[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

transformer_engine/common/fused_attn/utils.h

@@ -122,8 +122,7 @@ struct FADescriptor_v1 {
                     page_size_v, max_pages_per_seq_k, max_pages_per_seq_v, bias_b, bias_h,
                     attnScale, isTraining, dropoutProbability, layout, mask_type, softmax_type,
                     window_size_left, window_size_right, deterministic, bias_type, qkv_tensor_type,
-                    o_tensor_type, do_tensor_type, dqkv_tensor_type,
-                    generate_max_sum_exp) <
+                    o_tensor_type, do_tensor_type, dqkv_tensor_type, generate_max_sum_exp) <
            std::tie(rhs.b, rhs.h, rhs.hg, rhs.s_q, rhs.s_kv, rhs.d_qk, rhs.d_v, rhs.num_pages_k,
                     rhs.num_pages_v, rhs.page_size_k, rhs.page_size_v, rhs.max_pages_per_seq_k,
                     rhs.max_pages_per_seq_v, rhs.bias_b, rhs.bias_h, rhs.attnScale, rhs.isTraining,

transformer_engine/pytorch/cpp_extensions/fused_attn.py

@@ -323,7 +323,7 @@ def fused_attn_fwd(
     )
 
     if return_max_score:
-        qkv_format = qkv_layout.replace("3","").replace("2","").split("_")[0]
+        qkv_format = qkv_layout.replace("3", "").replace("2", "").split("_")[0]
         # thd:  output_tensors: out [tq, h, d],    Max [tq, h, 1],    Sum_Exp [tq, h, 1]
         # bshd: output_tensors: out [b, sq, h, d], Max [b, h, sq, 1], Sum_Exp [b, h, sq, 1]
         # sbhd: output_tensors: out [sq, b, h, d], Max [b, h, sq, 1], Sum_Exp [b, h, sq, 1]