Libraries

Open-source tools for efficient AI.

Two libraries, Apache 2.0 licensed. Drop them into any PyTorch project to compress and benchmark your models in a few lines of code.

01
FasterAI

Compress any PyTorch model.

A toolkit for shrinking and accelerating neural networks with research-backed techniques. Drop into existing training pipelines in a few lines of code.

Structured and unstructured pruning
Post-training and quantization-aware training
Knowledge distillation utilities
Plug directly into PyTorch workflows
$pip install fasterai
02
FasterBench

Benchmark what matters.

Measure speed, size, memory, compute, and energy in a single function call. The complete picture of your model's efficiency, with no extra wiring.

Latency and throughput
Memory footprint and model size
FLOPs and compute cost
Energy use and carbon emissions
$pip install fasterbench
03
Quickstart

From pretrained to production.

Load a pretrained model, compress it, benchmark it. Four steps to a smaller, faster model.

quickstart.py
from fasterai.prune.all import *
from fasterbench.benchmark import *
from torchvision.models import resnet18

# 1) Load a baseline model
model = resnet18()

# 2) Compress in seconds
pruner = Pruner(model, 50, 'global', large_final)
pruner.prune_model()

# 3) Benchmark compressed model
bench = benchmark(model, dummy)

# 4) Save compressed model
torch.save(model.state_dict(), "compressed-model.pth")

smaller. faster. open.


© 2026 smaller. faster. open. All rights reserved.