← all releases
Zlab Princeton·Jan 4, 2026·v1.0·open source

LLM-Pruning Collection

LLM-Pruning Collection is a JAX-based repository that consolidates major pruning algorithms for large language models into a single, reproducible framework. It aims to facilitate easy comparison of block-level, layer-level, and weight-level pruning methods under a consistent training and evaluation stack on both GPUs and TPUs.

MLInfrastructureLLMs
visit website
overview

LLM-Pruning Collection is a JAX-based repository that consolidates major pruning algorithms for large language models into a single, reproducible framework. It aims to facilitate easy comparison of block-level, layer-level, and weight-level pruning methods under a consistent training and evaluation stack on both GPUs and TPUs.

key features
  • 01Consolidates various pruning algorithms for large language models
  • 02Supports block-level, layer-level, and weight-level pruning methods
  • 03Compatible with both GPUs and TPUs for training and evaluation
related productsbrowse all →
SINQopen sourceSINQ (Sinkhorn-Normalized Quantization) is a novel, fast, and high-quality quantization method designed to make any Large Language Model (LLM) smaller while preserving accuracy. It offers a plug-and-play, model-agnostic technique that delivers state-of-the-art performance for LLMs without sacrificing accuracy.DetectFlowopen sourceDetectFlow is an open-source cybersecurity detection platform developed by SOC Prime. It leverages artificial intelligence to enhance the detection of cyber threats in real-time, enabling security operations teams to identify and respond to attacks more effectively.SkyRL txopen sourceSkyRL tx is an open-source library that implements a backend for the Tinker API, enabling users to set up their own Tinker-like services on personal hardware. It supports end-to-end reinforcement learning (RL) and offers significantly faster sampling. The library is designed to be modular, allowing easy prototyping of new training algorithms, environments, and execution plans without compromising usability or speed.