support the ppm for pyramid transformer

fairseq/modules/reduced_multihead_attention.py

@@ -204,7 +204,7 @@ class ReducedMultiheadAttention(nn.Module):
         q = self.q_proj(query)
         if self.self_attention:
             if self.sample_ratio > 1:
-                query_ = query.permute(1, 2, 0)    # bsz, dim, seq_len
+                query_ = query.permute(1, 2, 0)    # bsz, dim, seq_len:
                 query_ = self.sr(query_).permute(2, 0, 1)  # seq_len, bsz, dim
                 query = self.norm(query_)