Improve warnings for qnn runner (#15716)

Author: abhinaykukkadapu

examples/qualcomm/oss_scripts/llama/runner/runner.cpp

@@ -378,7 +378,22 @@ Error Runner<T>::generate_from_prompt_or_file(
   stats_.inference_start_ms = time_in_ms();
 
   int32_t seq_len = config.seq_len;
-  seq_len = (seq_len > 0 && seq_len <= context_len_) ? seq_len : context_len_;
+  if (seq_len > context_len_) {
+    ET_LOG(
+        Info,
+        "Warning: Requested seq_len (%d) exceeds compiled max_seq_len (%d). Clamping to %d.",
+        seq_len,
+        context_len_,
+        context_len_);
+    seq_len = context_len_;
+  } else if (seq_len <= 0) {
+    ET_LOG(
+        Info,
+        "Warning: Invalid seq_len (%d). Using compiled max_seq_len (%d).",
+        seq_len,
+        context_len_);
+    seq_len = context_len_;
+  }
   int32_t n_bos = (cur_pos_ == 0) ? 1 : 0;
 
   // encode the (string) prompt into tokens sequence

examples/qualcomm/oss_scripts/llama/runner/token_generator.cpp

@@ -323,6 +323,30 @@ Result<int64_t> TokenGenerator<T>::generate(
       break;
     }
   }
+
+  // Check if generation was truncated due to seq_len limit (no EOS token)
+  if (eos_ids_->count(cur_token) == 0 && pos >= seq_len - 1) {
+    printf("\n");
+    ET_LOG(
+        Info,
+        "Warning: Generation stopped at seq_len limit (%d) without reaching EOS token. Response may be incomplete.",
+        seq_len);
+    if (seq_len >= metadata_.context_len) {
+      ET_LOG(
+          Info,
+          "- seq_len (%d) already equals compiled max_seq_len (%d). Consider recompiling with larger --max_seq_len.",
+          seq_len,
+          metadata_.context_len);
+    } else {
+      ET_LOG(
+          Info,
+          "- seq_len (%d) is less than compiled max_seq_len (%d). Consider increasing --seq_len (up to %d).",
+          seq_len,
+          metadata_.context_len,
+          metadata_.context_len);
+    }
+  }
+
   return pos - start_pos;
 }
 // Explicit instantiations