A high-throughput and memory-efficient inference and serving engine for LLMs

MC-Sparse: Deconstructing and Closing the Dense–Sparse Attention Gap in Diffusion Transformers.

An end-to-end agent project for GPU kernel implementation, analysis, profiling, and iterative optimization. It helps an agent turn PyTorch logic or an existing kernel into a high-performance GPU ke…

A unified inference and post-training framework for accelerated video generation.

SOTA Weight-only Quantization Algorithm for LLMs

Lightweight Image Video Action Generation Inference Framework

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.

A framework for efficient model inference with omni-modality models

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Profiling Tools Interfaces for GPU (PTI for GPU) is a set of Getting Started Documentation and Tools Library to start performance analysis on Intel(R) Processor Graphics easily

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

Development repository for the Triton language and compiler

Intel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, spar…

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A safetensors extension to efficiently store sparse quantized tensors on disk

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention

rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

DeepGEMM: clean and efficient BLAS kernel library on GPU

A unified, torch-native training framework for MTP and block-parallel speculative decoding.