tspeterkim

flash-attention-minimal

Flash Attention in ~100 lines of CUDA (forward pass only)

insta-chat

DIY Instagram Chat Automation with Google Sheets

mixed-precision-from-scratch

Mixed precision training from scratch with Tensors and CUDA

paged-attention-minimal

a minimal cache manager for PagedAttention, on top of llama3.

attentive-reader

TensorFlow-based implementation of Stanford's Attentive Reader for the CNN/DailyMail datatset

cuda-1brc

My CUDA solution to the 1BRC

lucene-wikipedia

Lucene-based Multi-sentence context retriever for open-domain QA setting

tweet-emoji-predictor

Tweet Emoji Predictor - SemEval 2018 Task 2

carla-driver

Autonomous Driving Agent for CARLA

dotfiles

all hail vim

gpt

Hemorrhage-Predictor-from-MRIs

Accurate Hemorrhage Predictor using MRIs

PDB-Evaluator

A Python-based inference system for Probabilistic Databases

positioning

RNN based prediction of wearer's position given sensor data from Android Wear

style-transferer

Lightweight style transferer built with SqueezeNet

CS145

CS145 Fall 2016 - Project 1A

funGPT

the non-lobotomized chatGPT

autograd

autograd engine with basic neural net apis

CS118-Lab2

CS143

cs143 fall 2016 w/ scott

cuda-matmult

diffusion

the new transformers for generative models?

dqn

playing around with dqn

incubator-eagle

Mirror of Apache Eagle (Incubating)

ml-algorithms

from the scratch

naivecoin

A tutorial for building a cryptocurrency

policy-gradient

vanilla policy gradient on pong and maybe more

pyminer

really simple bitcoin python miner

tspeterkim.github.io

thanks for the free compute, github

uvicorn-gunicorn-fastapi-docker

Docker image with Uvicorn managed by Gunicorn for high-performance FastAPI web applications in Python 3.6 and above with performance auto-tuning. Optionally with Alpine Linux.