Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: huggingface/optimum
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: v2.0.0
Choose a base ref
...
head repository: huggingface/optimum
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: v2.1.0
Choose a head ref
  • 11 commits
  • 25 files changed
  • 8 contributors

Commits on Oct 9, 2025

  1. update deps (#2368) 

    v2 release
    @IlyasMoutawwakil
    IlyasMoutawwakil authored Oct 9, 2025
    Configuration menu
    Copy the full SHA
    c98f2b0 View commit details
    Browse the repository at this point in the history

  2. update README following v2 release (#2370)

    @echarlaix
    echarlaix authored Oct 9, 2025
    Configuration menu
    Copy the full SHA
    857ad93 View commit details
    Browse the repository at this point in the history

  3. Dev version (#2369)

    @echarlaix
    echarlaix authored Oct 9, 2025
    Configuration menu
    Copy the full SHA
    0fc0939 View commit details
    Browse the repository at this point in the history

Commits on Oct 27, 2025

  1. Add documentation typo fix (#2375) 

    Fixed a small typo
    @ImadSaddik
    ImadSaddik authored Oct 27, 2025
    Configuration menu
    Copy the full SHA
    86024c3 View commit details
    Browse the repository at this point in the history

Commits on Oct 28, 2025

  1. Combine documentation from all optimum subpackages (#2353) 

    * Combine documentation from all optimum subpackages

* style

* add links

* update workflow

* fix habana section title

* move habana section to make it closer to intel

* add redirects
    @echarlaix
    echarlaix authored Oct 28, 2025
    Configuration menu
    Copy the full SHA
    90815ff View commit details
    Browse the repository at this point in the history

Commits on Oct 30, 2025

  1. Update Intel doc (#2378)

    @regisss
    regisss authored Oct 30, 2025
    Configuration menu
    Copy the full SHA
    79e8cd8 View commit details
    Browse the repository at this point in the history

Commits on Oct 31, 2025

  1. Fix pip update for windows workflow (#2381)

    @echarlaix
    echarlaix authored Oct 31, 2025
    Configuration menu
    Copy the full SHA
    2e8e232 View commit details
    Browse the repository at this point in the history

Commits on Nov 14, 2025

  1. handle missing TF2_WEIGHTS_NAME for newer transformers versions (#2384)

    @niyarrbarman
    niyarrbarman authored Nov 14, 2025
    Configuration menu
    Copy the full SHA
    b7f00d5 View commit details
    Browse the repository at this point in the history

Commits on Dec 8, 2025

  1. Transformers v5 pre release (#2387) 

    * test main

* test

* fix

* fx

* move
    @IlyasMoutawwakil
    IlyasMoutawwakil authored Dec 8, 2025
    Configuration menu
    Copy the full SHA
    0227a1c View commit details
    Browse the repository at this point in the history

Commits on Dec 17, 2025

  1. Fully deprecate AutoGPTQ for GPT-QModel (#2385) 

    * call hf_select_quant_linear_v2()

Signed-off-by: ZX-ModelCloud <[email protected]>

* Remove the import of auto_gptq

Signed-off-by: ZX-ModelCloud <[email protected]>

* Remove the import of auto_gptq in unittests

Signed-off-by: ZX-ModelCloud <[email protected]>

* Fixed the incorrect layer_output when using the latest version of transformers.

Signed-off-by: ZX-ModelCloud <[email protected]>

* use assertEqual instead of assertTrue

Signed-off-by: ZX-ModelCloud <[email protected]>

* load_quantized_model() remove "disable_exllama" and "exllama_config" arguments

Signed-off-by: ZX-ModelCloud <[email protected]>

* fix gptq unittest

Signed-off-by: ZX-ModelCloud <[email protected]>

* fix gptq unittest

Signed-off-by: ZX-ModelCloud <[email protected]>

* setting offload_to_disk=False

Signed-off-by: ZX-ModelCloud <[email protected]>

* remove auto_gptq

Signed-off-by: ZX-ModelCloud <[email protected]>

* format

Signed-off-by: ZX-ModelCloud <[email protected]>

* format

Signed-off-by: ZX-ModelCloud <[email protected]>

* fix

* fix

* remove ExllamaV1 Test

Signed-off-by: ZX-ModelCloud <[email protected]>

* update ci

* test

* avoid uv

* re-enable uv and pin to >= 5.6.12

* Update .github/workflows/test_gptq.yml

Co-authored-by: Ilyas Moutawwakil <[email protected]>

---------

Signed-off-by: ZX-ModelCloud <[email protected]>
Co-authored-by: IlyasMoutawwakil <[email protected]>
Co-authored-by: Qubitium-ModelCloud <[email protected]>
Co-authored-by: Ilyas Moutawwakil <[email protected]>
    @ZX-ModelCloud @IlyasMoutawwakil @Qubitium
    4 people authored Dec 17, 2025
    Configuration menu
    Copy the full SHA
    3a85d51 View commit details
    Browse the repository at this point in the history

Commits on Dec 19, 2025

  1. git commit -m "Release: v2.1.0"

    @IlyasMoutawwakil
    IlyasMoutawwakil committed Dec 19, 2025
    Configuration menu
    Copy the full SHA
    8cfe543 View commit details
    Browse the repository at this point in the history
Loading