Tile primitives for speedy kernels

[ICLR 2025] Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.

A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, llava-onevision, llama-3.2-vision, qwen-vl, qwen2-vl, phi3-v etc.

Code for paper "Vocabulary Learning via Optimal Transport for Neural Machine Translation"

Fast web applications through dynamic, partially-stateful dataflow

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activelo…

Drogon: A C++14/17/20 based HTTP web application framework running on Linux/macOS/Unix/Windows

KenLM: Faster and Smaller Language Model Queries

Python wrapper for RE2

Efficient Markov Chain word alignment

Mac-style shortcut keys for Linux & Windows.

Static memory-efficient Trie-like structures for Python based on marisa-trie C++ library.

A Pytorch Implementation of ClariNet

python cffi bindings for the oniguruma regex engine

CMake wrapper for ICU supporting cross-compilation

Dynamic Batching for Deep Learning Serving

Serving the deep learning models easily.

Conversion between Traditional and Simplified Chinese

Unsupervised text tokenizer focused on computational efficiency

Language-Agnostic SEntence Representations

🆕 A machine learning plugin which supports an approximate k-NN search algorithm for Open Distro.

API spec validator and OpenAPI document generator for Python web frameworks.

C# class library to implement a request-batcher

Plugin to integrate approximate nearest neighbor(ANN) search with Elasticsearch

Repo for counting stars and contributing. Press F to pay respect to glorious developers.

A collection of commonly used torch models

An Open-Source Bootstrap 3 Jekyll Theme by Scotch