[BugFix][CI] Change max_tokens from 150 to 2048 (#3376)

Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
This commit is contained in:
amy-why-3459andGao Han authored and GitHub committed 2026-05-06 20:42:56 +08:00
1 parent 1e5f288a91
commit 282e0b6642
1 file changed
+6 -3
@@ -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"],
),