use correct total length to fix static kv_cache performance (#23615)

when using static kv_cache, past_sequence_length is the max sequence
length of kv_cache.
issue1: total_sequence_length will be larger than the cache entry
issue2: we do way more calculations that needed so things are noticeable
slower

onnxruntime/contrib_ops/webgpu/bert/attention.cc

@@ -439,7 +439,7 @@ Status ApplyAttention(const Tensor* Q, const Tensor* K, const Tensor* V, const T
                       WebgpuAttentionParameters& parameters, onnxruntime::webgpu::ComputeContext& context, const Tensor* seqlen_k) {
   const int output_count = std::min({context.OutputCount(), 1 + (past_key != nullptr ? 1 : 0) + (past_value != nullptr ? 1 : 0)});
   const int past_sequence_length = output_count > 1 ? parameters.past_sequence_length_ : 0;
-  const int total_sequence_length = past_sequence_length + parameters.kv_sequence_length_;
+  const int total_sequence_length = parameters.total_sequence_length_;
 
   const TensorShapeVector probs_dims({parameters.batch_size_, parameters.num_heads_,
                                       parameters.sequence_length_, total_sequence_length});