[CI] Refresh hybrid Model Runner V2 coverage (#51410)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
This commit is contained in:
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import os
|
||||
from typing import Any
|
||||
|
||||
import pytest
|
||||
@@ -72,12 +71,6 @@ def test_mtp_correctness(
|
||||
draft_model = None
|
||||
_skip_if_insufficient_gpus_for_tp(tp_size)
|
||||
|
||||
if "Qwen3.5" in model_name and os.environ.get("VLLM_USE_V2_MODEL_RUNNER"):
|
||||
pytest.skip(
|
||||
"Model Runner V2 does not yet support hybrid models "
|
||||
"(Qwen3.5 mixes Mamba-style GDN with attention layers)."
|
||||
)
|
||||
|
||||
attn_backend = "TRITON_ATTN" if current_platform.is_rocm() else "auto"
|
||||
|
||||
# Skip multimodal profiling for models that don't need it in this test.
|
||||
|
||||
Reference in New Issue
Block a user