This is the official PyTorch implementation of "Video-BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation."

Project homepage of Pyramid sparse attention

This is the official PyTorch implementation of "BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation."

A project implementing various agentic RL based on the Slime post-training framework

TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.

[CVPRW 2026 Oral] Less Detail, Better Answers: Degradation-Driven Prompting for VQA

A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-performance systems.

PTX ISA 9.1 documentation converted to searchable markdown. Includes Claude Code skill for CUDA development.

Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.

🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.

LM engine is a library for pretraining/finetuning LLMs

A Model Context Protocol (MCP) server for creating, reading, and manipulating Microsoft Word documents. This server enables AI assistants to work with Word documents through a standardized interfac…

Official repository of paper [FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic, NeurIPS 2025]

Artifact for PPoPP'26 "RoMeo: Mitigating Dual-dimensional Outliers with Rotated Mixed Precision Quantization"

flash attention tutorial written in python, triton, cuda, cutlass

DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference

A library of GPU kernels for sparse matrix operations.

SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs

Helpful kernel tutorials and examples for tile-based GPU programming

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

Accelerating MoE with IO and Tile-aware Optimizations

[ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter

The official repository for PTQTP implementation

Trainable fast and memory-efficient sparse attention

🚀🚀 Efficient implementations of Native Sparse Attention

PyTorch bindings for CUTLASS grouped GEMM.