[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475)
Signed-off-by: Roger Wang <hey@rogerw.io> Co-authored-by: Sun Kim <sunytokki@gmail.com>
This commit is contained in:
@@ -144,7 +144,7 @@ class ECExampleConnector(ECConnectorBase):
|
||||
Update ECConnector state after encoder cache allocation.
|
||||
"""
|
||||
mm_hash = request.mm_features[index].identifier
|
||||
num_encoder_token = request.get_num_encoder_tokens(index)
|
||||
num_encoder_token = request.get_num_encoder_embeds(index)
|
||||
# Insert mm_hash only if this block has not been recorded yet.
|
||||
self._mm_datas_need_loads[mm_hash] = num_encoder_token
|
||||
|
||||
|
||||
Reference in New Issue
Block a user