Neural network processing library with GPU acceleration support
Project description
midi-neural-procesor
A GPU-accelerated neural network processing library with support for NVIDIA CUDA, AMD HIP, and Intel oneAPI.
midi-neural-procesor automatically detects and compiles GPU acceleration modules during installation for your platform.
Features
- ✅ GPU Acceleration - CUDA, HIP, oneAPI support
- ✅ Auto-Compilation - Native GPU modules compile during install
- ✅ Platform Detection - Automatic GPU compiler detection
- ✅ Fallback Mode - Graceful CPU fallback if GPU unavailable
- ✅ Neural Operations - Batch processing, tensor operations
Installation
pip install midi-neural-procesor
Compatible GPU compilers are automatically detected and appropriate modules are compiled during installation.
Quick Start
import neural_processor as np
proc = np.create_processor()
status = proc.get_status()
print(f"GPU module available: {status['gpu_module_available']}")
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
File details
Details for the file midi_neural_procesor-1.0.0.tar.gz.
File metadata
- Download URL: midi_neural_procesor-1.0.0.tar.gz
- Upload date:
- Size: 6.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8c203ab3d51d276d1e09467f9b05f5b945096793ed068eb19468f7e117d3a252
|
|
| MD5 |
a76c2cc24e7af4461f2a79c1de59dd07
|
|
| BLAKE2b-256 |
3eb29923de3093bf62bc453b42629392674572417b91a149d643f5ac0ece2465
|