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.

Sign up for GitHub

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

Jump to bottom

[Quant tool] Handle input models with pre-quantized weights #22633

Merged
merged 13 commits into from
Nov 14, 2024
Merged

[Quant tool] Handle input models with pre-quantized weights #22633

merged 13 commits into from
Nov 14, 2024
+342 −11

Commits on Oct 28, 2024

  1. First working version that handles pre-quantized weights

    @adrianlizarraga
    adrianlizarraga committed Oct 28, 2024
    Configuration menu
    Copy the full SHA
    e104ef4 View commit details
    Browse the repository at this point in the history

  2. Remove extra options; just handle pre-quantized weights if they exist

    @adrianlizarraga
    adrianlizarraga committed Oct 28, 2024
    Configuration menu
    Copy the full SHA
    7af7f3a View commit details
    Browse the repository at this point in the history

  3. Undo import changes to run unittests locally

    @adrianlizarraga
    adrianlizarraga committed Oct 28, 2024
    Configuration menu
    Copy the full SHA
    33b0266 View commit details
    Browse the repository at this point in the history

Commits on Oct 29, 2024

  1. Use temp files to store unittest models

    @adrianlizarraga
    adrianlizarraga committed Oct 29, 2024
    Configuration menu
    Copy the full SHA
    b653ccc View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into adrianl/quant-tool-handle-prequantized-weights

    @adrianlizarraga
    adrianlizarraga committed Oct 29, 2024
    Configuration menu
    Copy the full SHA
    5d65b4c View commit details
    Browse the repository at this point in the history

Commits on Nov 13, 2024

  1. Merge main and fix conflicts

    @adrianlizarraga
    adrianlizarraga committed Nov 13, 2024
    Configuration menu
    Copy the full SHA
    29b839b View commit details
    Browse the repository at this point in the history

Commits on Nov 14, 2024

  1. Check for pre-quantized tensor instead of pre-quantized initializer s… 

    …pecifically.
    @adrianlizarraga
    adrianlizarraga committed Nov 14, 2024
    Configuration menu
    Copy the full SHA
    e87b53f View commit details
    Browse the repository at this point in the history

  2. Update unit tests for pre-quantized weights

    @adrianlizarraga
    adrianlizarraga committed Nov 14, 2024
    Configuration menu
    Copy the full SHA
    eb8981e View commit details
    Browse the repository at this point in the history

  3. Merge branch 'main' into adrianl/quant-tool-handle-prequantized-weights

    @adrianlizarraga
    adrianlizarraga committed Nov 14, 2024
    Configuration menu
    Copy the full SHA
    7adcbd7 View commit details
    Browse the repository at this point in the history

  4. Check that the scale/zero-point do not change for pre-quantized weigh… 

    …ts after quantization
    @adrianlizarraga
    adrianlizarraga committed Nov 14, 2024
    Configuration menu
    Copy the full SHA
    0f0a3e0 View commit details
    Browse the repository at this point in the history

  5. import annotations in onnx_model.py

    @adrianlizarraga
    adrianlizarraga committed Nov 14, 2024
    Configuration menu
    Copy the full SHA
    b70729d View commit details
    Browse the repository at this point in the history

  6. Simplify and reduce diff

    @adrianlizarraga
    adrianlizarraga committed Nov 14, 2024
    Configuration menu
    Copy the full SHA
    5096e7e View commit details
    Browse the repository at this point in the history

  7. Merge branch 'main' into adrianl/quant-tool-handle-prequantized-weights

    @adrianlizarraga
    adrianlizarraga committed Nov 14, 2024
    Configuration menu
    Copy the full SHA
    3df2ddb View commit details
    Browse the repository at this point in the history