AMD Ryzen™ AI Software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen™ AI powered PCs.

Generation of protein sequences and evolutionary alignments via discrete diffusion models

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Optimizing AlphaFold Training and Inference on GPU Clusters

OmegaFold Release Code

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

DFloat11: Lossless LLM Compression for Efficient GPU Inference

This is the top-level repository for the Accel-Sim framework.

Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.

Repository to host and maintain SCALE-Sim code

A fully open source biomolecular structure prediction model based on AlphaFold3

Code for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks".

[Patterns (Cell subsidiary journal)] The official code for "UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation".

🔥🔥🔥Official Codebase of "DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation"

A Lossless Compression Library for AI pipelines

여러 기능이 있는 위키 엔진 (Wiki engine with multiple functions)

PyTorch implementation of AlphaZero Chess from scratch

[NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.

Accelergy is an energy estimation infrastructure for accelerator energy estimations

[HPCA 2023] ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design

[ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs

Training small GPT-2 style models using Kolmogorov-Arnold networks.

Simulator for BitFusion

Attempt at reproduction of AlphaFold2

Implementation of the paper Fast Inference from Transformers via Speculative Decoding, Leviathan et al. 2023.

Code for paper "Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning"