[Bugfix][Pooling] Handle multimodal cache misses without crashing (#58975)
Signed-off-by: linchaoying6 <linchaoying6@jd.com> Co-authored-by: linchaoying6 <linchaoying6@jd.com> Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
co-authored by
linchaoying6
OpenAI Codex
parent
443dccd3c9
commit
592c6f3fbc
@@ -143,6 +143,13 @@ class WorkerBase:
|
||||
if callable(reset_fn):
|
||||
reset_fn()
|
||||
|
||||
def release_late_interaction_query_cache(self, query_keys: list[str]) -> None:
|
||||
release_fn = getattr(
|
||||
self.model_runner, "release_late_interaction_query_cache", None
|
||||
)
|
||||
if callable(release_fn):
|
||||
release_fn(query_keys)
|
||||
|
||||
def get_model(self) -> nn.Module:
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
Reference in New Issue
Block a user