Distillation Python Packages

vsa

A unified inference and post-training framework for accelerated video generation.

st-attn

A unified inference and post-training framework for accelerated video generation.

biosteam

The Biorefinery Simulation and Techno-Economic Analysis Modules

shad0wllm

System 0 for your LLM: learns the fixed-choice answers your LLM gives (intents, routing, moderation) and serves the repeats in microseconds from a small CPU table, at most 5% disagreement, certified. Zero-code proxy for the OpenAI Decisions API, System One and chat models.

fastvideo-kernel

A unified inference and post-training framework for accelerated video generation.

jevstiller

Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.

hensmith

Heat Exchanger Network Synthesis, Modeling, Integration, Thermodynamics, and Heuristics

stuntd

Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

oev

An 184M-parameter decision engine delivering calibrated distributions from one 22ms forward pass while matching models 2.3x its size.

fasterai

FasterAI: Prune and Distill your models with FastAI and PyTorch

wev-ai

OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisions and browser-agent steps.

fastvideo

A unified inference and post-training framework for accelerated video generation.

shrinkai

[CONTRIBUTORS WELCOME] Neural Network distillation and compression in Python

decisionsmith

Use and fine-tune System One models (Jev, Laya) on your data, with an LLM as the teacher.

openjev-ai

OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisions and browser-agent steps.

nskinetics

NSKinetics: Simulation of Non-Steady state enzyme kinetics including multiple inhibitory phenomena.

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.

monkey-patch-py

Prompt engineering for developers

turbodiffusion

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

tanuki-py

Prompt engineering for developers

bertdistiller

Faster, smaller BERT models in just a few lines of code.

agent2model

Compile a stable LangGraph/YAML agent into a small model that self-orchestrates with no runtime orchestrator — private + offline, ~100× cheaper inference (per the paper; reproduction in progress).

signalforgeai

Opinionated platform for agentic workflows, orchestration, evaluation, and learning

awave

Adaptive, interpretable wavelets across domains (NeurIPS 2021)