Stop after first EOS post-prompt (#2255)

Summary:
Pull Request resolved: #2255

Stop after first EOS post-prompt

Reviewed By: shoumikhin

Differential Revision: D54525365

Author: Michael Gschwind

examples/models/llama2/runner/runner.cpp

@@ -197,7 +197,6 @@ Error Runner::generate(
   int next; // will store the next token in the sequence
   int64_t pos = num_prompt_tokens - 1; // position in the sequence
   int token = prompt_tokens[pos]; // prefill starts from 0 to num_prompt_tokens
-  int eos_counter = 0; // counter to capture EOS
   int logits_index = 0; // index of the logits tensor in the output
   int k_cache_index = 0;
   int v_cache_index = 0;
@@ -340,13 +339,8 @@ Error Runner::generate(
 
     // data-dependent terminating condition: we have n_eos_ number of EOS
     if (pos >= num_prompt_tokens && next == eos_id_) {
-      eos_counter++;
-      if (eos_counter == n_eos_) {
-        ET_LOG(Info, "Reached to the end of generation");
-        break;
-      }
-    } else {
-      eos_counter = 0;
+      ET_LOG(Info, "Reached to the end of generation");
+      break;
     }
 
     token = next;

kernels/quantized/cpu/op_embedding.cpp

@@ -54,14 +54,12 @@ void check_embedding_byte_args(
     if (weight_scales.dim() == 2) {
       auto num_groups = weight_scales.size(1);
       auto remainder = weight.size(1) % num_groups;
-#if 0 // handle a partial last group
       ET_CHECK_MSG(
           remainder == 0,
           "Number of groups must divide weight.size(1)=%zd"
           ", but got # of groups = %zd",
           weight.size(1),
           num_groups);
-#endif // handle a partial last group
     }
   }