Efficiency

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

Official Implementation for the ACL 2026 paper "SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression"

A high-performance image processing library designed to optimize and extend the Albumentations library with specialized functions for advanced image transformat…

Token Cost Parity: Multilingual LLM Efficiency Analysis 2026

A tiny safety classifier for fast content filtering.

Accelerating generation by drafting tokens with a small model.

Post-training quantization tools for transformers.

Shrinking a model by storing its weights at lower precision.

Ternary-weight models that retain most of full-precision quality.

A compact speech-to-text model for on-device use.

A one-click quantization and benchmarking tool.