Vlm Python Packages

transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

tokenspeed-mla

TokenSpeed is a speed-of-light LLM inference engine.

sglang-kernel

SGLang is a high-performance serving framework for large language models and multimodal models.

aerosandbox

Aircraft design optimization made fast through computational graph transformations (e.g., automatic differentiation). Composable analysis tools for aerodynamics, propulsion, structures, trajectory design, and much more.

mineru-vl-utils

A Python package for interacting with the MinerU Vision-Language Model.

sgl-kernel

SGLang is a high-performance serving framework for large language models and multimodal models.

infinity-parser2

INF Tech's open-source MLLMs for SOTA visual-language understanding and advanced document intelligence.

evalscope

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

pytorch-pretrained-bert

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

vlmrun-hub

A hub for various industry-specific schemas to be used with VLMs.

pytorch-transformers-pvt-nightly

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

trainlens

TrainLens turns training runs into evidence: what changed, what went wrong, and what experiment to run next.

pytorch-transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

nemo-automodel

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

lmms-eval

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

paperbanana

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

oumi

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

optvl

AVL + python + optimization = OptVL

telekinesis-ai

Telekinesis Agentic Skill Library: build AI-powered Computer Vision, Robotics and Physical AI applications.

termux-vision

🚀 The Sovereign On-Device Computer Vision & Multimodal VLM Inference Engine for Android Termux & ARM64 (Dual-Engine Python & Node.js/TypeScript)

telekinesis-datatypes

Telekinesis Agentic Skill Library: build AI-powered Computer Vision, Robotics and Physical AI applications.

mantis-vl

Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024 Best Paper]

scaledp

ScaleDP is an Open-Source extension of Apache Spark for Document Processing