Search Packages

auto-round

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

auto-round-nightly

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

auto-round-lib

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

sigmaflow

SigmaFlow is a Python package designed to optimize the performance of task-flow related to LLMs/MLLMs or Multi-agent.

oumi

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

auto-round-hpu

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

auto-round-kernel

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

visionzip

Official repository for VisionZip (CVPR 2025)

docvision

Production-ready document parsing with Vision Language Models

docext

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

llm-markdownify

Convert PDFs, images to high-quality Markdown using Vision LLMs.

swiftannotate

Auto labelling tool for Text, Image, Video

doc-vision-parser

Python library for intelligent document parsing using Vision Language Models. Extract structured text and markdown from PDFs and images with self-correcting AI workflows. Supports OpenAI-compatible APIs.