This repository contains companion software for the Colfax Research paper "Categorical Foundations for CuTe Layouts".

A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.

Meta project around MLIR

Kimi K2 is the large language model series developed by Moonshot AI team

Templight is a Clang-based tool to profile the time and memory consumption of template instantiations and to perform interactive debugging sessions to gain introspection into the template instantia…

🇪🇺 💶 Generate e-invoices (E-Rechnung in German) conforming to EN16931 (Factur-X/ZUGFeRD, UBL, CII, XRechnung aka X-Rechnung) from LibreOffice Calc/Excel data or JSON.

Next-generation JavaScript analysis tooling

Distributed Compiler based on Triton for Parallel Systems

Custom Bindings for Enzyme Automatic Differentiation Tool and Interfacing with JAX.

A Datacenter Scale Distributed Inference Serving Framework

Intel® Tensor Processing Primitives extension for Pytorch*

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

This is a repository listing companies which offer full-time remote jobs with Spanish contracts

A feature-rich command-line audio/video downloader

KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems

Efficient Triton Kernels for LLM Training

A modern model graph visualizer and debugger

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

MLIR-based partitioning system

Type in Morse code by repeatedly slamming your laptop shut

A set of short tests designated to check Intel GPU SW environment and ability to execute user-generated code.

The Linux Kernel Module Programming Guide (updated for 5.0+ kernels)

Best practice for training LLaMA models in Megatron-LM

Ongoing research training transformer models at scale

The simplest, fastest repository for training/finetuning medium-sized GPTs.

[ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling

An experimental CPU backend for Triton

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

PArallelLOOPgEneratoR: Threaded Loops Code Generation Infrastructure targeting Tensor Contraction Applications such as GEMMs, Convolutions and Fused Deep Learning Primitives