tile-ai ORG

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

Tile-Based Runtime for Ultra-Low-Latency LLM Inference

Learning TileLang with 10 puzzles!

Ascend TileLang adapter

Tile-based language built for AI computation across all scales

High-performance LLM operator library built on TileLang.

No description.

No description.

No description.

MLIR-based TileLang Ascend Adapter

No description.

Open deep learning compiler stack for cpu, gpu and specialized accelerators

ReDesign of https://github.com/microsoft/BitBLAS

Efficient End2End Compiler for Mixed-Precision Deep Learning

Efficient TileLang Kernels for LLM Training

No description.

No description.

Documentation site for TileOps —— a high-performance LLM operator library built on TileLang.

DeepStack: Facilitating Co-Design Exploration of 3D DRAM-Stacked Accelerators for Distributed LLM Inference. Includes the MICRO 2026 AE artifact.

No description.

No description.

Tilelang compatible z3 build

CUDA Templates for Linear Algebra Subroutines