Integer-only FlashAttention kernel in Triton.

PyTorchSim is a Comprehensive, Fast, and Accurate NPU Simulation Framework

mcp for handling hwp

PyTorch CoreSIG

Generate a comprehensive review from an arXiv paper, then turn it into a blog post. This project powers the website below for the HuggingFace's Daily Papers (https://huggingface.co/papers).

[ECCV 2024] CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs

Efficient GPU kernels for mixed-precision Vision Transformers in Triton

List of papers related to Vision Transformers quantization and hardware acceleration in recent AI conferences and journals.

Code Repository of Evaluating Quantized Large Language Models

Hiera: A fast, powerful, and simple hierarchical vision transformer.

Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.

GPU programming related news and material links

Shared Middle-Layer for Triton Compilation

A beautiful, simple, clean, and responsive Jekyll theme for academics

Command-line program to download videos from YouTube.com and other video sites

Extract your SlidesLive presentation.

A tool to modify ONNX models in a visualization fashion, based on Netron and Flask.

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

[CVPR 2023] PD-Quant: Post-Training Quantization Based on Prediction Difference Metric

LLM inference in C/C++

This project aims to split onnx by reading yaml config.

Template repository to build PyTorch projects from source on any version of PyTorch/CUDA/cuDNN.

Code and models for mobile-former