Search Results for author: Mingfei Guo

Found 3 papers, 0 papers with code

Analyzing Quantization in TVM

no code implementations19 Aug 2023 Mingfei Guo

Typically, when applying 8-bit quantization to a deep learning model, it is usually expected to achieve around 50% of the full-precision inference time.

Quantization

Cannot find the paper you are looking for? You can Submit a new open access paper.