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

Test ResNet Ops Support #28

Closed
wants to merge 27 commits into from
Closed

Test ResNet Ops Support #28

wants to merge 27 commits into from

Commits on Jun 28, 2024

  1. E2M1 compression. (openvinotoolkit#2745) 

    ### Changes

Support e2m1 as type for weight compression.

### Reason for changes

e2m1 compression.

### Related tickets

CVS-140944
    @andreyanufr
    andreyanufr authored Jun 28, 2024
    Configuration menu
    Copy the full SHA
    2ba43bd View commit details
    Browse the repository at this point in the history

  2. Update Fast-/BC algorithms (openvinotoolkit#2747) 

    ### Changes

- Updated FastBiasCorrection algorithm to correct work with transposed
MatMul layers.
- Updated BiasCorrection algorithm to avoid recursion depth error.

### Reason for changes

- FastBiasCorrection algorithm adaptation.
- BiasCorrection improvement for many correctable layers.

### Related tickets

- 144240

---------

Co-authored-by: Aleksei Kashapov <[email protected]>
    @KodiaqQ @kshpv
    KodiaqQ and kshpv authored Jun 28, 2024
    Configuration menu
    Copy the full SHA
    beb9c04 View commit details
    Browse the repository at this point in the history

Commits on Jul 1, 2024

  1. Support TF 2.15 (openvinotoolkit#2609) 

    ### Changes

Support TF 2.15

### Reason for changes

Support TF 2.15

### Related tickets

133742

### Tests

pre-commit tests
    @andrey-churkin
    andrey-churkin authored Jul 1, 2024
    Configuration menu
    Copy the full SHA
    a25e56d View commit details
    Browse the repository at this point in the history

  2. [PT] Quantization of addmm function (openvinotoolkit#2713) 

    ### Changes

- quantize addmm function
- add gpt2 to post_training tests
- add calculation  int8 annd int4 const data for ptq


### Related tickets

142356
    @AlexanderDokuchaev
    AlexanderDokuchaev authored Jul 1, 2024
    Configuration menu
    Copy the full SHA
    082841c View commit details
    Browse the repository at this point in the history

  3. Remove reference data for TF 2.8 from the tests (openvinotoolkit#2770) 

    ### Changes

Remove reference data for TF 2.8 from the tests

### Reason for changes

Follow-up openvinotoolkit#2609

### Related tickets

133742

### Tests

pre-commit tests
    @andrey-churkin
    andrey-churkin authored Jul 1, 2024
    Configuration menu
    Copy the full SHA
    e8ea252 View commit details
    Browse the repository at this point in the history

  4. Revert "Update Fast-/BC algorithms (openvinotoolkit#2747)" (openvinot… 

    …oolkit#2771)

This reverts commit beb9c04.

post_training_quantization/415 - running
    @KodiaqQ
    KodiaqQ authored Jul 1, 2024
    Configuration menu
    Copy the full SHA
    f5ad4ea View commit details
    Browse the repository at this point in the history

Commits on Jul 2, 2024

  1. Extending functions by lstsq, svd, eye (openvinotoolkit#2774) 

    ### Changes
The following functions were added:

- numeric.py: eye
- linalg.py: lstsq, svd


### Reason for changes
Part of int4 with LoRA adaptation implementation.

### Related tickets
CVS-135863

### Tests
tests/shared/test_templates/template_test_nncf_tensor.py
    @ljaljushkin
    ljaljushkin authored Jul 2, 2024
    Configuration menu
    Copy the full SHA
    1f07622 View commit details
    Browse the repository at this point in the history

Commits on Jul 3, 2024

  1. Adjust NNCF to numpy 2.0 api (openvinotoolkit#2772) 

    ### Changes

- https://numpy.org/devdocs/numpy_2_0_migration_guide.html
- Enable numpy rules for ruff

### Related tickets

138867
    @AlexanderDokuchaev
    AlexanderDokuchaev authored Jul 3, 2024
    Configuration menu
    Copy the full SHA
    aeaaf19 View commit details
    Browse the repository at this point in the history

  2. Update Fast-/BC with MatMul/Gemm support (openvinotoolkit#2776) 

    ### Changes

- Updated FastBiasCorrection algorithm to correct work with transposed
MatMul (OV) and Gemm (ONNX) layers.
- Updated BiasCorrection algorithm to avoid recursion depth error.

### Reason for changes

- FastBiasCorrection algorithm adaptation.
- BiasCorrection improvement for many correctable layers.

### Related tickets

- 144240

### Tests

 - manual, post_training_quantization/418/ - passed
    @KodiaqQ
    KodiaqQ authored Jul 3, 2024
    Configuration menu
    Copy the full SHA
    a644a1e View commit details
    Browse the repository at this point in the history

  3. E8M0 scale for E2M1 weights. (openvinotoolkit#2767) 

    ### Changes

Changed default scale fot E2M1 weights from fp16 to fp8_e8m0

### Reason for changes

According to the "OCP Microscaling Formats (MX) Specification"

### Related tickets

CVS-140944

### Tests

Will extend E2M1 tests.
    @andreyanufr
    andreyanufr authored Jul 3, 2024
    Configuration menu
    Copy the full SHA
    fd0e33c View commit details
    Browse the repository at this point in the history

  4. TorchFX quantization init

    @daniil-lyakhov
    daniil-lyakhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    3ef206c View commit details
    Browse the repository at this point in the history

  5. Test code is removed

    @daniil-lyakhov
    daniil-lyakhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    58606d0 View commit details
    Browse the repository at this point in the history

  6. Reference graph are updated

    @daniil-lyakhov
    daniil-lyakhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    f0b926e View commit details
    Browse the repository at this point in the history

  7. torch-fx tests are added to pre-commit

    @daniil-lyakhov
    daniil-lyakhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    988c3a2 View commit details
    Browse the repository at this point in the history

  8. Comments

    @daniil-lyakhov
    daniil-lyakhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    acdf603 View commit details
    Browse the repository at this point in the history

  9. Model transformer minor refactoring

    @daniil-lyakhov
    daniil-lyakhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    55658a5 View commit details
    Browse the repository at this point in the history

  10. Comments

    @daniil-lyakhov
    daniil-lyakhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    1a1ef4a View commit details
    Browse the repository at this point in the history

  11. Comments

    @daniil-lyakhov
    daniil-lyakhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    ac37c1d View commit details
    Browse the repository at this point in the history

  12. Rebase

    @daniil-lyakhov
    daniil-lyakhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    c48ac6c View commit details
    Browse the repository at this point in the history

  13. Docstrings / SDPA unfold is removed

    @daniil-lyakhov
    daniil-lyakhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    c2f3201 View commit details
    Browse the repository at this point in the history

  14. Rebase

    @daniil-lyakhov
    daniil-lyakhov committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    745e6f0 View commit details
    Browse the repository at this point in the history

Commits on Jul 4, 2024

  1. Comments

    @daniil-lyakhov
    daniil-lyakhov committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    6ba8a34 View commit details
    Browse the repository at this point in the history

Commits on Jul 8, 2024

  1. Add pytest for resnet for FX

    @anzr299
    anzr299 committed Jul 8, 2024
    Configuration menu
    Copy the full SHA
    b56a3a4 View commit details
    Browse the repository at this point in the history

  2. Add ruff fix for unused variables

    @anzr299
    anzr299 committed Jul 8, 2024
    Configuration menu
    Copy the full SHA
    5c0d504 View commit details
    Browse the repository at this point in the history

  3. add test for mobilenet_v3_small and vit_b_16.

    @anzr299
    anzr299 committed Jul 8, 2024
    Configuration menu
    Copy the full SHA
    125a10f View commit details
    Browse the repository at this point in the history

  4. Edit operator metatypes to include torch.nn.hardswish_ and torch.drop… 

    …out_
    @anzr299
    anzr299 committed Jul 8, 2024
    Configuration menu
    Copy the full SHA
    d9e4c41 View commit details
    Browse the repository at this point in the history

  5. Remove debug print statements

    @anzr299
    anzr299 committed Jul 8, 2024
    Configuration menu
    Copy the full SHA
    e532407 View commit details
    Browse the repository at this point in the history