[Bugfix] Add missing encoder only guard for do_kv_cache_update (#33269)

Signed-off-by: Gregory Shtrasberg <[email protected]>

vllm/v1/attention/backends/triton_attn.py

@@ -572,6 +572,10 @@ class TritonAttentionImpl(AttentionImpl):
         kv_cache: torch.Tensor,
         slot_mapping: torch.Tensor,
     ):
+        if self.attn_type in (AttentionType.ENCODER_ONLY, AttentionType.ENCODER):
+            # For encoder attention,
+            # we use direct Q, K, V tensors without caching
+            return
         # For decoder and cross-attention, use KV cache as before
         key_cache, value_cache = kv_cache.unbind(1)