Large Language Models are zero-shot text classifiers; Smart Expert System: Large Language Models as Text Classifiers

AICI: Prompts as (Wasm) Programs

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learna…

Inference Llama 2 in one file of pure Java

Tile primitives for speedy kernels

Tools for merging pretrained large language models.

High-performance In-browser LLM Inference Engine

An experimental UI for text-to-knowledge-graph generation

Mac app for Ollama

build-once run-anywhere c library

Performant, Concurrent, simplified Stream API leveraging Project Loom's virtual threads for efficient concurrent processing. Optimized for multithreaded environments

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

🗺 MapSCII is a Braille & ASCII world map renderer for your console - enter => telnet mapscii.me <= on Mac (brew install telnet) and Linux, connect with PuTTY on Windows

The production-scale datacenter profiler (C/C++, Go, Rust, Python, Java, NodeJS, .NET, PHP, Ruby, Perl, ...)

Distribute and run LLMs with a single file.

CLI tool to visualise CloudFormation/SAM/CDK stacks as visjs networks, draw.io or ascii-art diagrams.

Garnet is a remote cache-store from Microsoft Research that offers strong performance (throughput and latency), scalability, storage, recovery, cluster sharding, key migration, and replication feat…

LLRT (Low Latency Runtime) is an experimental, lightweight JavaScript runtime designed to address the growing demand for fast and efficient Serverless applications.

A repository showing various parts and variations of parser and tokenizer designs and implementations.

Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one

A technical explainer by @kognise of how your computer runs programs, from start to finish.

Minimalist ML framework for Rust

Tuweni is a set of libraries and other tools to aid development of blockchain and other decentralized software in Java and other JVM languages. It includes a low-level bytes library, serialization …

Inference Llama 2 in Scala with AVX2 kernels in C (A port of llama2.c from Andrej Karpathy)

Inference Llama 2 in one file of pure C

Code Repository for Liquid Time-Constant Networks (LTCs)

Spring boot library for continuous profiling with async-profiler