Yang Song

Professor at Caltech; Research Scientist at OpenAI

Starred Projects (36)

tilelang by tile-ai

DSL for high-performance GPU/CPU kernel development (GEMM, attention, etc.)

luiscape:

zhuohan123:

zhyncs:

Created 11 months ago

Updated 15 hours ago

cocoindex by cocoindex-io

Real-time data transformation framework for AI indexing

generall:

Created 6 months ago

Updated 17 hours ago

flash-linear-attention by fla-org

Efficient Torch/Triton implementations for linear attention models

hiyouga:

xiezhq-hermann:

zhyncs:

winglian:

Created 1 year ago

Updated 2 days ago

simple-evals by openai

Lightweight library for evaluating language models

patrickvonplaten:

simonw:

zhyncs:

philschmid:

Created 1 year ago

Updated 1 month ago

PiPPy by pytorch

PyTorch tool for pipeline parallelism

jph00:

JohannesHa:

stas00:

Edward-Sun:

Created 3 years ago

Updated 1 year ago

consistencydecoder by openai

Improved decoding for stable diffusion VAEs

shyamal-anadkat:

gakonst:

simonw:

vincentweisser:

Created 1 year ago

Updated 1 year ago

vector-quantize-pytorch by lucidrains

PyTorch library for vector quantization techniques

Jiayi-Pan:

codekansas:

Created 5 years ago

Updated 2 weeks ago

aim by aimhubio

Experiment tracker for AI model training runs

amin3141:

patrick-kidger:

transitive-bullshit:

stas00:

Created 6 years ago

Updated 1 day ago

LLM-Training-Puzzles by srush

Hands-on puzzles for large language model training

Jiayi-Pan:

albertfgu:

willccbb:

hiyouga:

Created 2 years ago

Updated 1 year ago

guidance by guidance-ai

Guidance is a programming paradigm for steering LLMs

tobi:

ekzhu:

stas00:

Ying1123:

Created 2 years ago

Updated 1 day ago

consistency_models by openai

PyTorch code for consistency models research paper

codekansas:

patrickvonplaten:

JustinLin610:

ablattmann:

Created 2 years ago

Updated 1 year ago

equinox by patrick-kidger

JAX library for neural networks and scientific computing

mattjj:

hammer:

jrk:

hanlint:

Created 4 years ago

Updated 3 weeks ago

glide-text2im by openai

Text-conditional image synthesis model from research paper

ShengjiaZhao:

Edward-Sun:

patrickvonplaten:

Jiayi-Pan:

Created 3 years ago

Updated 1 year ago

numpyro by pyro-ppl

Probabilistic programming library using JAX for GPU/TPU/CPU

omarsar:

froystig:

hammer:

ibab:

Created 6 years ago

Updated 1 week ago

guided-diffusion by openai

Image synthesis codebase for diffusion models

aravindsrinivas:

JustinLin610:

rromb:

patrickvonplaten:

Created 4 years ago

Updated 1 year ago

gpt-neo by EleutherAI

GPT-2/3-style model implementation using mesh-tensorflow

ebursztein:

okhat:

stellaathena:

JohannesHa:

Created 5 years ago

Updated 3 years ago

minGPT by karpathy

Minimal PyTorch re-implementation for GPT training and inference

aravindsrinivas:

nat:

geohot:

lilianweng:

Created 5 years ago

Updated 1 year ago

taming-transformers by CompVis

Image synthesis research paper using transformers

karpathy:

Jiayi-Pan:

codekansas:

stellaathena:

Created 4 years ago

Updated 1 year ago

DeepSpeed by deepspeedai

Deep learning optimization library for distributed training and inference

aravindsrinivas:

ValentaTomas:

winglian:

stas00:

Created 5 years ago

Updated 1 day ago

CLIP by openai

Image-text matching model for zero-shot prediction

aravindsrinivas:

transitive-bullshit:

Edward-Sun:

mholt:

Created 4 years ago

Updated 1 year ago

ml-visuals by dair-ai

ML visuals for science communication

rstojnic:

omarsar:

Created 5 years ago

Updated 2 years ago

streamlit by streamlit

SDK for rapidly building interactive data apps

kellyamanda:

treuille:

hsbt:

samuelcolvin:

Created 6 years ago

Updated 14 hours ago

pytorch-lightning by Lightning-AI

Deep learning framework for pretraining, finetuning, and deploying AI models

albertfgu:

soldni:

omarsar:

zhangce:

Created 6 years ago

Updated 1 day ago

ncsn by ermongroup

Research paper implementation for generative modeling via score estimation

chenlin9:

jiamings:

Created 6 years ago

Updated 1 year ago

flax by google

NN library for JAX, designed for flexibility in neural network research

charliermarsh:

codekansas:

Jiayi-Pan:

jaredpalmer:

Created 5 years ago

Updated 19 hours ago

tianshou by thu-ml

PyTorch RL library for algorithm development and application

chiphuyen:

pgarbacki:

shizhediao:

youkaichao:

Created 7 years ago

Updated 1 week ago

pixel-cnn-pp by pclucas14

Pytorch implementation of PixelCNN++ for generative image modeling

chenlin9:

jiamings:

Created 7 years ago

Updated 4 years ago

DALI by NVIDIA

GPU-accelerated library for data pre-processing in deep learning

hammer:

agermanidis:

apsdehal:

cvalenzuela:

Created 7 years ago

Updated 16 hours ago

tqdm by tqdm

Progress bar for Python and CLI tools

bcherny:

geohot:

hugs:

parano:

Created 10 years ago

Updated 3 months ago

horovod by horovod

Distributed training framework for TF, Keras, PyTorch, and MXNet

aravindsrinivas:

fchollet:

winglian:

transitive-bullshit:

Created 8 years ago

Updated 2 days ago

rlkit by rail-berkeley

RL algorithm collection implemented in PyTorch

aravindsrinivas:

MishaLaskin:

natolambert:

millionintegrals:

Created 7 years ago

Updated 1 year ago

tensor2tensor by tensorflow

Deprecated library for deep learning models/datasets, successor to Trax

lilianweng:

aravindsrinivas:

eiso:

JohannesHa:

Created 8 years ago

Updated 2 years ago

Arcade-Learning-Environment by Farama-Foundation

AI research platform for Atari 2600 game environments

fchollet:

glample:

bshlgrs:

pathak22:

Created 13 years ago

Updated 1 week ago

examples by pytorch

PyTorch examples for diverse AI tasks

lilianweng:

hammer:

tjbck:

ari-holtzman:

Created 9 years ago

Updated 2 weeks ago

awesome-deep-learning-papers by terryum

Curated list of seminal deep learning papers (2012-2016)

lilianweng:

ShengjiaZhao:

bcherny:

chenlin9:

Created 9 years ago

Updated 1 year ago

neon by NervanaSystems

Deep learning framework (discontinued)

fchollet:

parano:

trishume:

hanlint:

Created 11 years ago

Updated 4 years ago

Feedback? Help us improve.