teelinsan/parallel-decoding
Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"
This project offers methods to make existing machine translation systems faster without changing the underlying model or retraining it. You input a pre-trained machine translation model and source text, and it outputs the translated text much quicker. Researchers working on improving the efficiency of machine translation or natural language processing models would use this.
124 stars. No commits in the last 6 months.
Use this if you are a researcher focused on accelerating transformer-based machine translation inference for research purposes.
Not ideal if you need a production-ready solution for live translation services or if you are not comfortable with command-line operations and research-focused code.
Stars
124
Forks
7
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/teelinsan/parallel-decoding"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
openvinotoolkit/nncf
Neural Network Compression Framework for enhanced OpenVINO™ inference
huggingface/optimum
🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers...
NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
huggingface/optimum-intel
🤗 Optimum Intel: Accelerate inference with Intel optimization tools
eole-nlp/eole
Open language modeling toolkit based on PyTorch