Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

[ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

QUDA is a library for performing calculations in lattice QCD on GPUs.

CUDA Kernel Benchmarking Library

AMD's graph optimization engine.

AOMP is an open source Clang/LLVM based compiler with added support for the OpenMP® API on Radeon™ GPUs. Use this repository for releases, issues, documentation, packaging, and examples.

LLVM/MLIR based compiler instrumentation of AMD GPU kernels

[DEPRECATED] Moved to ROCm/rocm-systems repo

AI Tensor Engine for ROCm

FlashMLA: Efficient Multi-head Latent Attention Kernels

[DEPRECATED] Moved to ROCm/rocm-libraries repo

[DEPRECATED] Moved to ROCm/rocm-libraries repo

A retargetable MLIR-based machine learning compiler and runtime toolkit.

CUDA Templates and Python DSLs for High-Performance Linear Algebra

[DEPRECATED] Moved to ROCm/rocm-libraries repo

HIP: C++ Heterogeneous-Compute Interface for Portability

GPU-accelerated compiler

AMD SMI

[DEPRECATED] Moved to ROCm/rocm-systems repo

C++ Insights - See your source code with the eyes of a compiler

Trio – a friendly Python library for async concurrency and I/O

A lightweight library for portable low-level GPU computation using WebGPU.

Kokkos C++ Performance Portability Programming Ecosystem: The Programming Model - Parallel Execution and Memory Abstraction

The Tensor Algebra Compiler (taco) computes sparse tensor expressions on CPUs and GPUs

[DEPRECATED] Moved to ROCm/rocm-libraries repo

[DEPRECATED] Moved to ROCm/rocm-systems repo