TorchProfile
TorchProfile counts the number of MACs (multiply-accumulate operations) in a PyTorch model. It works by tracing the computation graph with torch.jit.trace, making it more accurate than hook-based profilers and more general than ONNX-based ones.
Installation
pip install torchprofile
Quick Start
import torch
from transformers import AutoModel
from torchprofile import profile_macs
model = AutoModel.from_pretrained("meta-llama/Llama-3.2-1B").eval()
inputs = torch.randint(0, model.config.vocab_size, (1, 128))
macs = profile_macs(model, inputs)
print(f"{macs / 1e9:.2f} GMACs")
To get a per-operator breakdown, pass reduction=None:
results = profile_macs(model, inputs, reduction=None)
for node, macs in results.items():
if macs > 0:
print(f"{node.scope:40s} {node.operator:30s} {macs / 1e6:>8.2f} MMACs")
License
This repository is released under the MIT license. See LICENSE for additional details.
1 maintainer
Metadata
1 maintainer
Release files for torchprofile 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| torchprofile-0.1.0.tar.gz | 10.6 kB | With provenance | Details for torchprofile-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| torchprofile-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for torchprofile-0.1.0-py3-none-any.whl |
Total release size: 19.9 kB
Release files / torchprofile-0.1.0.tar.gz
| Download URL | torchprofile-0.1.0.tar.gz |
|---|---|
| Size | 10.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
aeb725e9446b3a6d8f82d0f0cf944a6ffb9cced4e5db1354ad3b9692ce820dac
|
|
BLAKE2b-256 checksum How to use checksums |
0339564175b0147da5f712702209de3904cf97de492a115943c75af1b1b56d82
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 10, 2026.
Transparency logRelease files / torchprofile-0.1.0-py3-none-any.whl
| Download URL | torchprofile-0.1.0-py3-none-any.whl |
|---|---|
| Size | 9.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
39aefcd194927befb0cfe7ed886be565dee384e3889d0b6890bace5ae1614578
|
|
BLAKE2b-256 checksum How to use checksums |
137682c336b80fcd19ad9eedd7c17e459d69a0024aed7229dbcf663c975c5ded
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 10, 2026.
Transparency logSecurity for torchprofile 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for torchprofile-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 10, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
