lsy105

LLM101n

LLM101n: Let's build a Storyteller

cuda-repo

From zero to hero CUDA for accelerating maths and machine learning on GPU.

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

InferLLM

a lightweight LLM model inference framework

gpusimilarity

A Cuda/Thrust implementation of fingerprint similarity searching

IPSC

Introduction to parallel scientific computing

minit

ORDerly

Chemical reaction data & benchmarks. Extraction and cleaning of data from Open Reaction Database (ORD)

crem

CReM: chemically reasonable mutations framework

llm.c

LLM training in simple, raw C/CUDA

MoleculeSTM

Multi-modal Molecule Structure-text Model for Text-based Editing and Retrieval, Nat Mach Intell 2023 (https://www.nature.com/articles/s42256-023-00759-6)

tiny-training

On-Device Training Under 256KB Memory [NeurIPS'22]

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

TinyChatEngine

TinyChatEngine: On-Device LLM Inference Library

llama_cu_awq

llama INT4 cuda inference with AWQ

llamol

Offical repository for the paper "Llamol: a dynamic multi-conditional generative transformer for de novo molecular design" (https://doi.org/10.1186/s13321-024-00863-8)

CS149-parallel-computing

Learning materials for Stanford CS149 : Parallel Computing

CS149-asst2

Parallel Computing asst 2: Scheduling Task Graphs on a Multi-Core CPU

AI-System

System for AI Education Resource.

CMU10-714

Learning material for CMU10-714: Deep Learning System

Parametric-Leaky-Integrate-and-Fire-Spiking-Neuron

Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks

SNN_Calibration

Pytorch Implementation of Spiking Neural Networks Calibration, ICML 2021

snn_optimal_conversion_pipeline

Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks

hybrid-snn-conversion

Training spiking networks with hybrid ann-snn conversion and spike-based backpropagation

moses

Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models

ng-video-lecture

e3_diffusion_for_molecules

DIG

A library for graph deep learning research

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.