Stars
Techniques and numbers for estimating system's performance from first-principles
Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).
Language Modeling with the H3 State Space Model
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".
Custom AI agent platform to speed up your work.
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
Cover Tree implementation in C++ for k-Nearest Neighbours and range search
C++ Implementations of sketch data structures with SIMD Parallelism, including Python bindings
Open-source vector similarity search for Postgres
Python library using the Futhark C backend via CFFI
Nearest Neighbor Search with Neighborhood Graph and Tree for High-dimensional Data
Vald. A Highly Scalable Distributed Vector Search Engine
A comprehensive library for machine learning and numerical computing. Apply Machine Learning with Rust leveraging first principles.
Transpile trained scikit-learn estimators to C, Java, JavaScript and others.
💥💻💥 A data-parallel functional programming language
A build tool/package manager for C, configured with Dhall
Modern webserver in Haskell: Graphql + Postgresql + Authentication + DB migration + Dotenv and more