Skip to content
/ Model-Quantization Public template

Quantization is a technique to reduce the computational and memory costs of running inference by representing the weights and activations with low-precision data types like 8-bit integer (int8) instead of the usual 32-bit floating point (float32).

Notifications You must be signed in to change notification settings

SRDdev/Model-Quantization

Error
Looks like something went wrong!

About

Quantization is a technique to reduce the computational and memory costs of running inference by representing the weights and activations with low-precision data types like 8-bit integer (int8) instead of the usual 32-bit floating point (float32).

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published