-
Notifications
You must be signed in to change notification settings - Fork 31.2k
fix test failure of speculative_generation on xpu #42052
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
Conversation
Signed-off-by: Wang, Yi A <[email protected]>
|
@vasqu could you help review it, thanks |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The conditionals are getting longer and longer. Maybe it would be nicer to split these into cuda vs xpu and have proper explanations/comments at each point?
Edit: Not sure if the change in expected outputs is good, depends if things were faulty before (which I assume was the case) it's expected and was clarified under this review
Signed-off-by: Wang, Yi A <[email protected]>
I split xpu out and add comment in the func |
vasqu
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thx, lgtm let's just move this one if a bit and add a comment there
Signed-off-by: Wang, Yi A <[email protected]>
|
[For maintainers] Suggested jobs to run (before merge) run-slow: qwen3 |
|
Thx for iterating, merging now |
|
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. |
fix pytest failure of following case
tests/generation/test_candidate_generator.py::TestUniversalSpeculativeDecoding::test_usd_vs_vanilla_sampling
tests/models/mistral/test_modeling_mistral.py::MistralIntegrationTest::test_speculative_generation
tests/models/qwen2/test_modeling_qwen2.py::Qwen2IntegrationTest::test_speculative_generation
tests/models/qwen3/test_modeling_qwen3.py::Qwen3IntegrationTest::test_speculative_generation
tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_speculative_decoding_non_distil
tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_speculative_decoding_distil
tests/models/sam2_video/test_modeling_sam2_video.py::Sam2VideoModelIntegrationTest::test_inference_propagate_on_streamed_video
tests/models/sam2_video/test_modeling_sam2_video.py::Sam2VideoModelIntegrationTest::test_inference_mask_generation_video_one_point_propagate_in_video_directly
tests/models/univnet/test_modeling_univnet.py::UnivNetModelIntegrationTests::test_integration