diffq-fixed

library0.2.4pypypi✓ verified 85d ago

A differentiable quantization framework for PyTorch, fixed for compatibility with Python 3.11 and newer. This library provides differentiable quantization-aware training with custom quantizers and gradient approximations. Version 0.2.4 is current; no regular release cadence.

ai-ml

pip install diffq-fixed

github ↗package ↗

INSTALL

IMPORT

SIG · DIFFQ-FIXED

diffq-fixed

ai-mlpythonv0.2.4

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

DiffQuantizer

✓ from diffq import DiffQuantizer

✗ from diffq_fixed import DiffQuantizer

The package name is 'diffq-fixed' but import uses 'diffq'.

Initialize a DiffQuantizer wrapping a model, run a training step.

import torch from diffq import DiffQuantizer model = torch.nn.Linear(10, 5) quantizer = DiffQuantizer(model, n_bits=8) optimizer = torch.optim.SGD(model.parameters(), lr=0.01) x = torch.randn(4, 10) y = model(x) loss = y.sum() loss.backward() optimizer.step() print("Training step completed")

Debug

Known issues

gotchaImport path uses 'diffq' not 'diffq_fixed' even though the package is installed as 'diffq-fixed'.

fix

Use 'from diffq import DiffQuantizer' instead of 'from diffq_fixed import ...'

affects: all

breakingThis fork may not be compatible with the original diffq's serialization format (model checkpoints). Loading checkpoints saved with original diffq could fail.

fix

Re-train or re-quantize models using diffq-fixed from scratch, or check the release notes for any conversion tools.

affects: 0.2.4

Errors

Common errors & fixes

ModuleNotFoundError: No module named 'diffq'

Installed the pip package 'diffq-fixed' but trying to import 'diffq_fixed' instead of 'diffq'.

fix

Change import to: from diffq import DiffQuantizer

RuntimeError: Quantizer not initialized

Calling forward on DiffQuantizer before initializing with the model (or calling .to_device()?).

fix

Ensure you pass the model to DiffQuantizer constructor: quantizer = DiffQuantizer(model, ...)

Upgrade

Version history

0.2.4latest on PyPI · released Nov 12, 2024

Audit

Dependencies

torchrequiredCore dependency; diffq builds on PyTorch tensors and autograd

Agent activity

19 hits · last 30 days

node

Amazon

OpenAI (training)

Resources

githubhttps://github.com/JackismyShephard/diffq ↗

packagehttps://pypi.org/project/diffq-fixed/ ↗