model Development Toolchain

From model import, quantization, compilation optimization to hardware simulation and deployment, FFI-SDK provides a complete development experience to maximize AI model performance on FFI8805 series hardware.

0%
HW Correlation
0 Frameworks
Supported AI Frameworks
0
OS Support
0+
Pre-built Templates
Core Features

Full-Stack Development Tools

FFI-SDK covers every stage from AI model development to deployment, providing industry-leading compilers, profilers, and simulators.

CIM Compiler

Compile ONNX/TFLite/PyTorch models to FFI8805 native instruction set with automatic graph optimization, memory scheduling, and operator fusion.

Performance Profiler

Layer-by-layer, operator-level profiling including latency, memory bandwidth, and power metrics with bottleneck identification.

Hardware Simulator

Cycle-accurate hardware simulator with > 98% correlation to actual silicon, enabling model validation without physical hardware.

Quantization Optimizer

INT4/INT8/FP16 mixed-precision quantization with automatic strategy search, < 0.5% accuracy loss while maximizing inference speed.

CLI Tools

Command-line interface for batch compilation, automated testing, and script integration, ideal for CI/CD pipelines and large-scale deployment.

CI/CD Integration

GitHub Actions / GitLab CI templates with model version management, automated regression testing, and deployment pipelines.

Compilation Pipeline

Five-Step Model Deployment

FFI-SDK simplifies the complex CIM compilation process into five intuitive steps from model import to hardware deployment.

1

Model Import

ONNX / TFLite / PyTorch / PaddlePaddle

2

Quantization

INT4/INT8/FP16 mixed-precision auto-search

3

CIM Compile

Graph optimization + memory scheduling + op fusion

4

HW Simulation

Cycle-accurate simulation & perf estimation

5

Deploy

One-click deploy to FFI8805 target hardware

Supported Frameworks

FFI-SDK natively supports major AI frameworks with no manual model format conversion required.

ONNX
1.14+
TensorFlow Lite
2.x
PyTorch
2.0+
PaddlePaddle
2.5+
Interactive Demo

SDK Compilation Flow Experience

Simulate the complete FFI-SDK compilation flow from model import to deployment, click each step for details

Model Import
Quantization
CIM Compile
HW Simulation
Deploy
Select model and parameters, then click Start Compile

Detailed Technical Specifications

Login to View Full Specs

Detailed specifications and use cases require login to access.

Get Started with FFI-SDK

Contact our technical team for FFI-SDK trial license and support.