FemtoFlow
femtoflow is a Python package that enables pruning and quantization of TensorFlow models for optimized deployment to Femtosense's SPU (Sparse Processing Unit). The package provides a straightforward and flexible interface for reducing model size and complexity while maintaining high-performance inference on the SPU.
Features
- Pruning: Reduce model size by removing unimportant connections and neurons from your TensorFlow model.
- Quantization: Lower the precision of weights and activations to reduce memory requirements and computational costs while preserving model accuracy.
Getting Started
You can install femtoflow using pip:
pip install femtoflow
Documentation
Detailed documentation for femtoflow, including tutorials, API reference, and examples, can be found on the official website: https://femtoflow.femtosense.ai
2 maintainers
Metadata
2 maintainers
Release files for femtoflow 0.1.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| femtoflow-0.1.8-py3-none-any.whl | Python 3 | none | any | Details for femtoflow-0.1.8-py3-none-any.whl |
Release files / femtoflow-0.1.8-py3-none-any.whl
| Download URL | femtoflow-0.1.8-py3-none-any.whl |
|---|---|
| Size | 76.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4b095f8b463680429a40b66957647d47f6602e8806e470761e6100fb19684f49
|
|
BLAKE2b-256 checksum How to use checksums |
5d2fe9ee1b92464c835167e55124a0747596571b1bcde77aa88e8239b7b4b19a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.10.12
|
Security for femtoflow 0.1.8
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A 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.
