From 282e0b664231275d9a17f56880c99e084028a435 Mon Sep 17 00:00:00 2001 From: amy-why-3459 Date: Wed, 6 May 2026 20:42:56 +0800 Subject: [PATCH] [BugFix][CI] Change max_tokens from 150 to 2048 (#3376) Signed-off-by: amy-why-3459 Co-authored-by: Gao Han --- tests/e2e/online_serving/test_qwen3_omni_expansion.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tests/e2e/online_serving/test_qwen3_omni_expansion.py b/tests/e2e/online_serving/test_qwen3_omni_expansion.py index 9601057d4..2d23a3fb3 100644 --- a/tests/e2e/online_serving/test_qwen3_omni_expansion.py +++ b/tests/e2e/online_serving/test_qwen3_omni_expansion.py @@ -49,7 +49,7 @@ def get_batch_token_config(default_path): ) -def get_async_chunk_config(default_path): +def get_default_config(default_path): """Flip async_chunk on and bump stage 0 thinker output to 2048 tokens. Pipeline registry (qwen3_omni/pipeline.py) already wires @@ -75,14 +75,17 @@ default_path = get_deploy_config_path("ci/qwen3_omni_moe.yaml") test_params = [ pytest.param( OmniServerParams( - model=model, stage_config_path=default_path, use_stage_cli=True, server_args=["--no-async-chunk"] + model=model, + stage_config_path=get_default_config(default_path), + use_stage_cli=True, + server_args=["--no-async-chunk"], ), id="default", ), pytest.param( OmniServerParams( model=model, - stage_config_path=get_async_chunk_config(default_path), + stage_config_path=get_default_config(default_path), use_stage_cli=True, server_args=["--async-chunk"], ),