LLM Serving simulation for multi-core NPU

Asynchronous semantics for architectural simulation and synthesis.

A machine learning accelerator core designed for energy-efficient AI at the edge.

kernels, of the mega variety

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Open, Modular, Deep Learning Accelerator

cricket is a virtualization solution for GPUs

A reference-counted netlist library for EDA tool development

Run Time for AIE and FPGA based platforms

The CP-SAT Primer: Using and Understanding Google OR-Tools' CP-SAT Solver

WaferLLM: Large Language Model Inference at Wafer Scale

Asterinas is a secure, fast, and general-purpose OS kernel, written in Rust and providing Linux-compatible ABI.

A collection of pre-trained, state-of-the-art models in the ONNX format

Fork of LLVM to support AMD AIEngine processors

AMD Ryzen™ AI Software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen™ AI powered PCs.

Exocompilation for productive programming of hardware accelerators

Berkeley's Spatial Array Generator

An MLIR Complier for PyTorch/C/C++ Codes into HLS Dataflow Designs

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

ARIES: An Agile MLIR-Based Compilation Flow for Reconfigurable Devices with AI Engines (FPGA 2025 Best Paper Nominee)

An MLIR-based toolchain for AMD AI Engine-enabled devices.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Bridging polyhedral analysis tools to the MLIR framework