English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The latest industrial inference engines, such as FasterTransformer andTurboTransformers, have verified that half-precision floating point (FP16) and8-bit integer (INT8) quantization can greatly improve model inference speed.However, the existing INT8 quantization methods are too complicated, andimproper usage will lead to model performance damage greatly. In this paper, wedevelop a toolkit for users to easily quantize their models for inference, inwhich Self-Adaptive Mixed-Precision (SAMP) is proposed to automatically controlquantization rate by a mixed-precision architecture to balance model accuracyand efficiency. Experimental results show that our SAMP toolkit has a higherspeedup than PyTorch and FasterTransformer while ensuring the requiredaccuracy. In addition, SAMP is based on a modular design, decoupling thetokenizer, embedding, encoder and target layers, which allows users to handlevarious downstream tasks and can be seamlessly integrated into PyTorch.

SAMP: A Model Inference Toolkit of Post-Training Quantization for Text Processing via Self-Adaptive Mixed-Precision