DCP supports hybrid attention (#40996)
Signed-off-by: YanXu <yancey.yx@alibaba-inc.com> Signed-off-by: Jingyi Yang <girasoleyang@gmail.com> Co-authored-by: Jingyi Yang <girasoleyang@gmail.com>
This commit is contained in:
@@ -171,6 +171,7 @@ MODEL_CONFIGS: dict[str, VitCudagraphTestConfig] = {
|
||||
"Describe this video in one sentence."
|
||||
),
|
||||
needs_video_metadata=True,
|
||||
vllm_runner_kwargs={"enable_chunked_prefill": True},
|
||||
marks=[pytest.mark.core_model],
|
||||
),
|
||||
"internvl": VitCudagraphTestConfig(
|
||||
|
||||
Reference in New Issue
Block a user