Stars
LeaderWorkerSet & DisaggregatedSet: Kubernetes APIs for Distributed and Disaggregated AI Serving
Pure C inference of Mistral Voxtral Realtime 4B speech to text model
Run pre-commit in subfolder. Allow to use monorepos.
The simplest but fast implementation of matrix multiplication in CUDA.
Tile primitives for speedy kernels
Sioyek is a PDF viewer with a focus on textbooks and research papers
Orillusion is a pure Web3D rendering engine which is fully developed based on the WebGPU standard.
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
Ongoing research training transformer models at scale
Minimalistic large language model 3D-parallelism training
Training MLP on MNIST in 1.5 seconds with pure CUDA
YourMumBot is a discord bot that makes your mum jokes based on content sent by users.
Convert Machine Learning Code Between Frameworks
PonderNET implementation to test on the MNIST dataset, using the degrees of rotation as a complexity measure.
Story-Based Retrieval with Contextual Embeddings. Largest freely available movie video dataset. [ACCV'20]
DisplayLink driver installer for Debian and Ubuntu based Linux distributions.
💻 A better and friendly vi(vim) mode plugin for ZSH.
Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers.
PAIR.withgoogle.com and friend's work on interpretability methods
Alphabetical list of free/public domain datasets with text data for use in Natural Language Processing (NLP)