Stars
High-performance GPU kernels written in TIRx.
A high-throughput and memory-efficient inference and serving engine for LLMs
A minimal, complete, Pokémon battle simulation engine optimized for performance
Utilities intended for use with Llama models.
A self-organizing file system with llama 3
Distributed stress testing framework in Rust
Unified multidimensional array model that collects nonrectangular shapes, advanced indexing, views and sparsity into a single set of composable abstractions Resources
Fast Differentiable Tensor Library in JavaScript and TypeScript with Bun + Flashlight
Running large language models on a single GPU for throughput-oriented scenarios.
An interactive profiler for https://github.com/facebookresearch/shumai
Free group video call for the web. No signups. No downloads.
High performance Node.js image processing, the fastest module to resize JPEG, PNG, WebP, AVIF and TIFF images. Uses the libvips library.
A LinearOperator implementation to wrap the numerical nuts and bolts of GPyTorch
A flexible, high-performance 3D simulator for Embodied AI research.
A tiny JavaScript runtime for RP2040 (Raspberry Pi Pico)
Loop Nest - Linear algebra compiler and code generator.
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
nanobind: tiny and efficient C++/Python bindings
RLMeta is a light-weight flexible framework for Distributed Reinforcement Learning Research.
Repository for suggesting new lineages that should be added to the current scheme
🚀 A very efficient Texas Holdem GTO solver