Stars
Automatic differentiation for Triton Kernels
PyTorch code for FLD (Feature Likelihood Divergence), FID, KID, Precision, Recall, etc. using DINOv2, InceptionV3, CLIP, etc.
We integrate discrete diffusion models with neurosymbolic predictors for scalable and calibrated learning and reasoning
A library for efficient similarity search and clustering of dense vectors.
Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.
Python package for graph statistics
A toolkit for enforcing logical specifications on neural networks
GitPython is a python library used to interact with Git repositories.
Collection of library stubs for Python, with static types
[NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)
This repository holds the code for the NeurIPS 2022 paper, Semantic Probabilistic Layers
A python library for creating Kronecker Product operators with efficient lazy computation
An extremely fast Python linter and code formatter, written in Rust.
Hyper optimized contraction trees for large tensor networks and einsums
CUDA kernels for generalized matrix-multiplication in PyTorch
Differentiable signal processing on the sphere for PyTorch
We integrate discrete diffusion models with neurosymbolic predictors for scalable and calibrated learning and reasoning
Production-grade client-side tracing, profiling, and analysis for complex software systems.
An extremely fast Python type checker and language server, written in Rust.
mlpack: a fast, header-only C++ machine learning library