QAT pipeline

QAT is the second paradigm in the R3AL.AI SDK. Where PTQ needs no training, QAT fine-tunes your model with quantization simulated in the loop, then quantizes it. The training runs on R3AL GPU infrastructure; the SDK uploads your model and images, streams progress, and downloads the result. A QAT job consumes one plan run.

When to use it

PTQ accuracy acceptable?         → use PTQ (ptq_dynamic / ptq_static)
Low bit-width (3-4 bit) needed?  → QAT recovers accuracy PTQ can't
Have representative images?      → QAT

Run it

import r3alai.platform as platform
from r3alai.quant import QuantConfig, Quantizer

platform.login("r3l_live_...")   # or set R3AL_API_KEY

config = QuantConfig(mode="qat", qat_wbit=8, qat_abit=8)
result = Quantizer(config).train_qat(
    "model.onnx",
    calibration_data=["/data/img1.jpg", "/data/img2.jpg"],
    output_dir="./qat_out",
    epochs=3,
)
print(result.path)

What happens on the platform

Upload

The SDK uploads your model (exporting to ONNX locally first if you passed a checkpoint) and your calibration images.

Fine-tune with quantization in the loop

R3AL’s engine trains on GPU with lower precision simulated during the forward pass, and automatically protects accuracy-sensitive layers.

Download the bundle

The engine exports a standard quantized ONNX model plus r3alai_manifest.json, downloaded into your output_dir.

Key options

Field	Default	Description
`model`	required	Path to `.onnx` (or a checkpoint for local export)
`calibration_data`	required	Training / calibration images
`epochs`	`1`	Training epochs (`1` = smoke test)
`qat_wbit` / `qat_abit`	`8` / `8`	Weight / activation bit widths (3-8), set on `QuantConfig`
`qat_calib_batches`	`16`	Batches for activation calibration, set on `QuantConfig`
`learning_rate`	`1e-4`	Optimizer learning rate, passed to `train_qat()`

See QAT explained for a detailed breakdown of qat_wbit and qat_abit.

Monitoring and results

train_qat() blocks and prints live progress; you can also follow the job on the platform’s Jobs page. When it finishes, the deliverable is downloaded and result.path points at the bundle:

qat_out/
├── model_qat.quantized.onnx
└── r3alai_manifest.json

epochs=1 is a smoke test, not a converged model. Use representative images from your deployment domain and more epochs for production runs.

Get Started

Core Concepts

Guides

When to use it

Run it

What happens on the platform

Key options

Monitoring and results

Next steps

QAT explained

Calibration

​When to use it

​Run it

​What happens on the platform

​Key options

​Monitoring and results

​Next steps

QAT explained

Calibration

When to use it

Run it

What happens on the platform

Key options

Monitoring and results

Next steps