Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add option to disable fake quant for 8da4w QAT #198

Merged
merged 4 commits into from
May 4, 2024
Merged

Commits on May 2, 2024

  1. Add option to disable fake quant for 8da4w QAT

    Summary: This feature helps with model convergence during QAT.
    The user can disable observation/fake quant for the first N
    steps and renable them later, allowing the activation and
    weight values to stabilize before applying quantization.
    
    Test Plan:
    python test/quantization/test_qat.py -k test_qat_8da4w_quantizer_disable_fake_quant
    python test/quantization/test_qat.py -k test_qat_8da4w_quantizer_disable_fake_quant_backward
    
    Reviewers: jerryzh168, cpuhrsch
    
    Subscribers: jerryzh168, cpuhrsch, supriyar
    andrewor14 committed May 2, 2024
    Configuration menu
    Copy the full SHA
    56afc27 View commit details
    Browse the repository at this point in the history

Commits on May 3, 2024

  1. Configuration menu
    Copy the full SHA
    162a37d View commit details
    Browse the repository at this point in the history
  2. Configuration menu
    Copy the full SHA
    14af551 View commit details
    Browse the repository at this point in the history

Commits on May 4, 2024

  1. Configuration menu
    Copy the full SHA
    05ff87c View commit details
    Browse the repository at this point in the history