cfoster0

supervision

We write your reusable computer vision tools. 💜

dspy

DSPy: The framework for programming—not prompting—foundation models

instructor

structured outputs for llms

marvin

✨ Build AI interfaces that spark joy

moondream

tiny vision language model

Vim

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

penzai

A JAX research toolkit for building, editing, and visualizing neural networks.

schedule_free

Schedule-Free Optimization in PyTorch

gsplat

CUDA accelerated rasterization of gaussian splatting

punica

Serving multiple LoRA finetuned LLM as one

flashinfer

FlashInfer: Kernel Library for LLM Serving

DataDreamer

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

modal-examples

Examples of programs built using Modal

attorch

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

crepes

Conformal classifiers, regressors and predictive systems

fltr

Like grep but for natural language questions. Based on Mistral 7B or Mixtral 8x7B.

rax

Rax is a Learning-to-Rank library written in JAX.

einx

Tensor Operations in Einstein-Inspired Notation for Python.

lightplane

Lightplane implements a highly memory-efficient differentiable radiance field renderer, and a module for unprojecting features from images to 3D grids.

Score-Entropy-Discrete-Diffusion

Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

haystackdb

rebased

Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"

mamba.rs

hippogriff

Griffin MQA + Hawk Linear RNN Hybrid

amago

a simple and scalable agent for training adaptive policies with sequence-based RL

Inflection-Benchmarks

Public Inflection Benchmarks

stk

LASP

Linear Attention Sequence Parallelism (LASP)

flashT5

A fast implementation of T5/UL2 in PyTorch using Flash Attention

ffvec