[MM][CG] Optimize default max_frames_per_batch auto-infer for ViT CUDA graph video inference (#40445)
Signed-off-by: shen-shanshan <467638484@qq.com>
This commit is contained in:
@@ -1531,6 +1531,12 @@ class SupportsEncoderCudaGraph(Protocol):
|
||||
"""Return the modality of the inputs."""
|
||||
...
|
||||
|
||||
def get_max_frames_per_video(
|
||||
self,
|
||||
) -> int:
|
||||
"""Return model-specific max frames per video."""
|
||||
...
|
||||
|
||||
def get_encoder_cudagraph_budget_range(
|
||||
self,
|
||||
vllm_config: "VllmConfig",
|
||||
|
||||
Reference in New Issue
Block a user