diff --git a/src/h3_blackwell_runtime/qwen3vl_vision.py b/src/h3_blackwell_runtime/qwen3vl_vision.py
index cd7e26d..1d058c6 100644
--- a/src/h3_blackwell_runtime/qwen3vl_vision.py
+++ b/src/h3_blackwell_runtime/qwen3vl_vision.py
@@ -473,7 +473,7 @@ def build_fl2va_presentation(
             token_ids.append(int(tok))
 
     seq_len = len(token_ids)
-    input_ids = torch.tensor([int(t) for t in token_ids], dtype=torch.long, device=device)
+    input_ids = torch.tensor([int(t) for t in token_ids], dtype=torch.long, device=device).unsqueeze(0)  # [1, seq]
 
     # Build the Qwen hidden-state input: scaled token embeds, with the merged vision
     # rows spliced over the pad positions.