Knowledge Distillation Python Packages

neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

suod

(MLSys' 21) An Acceleration System for Large-scare Unsupervised Heterogeneous Outlier Detection (Anomaly Detection)

paddleclas

A treasure chest for visual classification and recognition powered by PaddlePaddle

torchdistill

A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆26 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

easy-zh-bert

easy-bert是一个中文NLP工具，提供诸多bert变体调用和调参方法，极速上手；清晰的设计和代码注释，也很适合学习

resonance-layer

Emotional intelligence layer for AI - detects emotion, tracks wellbeing, and gives any LLM the context to respond to how people actually feel.

neural-compressor-pt

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

optipfair

Structured pruning, knowledge distillation, and fairness analysis for Large Language Models.

mmrazor

OpenMMLab Model Compression Toolbox and Benchmark.

tokenknows-mcp

Distill AI coding sessions (Claude Code / Codex / Cursor) into weekly reports, ADRs, incident reviews and a knowledge graph — local-first, evidence-linked.

thekaveh-nnx

Lightweight PyTorch toolkit for training, fine-tuning, and exporting modern neural nets. FFN + GNN + decoder-only LM + diffusion + JEPA + MoE; PEFT (LoRA/DoRA/IA3/Prefix/Prompt), PTQ/QAT, pruning, surgery; ONNX/GGUF/Ollama/HuggingFace Hub interop. Dataclass-configured runs with fluent builders, automatic checkpointing, and Plotly viz.

neural-compressor-tf

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

aquvitae

Knowledge Distillation Toolkit

distill-anything

Distill any AI model into one you own — a teacher (Claude/GPT/HF/Ollama) generates your dataset, a student trains on its logits or its words, a judge scores it blind, a benchmark prices it. Runs on a MacBook.

insurance-distill

Distil GBM models into multiplicative GLM factor tables for insurance rating engines.

ollama-rag

A programming framework for knowledge management

uni-layer

A Universal Framework for Layer Contribution Analysis

neural-compressor-full

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

kd-lib

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.

langformers

🚀 Unified NLP Pipelines for Language Models

sc2bench

SC2 Benchmark: Supervised Compression for Split Computing.

neural-solution

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

neural-insights

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

easytransfer

PAI EasyTransfer Toolkit