@@ -151,7 +151,8 @@ std::vector<Token> greedy_decode_executorch(
151151 int64_t blank_id,
152152 int64_t num_rnn_layers = 2 ,
153153 int64_t pred_hidden = 640 ,
154- int64_t max_symbols_per_step = 10 ) {
154+ int64_t max_symbols_per_step = 10 ,
155+ ::executorch::extension::llm::Stats* stats = nullptr ) {
155156 std::vector<Token> hypothesis;
156157
157158 // Shape: [1, T, joint_hidden]
@@ -289,6 +290,9 @@ std::vector<Token> greedy_decode_executorch(
289290 t += std::max (dur, static_cast <int64_t >(1 ));
290291 symbols_on_frame = 0 ;
291292 } else {
293+ if (hypothesis.empty () && stats) {
294+ stats->first_token_ms = ::executorch::extension::llm::time_in_ms ();
295+ }
292296 hypothesis.push_back ({static_cast <TokenId>(k), t, dur});
293297
294298 std::vector<int64_t > token_data = {k};
@@ -367,6 +371,19 @@ int main(int argc, char** argv) {
367371 ET_LOG (Error, " Failed to load model." );
368372 return 1 ;
369373 }
374+
375+ // Load all methods upfront so model_load_time captures the real cost.
376+ // With Mmap load mode, model->load() only sets up memory mappings;
377+ // the actual data is paged in lazily when methods are first loaded.
378+ const std::vector<std::string> required_methods = {
379+ " preprocessor" , " encoder" , " decoder_step" , " joint" };
380+ for (const auto & method : required_methods) {
381+ auto method_load_error = model->load_method (method);
382+ if (method_load_error != Error::Ok) {
383+ ET_LOG (Error, " Failed to load method: %s" , method.c_str ());
384+ return 1 ;
385+ }
386+ }
370387 stats.model_load_end_ms = ::executorch::extension::llm::time_in_ms ();
371388 stats.inference_start_ms = ::executorch::extension::llm::time_in_ms ();
372389
@@ -420,8 +437,6 @@ int main(int argc, char** argv) {
420437 return 1 ;
421438 }
422439 stats.prompt_eval_end_ms = ::executorch::extension::llm::time_in_ms ();
423- stats.first_token_ms =
424- stats.prompt_eval_end_ms ; // For ASR, first token is at end of encoding
425440
426441 auto & enc_outputs = enc_result.get ();
427442 auto f_proj = enc_outputs[0 ].toTensor (); // [B, T, joint_hidden]
@@ -478,7 +493,14 @@ int main(int argc, char** argv) {
478493
479494 ET_LOG (Info, " Running TDT greedy decode..." );
480495 auto decoded_tokens = greedy_decode_executorch (
481- *model, f_proj, encoded_len, blank_id, num_rnn_layers, pred_hidden);
496+ *model,
497+ f_proj,
498+ encoded_len,
499+ blank_id,
500+ num_rnn_layers,
501+ pred_hidden,
502+ 10 ,
503+ &stats);
482504
483505 ET_LOG (Info, " Decoded %zu tokens" , decoded_tokens.size ());
484506
0 commit comments