[Bugfix] Fix DP Attention Padding in Dummy Run (#34187)

Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>

vllm/v1/worker/gpu_model_runner.py

@@ -4787,6 +4787,7 @@ class GPUModelRunner(
             pad_attn = cudagraph_runtime_mode == CUDAGraphMode.FULL
             attn_metadata, _ = self._build_attention_metadata(
                 num_tokens=num_tokens_unpadded,
+                num_tokens_padded=num_tokens_padded if pad_attn else None,
                 num_reqs=num_reqs_padded,
                 max_query_len=max_query_len,
                 ubatch_slices=ubatch_slices_padded if pad_attn else ubatch_slices,