Download
TurboTransformers is a high-performance inference framework optimized for running Transformer models efficiently on CPUs and GPUs. It improves latency and throughput for NLP applications.
Features
- Optimized for low-latency Transformer model inference
- Supports both CPU and GPU acceleration
- Works with popular Transformer models like BERT and GPT
- Implements kernel fusion for performance optimization
- Compatible with PyTorch and TensorFlow
- Provides quantization support for lower memory usage
Project Samples
License
BSD LicenseFollow TurboTransformers
Other Useful Business Software
Our Free Plans just got better! | Auth0
You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of TurboTransformers!