ai-compiler

Open deep learning compiler stack for Kendryte AI accelerators ✨

A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.

FREE TPU V3plus for FPGA is the free version of a commercial AI processor (EEP-TPU) for Deep Learning EDGE Inference

Deterministic ONNX-to-C compiler for embedded and safety-critical systems, generating static, auditable C code with no dynamic memory or runtime dependencies.

Camel is a graph-native, multi-stage, and type-driven domain-specific language (DSL) designed to bridge the gap between AI research and production deployment.

This is a cross-chip platform collection of operators and a unified neural network library.

World's first compiler and execution platform for AI systems — turn prompts, skills, and multi-step agent workflows into versioned, packageable software that runs with dependency-aware parallel execution.

Backend for triton language to compile and execute triton kernel

TREe Ensemble COmpiler for efficient inferences

Your AI Catalyst: inference backend to maximize your model's inference performance

MLIR-OPT-SKILL is an agent skill for optimizing MLIR GPU code generation.

kolm — the AI compiler. Compile any task into a signed .kolm artifact that runs locally. RS-1 open spec, MIT.

🍒 A simple AI compiler based on MLIR

FORCE AI: Fast Optimization for Resource-Constrained Efficient AI Inference

A step-by-step implementation of the MLIR Toy compiler tutorial with custom dialect, shape inference, pattern rewrites, and Matmul affine lowering.基于 MLIR 的 Toy 编译器从零实战教程，涵盖方言定义、AST转译、形状推导、规范化重写及自定义 Matmul 算子的 Affine 降级实现。

C++20 AI graph compiler and heterogeneous inference runtime — ONNX -> optimized IR -> CPU/GPU/NPU partitioning -> static memory planning -> .aigc -> graph-independent execution.

Hardware-agnostic AI compiler suite. Compile GGUF, ONNX, PyTorch, and SafeTensors models onto FPGAs, analog circuits, MCU swarms, photonic MZI meshes, neuromorphic chips, and CIM accelerators — not GPUs. Includes SiL emulator, real-time dashboard, federated learning, and carbon-aware compilation.

my blog，about AI compiler, Operator accelerate, Neural network

The ultimate AI compiler based on MLIR

Browser-based IDE for a custom DSL - full compiler pipeline (Lexer → Parser → AST → Evaluator) with AI-powered error correction, auto-fix, and CodeMirror editor. Python + HTML/JS.