[CI]enable chunked prefill by default (#4569)
set `enable_chunked_prefill` to True for e2e test by default to keep the same behavior with vLLM - vLLM version: v0.11.2 Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
@@ -58,7 +58,6 @@ 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:
|
||||
|
||||
Reference in New Issue
Block a user