From b799f4b9ea8d15d62c4f4a97926b274561fd9492 Mon Sep 17 00:00:00 2001 From: 22quinn <33176974+22quinn@users.noreply.github.com> Date: Sun, 10 Aug 2025 19:30:00 -0700 Subject: [PATCH] [CI/Build] Fix tensorizer test for load_format change (#22583) Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com> --- .buildkite/test-pipeline.yaml | 1 - tests/entrypoints/openai/test_tensorizer_entrypoint.py | 2 +- tests/tensorizer_loader/test_tensorizer.py | 4 ++-- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml index 221888edb3740..db7351edbb8d6 100644 --- a/.buildkite/test-pipeline.yaml +++ b/.buildkite/test-pipeline.yaml @@ -426,7 +426,6 @@ steps: - label: Tensorizer Test # 11min mirror_hardwares: [amdexperimental] - soft_fail: true source_file_dependencies: - vllm/model_executor/model_loader - tests/tensorizer_loader diff --git a/tests/entrypoints/openai/test_tensorizer_entrypoint.py b/tests/entrypoints/openai/test_tensorizer_entrypoint.py index 4bf3798503656..058e96f203c38 100644 --- a/tests/entrypoints/openai/test_tensorizer_entrypoint.py +++ b/tests/entrypoints/openai/test_tensorizer_entrypoint.py @@ -44,7 +44,7 @@ def model_uri(tmp_dir): def tensorize_model_and_lora(tmp_dir, model_uri): tensorizer_config = TensorizerConfig(tensorizer_uri=model_uri, lora_dir=tmp_dir) - args = EngineArgs(model=MODEL_NAME, device="cuda") + args = EngineArgs(model=MODEL_NAME) tensorize_lora_adapter(LORA_PATH, tensorizer_config) tensorize_vllm_model(args, tensorizer_config) diff --git a/tests/tensorizer_loader/test_tensorizer.py b/tests/tensorizer_loader/test_tensorizer.py index b8d7892e57f21..0fb142a1b6e56 100644 --- a/tests/tensorizer_loader/test_tensorizer.py +++ b/tests/tensorizer_loader/test_tensorizer.py @@ -166,7 +166,7 @@ def test_load_without_tensorizer_load_format(vllm_runner, capfd, model_ref): combined_output = out + err assert ("ValueError: Model loader extra config " "is not supported for load " - "format LoadFormat.AUTO") in combined_output + "format auto") in combined_output finally: del model gc.collect() @@ -186,7 +186,7 @@ def test_raise_value_error_on_invalid_load_format(vllm_runner, capfd, combined_output = out + err assert ("ValueError: Model loader extra config is not supported " - "for load format LoadFormat.SAFETENSORS") in combined_output + "for load format safetensors") in combined_output finally: del model gc.collect()