Support encoder-only models without KV-Cache (#21270)

Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>

tests/v1/attention/utils.py

@@ -93,6 +93,7 @@ def create_common_attn_metadata(
         max_query_len=max_query_len,
         block_table_tensor=block_table_tensor,
         slot_mapping=slot_mapping,
+        causal=True,
     )