Skip to content

enable 2 llama UT cases on xpu #37126

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
Merged
ydshieh merged 11 commits into from
Apr 7, 2025
Merged

enable 2 llama UT cases on xpu #37126

ydshieh merged 11 commits into from
Apr 7, 2025

Conversation

@yao-matrix
Copy link
Contributor

@yao-matrix yao-matrix commented Mar 31, 2025 •
edited
Loading

case 1: pytest -rA tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits
case 2: pytest -rA tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16

both don't have XPU criteria, put them as key 0 and reuse A100/A100 ground truth. Both can pass in Ponte Vecchio XPU.

@yao-matrix
enable tests/models/llama/test_modeling_llama.py::LlamaIntegrationTes…
0f0bf39 
…t::test_model_7b_logits and tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16 on xpu

Signed-off-by: YAO Matrix <[email protected]>
@github-actions github-actions bot marked this pull request as draft March 31, 2025 05:19
@github-actions
Copy link
Contributor

github-actions bot commented Mar 31, 2025

Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. The CI will be paused while the PR is in draft mode. When it is ready for review, please click the Ready for review button (at the bottom of the PR page). This will assign reviewers and trigger CI.

@yao-matrix yao-matrix marked this pull request as ready for review March 31, 2025 05:22
@github-actions github-actions bot requested a review from ydshieh March 31, 2025 05:22
@ydshieh
Copy link
Collaborator

ydshieh commented Mar 31, 2025

Hi @yao-matrix Thank you for this PR. It's not good to use 0 as the key IMO.

In #36569, @ivarflakstad introduced a way to better deal with more general expected values. Could you try to use that new approach in this PR? Thank you!

@yao-matrix
Copy link
Contributor Author

yao-matrix commented Apr 1, 2025

Hi @yao-matrix Thank you for this PR. It's not good to use 0 as the key IMO.

In #36569, @ivarflakstad introduced a way to better deal with more general expected values. Could you try to use that new approach in this PR? Thank you!

@ydshieh i switched to use Expectations, pls help review, thx.

ydshieh
ydshieh reviewed Apr 1, 2025
View reviewed changes
@ydshieh ydshieh mentioned this pull request Apr 2, 2025
Merged
ydshieh
ydshieh approved these changes Apr 3, 2025
View reviewed changes
Copy link
Collaborator

@ydshieh ydshieh left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for the iteration 🙏 💯

SunMarc
SunMarc approved these changes Apr 7, 2025
View reviewed changes
Copy link
Member

@SunMarc SunMarc left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice

@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Apr 7, 2025

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@ydshieh
Copy link
Collaborator

ydshieh commented Apr 7, 2025 •
edited
Loading

Let me run on CI runner and merge if everything is good !
Thank you a lot for the iterations.

@ydshieh ydshieh merged commit 12bf24d into huggingface:main Apr 7, 2025
18 of 20 checks passed
@Rocketknight1 Rocketknight1 mentioned this pull request Apr 7, 2025
Merged
vasqu pushed a commit to vasqu/transformers that referenced this pull request Apr 7, 2025
@yao-matrix @SunMarc @vasqu
enable 2 llama UT cases on xpu (huggingface#37126)
3ccf0b4 
* enable tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits and tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16 on xpu

Signed-off-by: YAO Matrix <[email protected]>

* switch to use Expectations

Signed-off-by: YAO Matrix <[email protected]>

* fix style

Signed-off-by: YAO Matrix <[email protected]>

* extract gen bits from architecture and use it

Signed-off-by: YAO Matrix <[email protected]>

* add cross refererence

Signed-off-by: YAO Matrix <[email protected]>

* fix style

Signed-off-by: YAO Matrix <[email protected]>

---------

Signed-off-by: YAO Matrix <[email protected]>
Co-authored-by: Marc Sun <[email protected]>
@yao-matrix yao-matrix deleted the issue175 branch April 8, 2025 00:22
cyr0930 pushed a commit to cyr0930/transformers that referenced this pull request Apr 18, 2025
@yao-matrix @SunMarc
enable 2 llama UT cases on xpu (huggingface#37126)
2b97653 
* enable tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits and tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16 on xpu

Signed-off-by: YAO Matrix <[email protected]>

* switch to use Expectations

Signed-off-by: YAO Matrix <[email protected]>

* fix style

Signed-off-by: YAO Matrix <[email protected]>

* extract gen bits from architecture and use it

Signed-off-by: YAO Matrix <[email protected]>

* add cross refererence

Signed-off-by: YAO Matrix <[email protected]>

* fix style

Signed-off-by: YAO Matrix <[email protected]>

---------

Signed-off-by: YAO Matrix <[email protected]>
Co-authored-by: Marc Sun <[email protected]>
zucchini-nlp pushed a commit to zucchini-nlp/transformers that referenced this pull request May 14, 2025
@yao-matrix @SunMarc @zucchini-nlp
enable 2 llama UT cases on xpu (huggingface#37126)
8a4f709 
* enable tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits and tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16 on xpu

Signed-off-by: YAO Matrix <[email protected]>

* switch to use Expectations

Signed-off-by: YAO Matrix <[email protected]>

* fix style

Signed-off-by: YAO Matrix <[email protected]>

* extract gen bits from architecture and use it

Signed-off-by: YAO Matrix <[email protected]>

* add cross refererence

Signed-off-by: YAO Matrix <[email protected]>

* fix style

Signed-off-by: YAO Matrix <[email protected]>

---------

Signed-off-by: YAO Matrix <[email protected]>
Co-authored-by: Marc Sun <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@ydshieh ydshieh ydshieh approved these changes

@ivarflakstad ivarflakstad ivarflakstad left review comments

@SunMarc SunMarc SunMarc approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@yao-matrix @ydshieh @HuggingFaceDocBuilderDev @SunMarc @ivarflakstad