Commits on May 31, 2024

1. Replace implementation for int8 dynamic quantization with call to `qu… …

   …antize`
   
   Summary:
   Previously we added `quantize` as a general API (pytorch#256) for
   Affine Quantized tensor subclass, and also tensor subclass based dtype conversion in general.
   
   The plan is to use this to replace existing quant APIs including int4 weight only, int8 weight only, int8 dynamic quant
   and 8da4w (for executorch).
   
   This PR we started replacing the implementation of int8 dynamic quant API with `quantize` API with affine quantized tensor
   subclass. We'll make sure the performance does not regress for vit model.
   
   Test Plan:
   TORCH_LOGS='output_code' python tutorials/quantize_vit/run_vit_b_quant.py
   
   reference: elapsed_time:  1.4821058654785155  milliseconds
   after refactor: elapsed_time:  1.4804757690429688  milliseconds
   
   generated code diff: https://gist.github.com/jerryzh168/90c71107a5aaaa5d8dd2170c573e076d
   
   Reviewers:
   
   Subscribers:
   
   Tasks:
   
   Tags:

   

   jerryzh168 committed May 31, 2024
   Configuration menu

   • View commit details
   • Copy full SHA for 4ec820d
   • Browse repository at this point

   Copy the full SHA

   4ec820d View commit details

   Browse the repository at this point in the history