[BugFix] Adapted Qwen3-Next eager mode to v0.11.2 (#4477)

### What this PR does / why we need it?

Adapted Qwen3-Next eager mode to `v0.11.2`.


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

Signed-off-by: drslark <slarksblood@qq.com>
This commit is contained in:
drslark
2025-11-27 17:44:59 +08:00
committed by GitHub
parent b220de33e8
commit 1cae3e4a49
3 changed files with 16 additions and 13 deletions

View File

@@ -58,6 +58,7 @@ INPUT_PROMPTS = [
]
@pytest.mark.skip(reason="Fix me, the accuracy is not correct")
@pytest.mark.parametrize("model", MODELS)
@pytest.mark.parametrize("max_tokens", [50])
def test_prefix_cache_with_v1_scheduler(model: str, max_tokens: int) -> None: