language-model

KoboldCpp - Run GGUF AI models locally with a KoboldAI UI. One File. Zero Install.

Turbopilot is an open source large-language-model based code completion engine that runs locally on CPU

C++ Implementation of PyTorch Tutorials for Everyone

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

[support ollama/other model]【兼容ollama和其他模型】将任何具有OpenAI API调用方法的模型集成到PotPlayer中。它使你在观看视频时能够实时翻译字幕，从而打破语言障碍，提升你的观看体验。 This real-time subtitle translation plugin integrates OpenAI's ChatGPT API (or any model with the same API calling method) into PotPlayer. It enables you to translate subtitles on-the-fly while watching videos.

Connectionist Temporal Classification (CTC) decoder with dictionary and language model.

A lightweight vLLM-style inference engine in Rust

A C++ library providing fast language model queries in compressed space.

Tensorflow with KenLM integrated for beam search scoring

A GPU language model, based on btree backed tries.

24-hour Automatic Speech Recognition

ANYKS Spell-Checker

Evaluation of Large Language Models on Code Obfuscation

Welcome to KLLM, an advanced project focused on core kernel AI development, integrating on-device language models (LMs) for efficient and powerful AI capabilities.

The Universal LLM Gateway - Integrate ANY AI Model with One Consistent API

Este projeto é um novo compilador que está sendo desenvolvido, A Linguagem Plax. O Plax (Predefined Language of Automated eXecution) é uma linguagem compilada e multi-paradigma no intuito de ser dinâmica e rápida, a linguagem contém junções de paradigmas e diferentes sintaxes.

a low-latency and high-performance inference engine for large models on low-memory GPU platform.

Transformer (GPT) implemented from scratch in C++. Runs on modest hardware with complete mathematical derivations and optimized tensor operations.

CPPCorrector 中文文本纠错工具， Text Error Correction Tool，Spelling Check

A small, fast, statically typed programming language with clean syntax, a built-in Windows-ready toolchain, and an optional C++ backend.