From 107422b1dc0cb4a03a84f814f6ffe0d74994c4e6 Mon Sep 17 00:00:00 2001 From: Jack Zhang Date: Fri, 15 Nov 2024 17:43:39 -0500 Subject: [PATCH] Temp disable OOMing llama vision decoder test --- .ci/scripts/gather_test_models.py | 2 +- examples/models/__init__.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.ci/scripts/gather_test_models.py b/.ci/scripts/gather_test_models.py index 078561c9d85..87ed31af3dd 100755 --- a/.ci/scripts/gather_test_models.py +++ b/.ci/scripts/gather_test_models.py @@ -25,7 +25,7 @@ "resnet50": "linux.12xlarge", "llava": "linux.12xlarge", "llama3_2_vision_encoder": "linux.12xlarge", - "llama3_2_text_decoder": "linux.12xlarge", + # "llama3_2_text_decoder": "linux.12xlarge", # TODO: re-enable test when Huy's change is in / model gets smaller. # This one causes timeout on smaller runner, the root cause is unclear (T161064121) "dl3": "linux.12xlarge", "emformer_join": "linux.12xlarge", diff --git a/examples/models/__init__.py b/examples/models/__init__.py index 842b87241cc..706b0105af8 100644 --- a/examples/models/__init__.py +++ b/examples/models/__init__.py @@ -19,7 +19,7 @@ "llama2": ("llama", "Llama2Model"), "llama": ("llama", "Llama2Model"), "llama3_2_vision_encoder": ("llama3_2_vision", "FlamingoVisionEncoderModel"), - "llama3_2_text_decoder": ("llama3_2_vision", "Llama3_2Decoder"), + # "llama3_2_text_decoder": ("llama3_2_vision", "Llama3_2Decoder"), "lstm": ("lstm", "LSTMModel"), "mobilebert": ("mobilebert", "MobileBertModelExample"), "mv2": ("mobilenet_v2", "MV2Model"),