Arm backend: Test partial quantization of models on VGF#16311
Arm backend: Test partial quantization of models on VGF#16311zingo merged 1 commit intopytorch:mainfrom
Conversation
Run tests of partial quantization on the MobileNetV2 and Llama models using the VGF backend (INT+FP profile). Signed-off-by: Martin Lindström <Martin.Lindstroem@arm.com> Change-Id: I581f1c2be89e15ed186db2189fc507bfa1a82d6a
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16311
Note: Links to docs will display an error until the docs builds have been completed. ❌ 8 New Failures, 2 Unrelated FailuresAs of commit 5d0df2d with merge base 3233761 ( NEW FAILURES - The following jobs have failed:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@pytorchbot label ciflow/trunk |
|
@pytorchbot label "partner: arm" |
This PR needs a
|
zingo
left a comment
There was a problem hiding this comment.
Some CI fails, this might just need a rerun
FAILED backends/arm/test/misc/test_mixed_type_lowering.py::test_mixed_type_lowering - RuntimeError: Expected 2 occurencies of op='ADD', dtype='FP32' but found 6.
= 1 failed, 5985 passed, 2578 skipped, 176 xfailed, 14 xpassed, 36156 warnings in 5569.39s (1:32:49) =
Arm: test_T5ForConditionalGeneration_tosa_* fails are unrelated and fails without the PR
|
Known unrelated Arm fails |
Run tests of partial quantization on the MobileNetV2 and Llama models using the VGF backend (INT+FP profile). Signed-off-by: Martin Lindström <Martin.Lindstroem@arm.com> Co-authored-by: Martin Lindström <Martin.Lindstroem@arm.com>
Run tests of partial quantization on the MobileNetV2 and Llama models using the VGF backend (INT+FP profile).
cc @freddan80 @per @zingo @oscarandersson8218 @digantdesai