Fix QNN runner KV cache bitwidth detection in Android JNI

Summary:
The QNN runner in the Android JNI layer was hardcoded to use
Runner<uint16_t>, but models can be exported with either 8-bit or
16-bit KV caches. This mismatch caused the KV cache data to be
misinterpreted, resulting in gibberish output in the Android demo app
while the same model worked correctly via the CLI runner.

This change mirrors the dynamic KV bitwidth detection already present
in qnn_llama_runner.cpp by querying the model's get_kv_io_bit_width
method and instantiating the correct Runner<uint8_t> or
Runner<uint16_t> accordingly. Also passes temperature_ to the Runner
constructor which was previously omitted.

Fixes #18571
Closes #17622

Test Plan:
- Built Android AAR with QNN support (SDK 2.37) — jni_layer_llama.cpp
  compiles cleanly with both Runner<uint8_t> and Runner<uint16_t>
  template instantiations
- Unit tests pass (gradlew testDebugUnitTest)

Author: Abhinay Kukkadapu

extension/android/jni/jni_layer_llama.cpp

@@ -203,13 +203,41 @@ class ExecuTorchLlmJni : public facebook::jni::HybridClass<ExecuTorchLlmJni> {
               data_files_vector,
               cpp_load_mode);
       std::string decoder_model = "llama3"; // use llama3 for now
-      runner_ = std::make_unique<example::Runner<uint16_t>>( // QNN runner
-          std::move(module),
-          decoder_model.c_str(),
-          model_path->toStdString().c_str(),
-          tokenizer_path->toStdString().c_str(),
-          "",
-          "");
+      // Using 8bit as default since this meta is introduced with 16bit kv io
+      // support and older models only have 8bit kv io.
+      example::KvBitWidth kv_bitwidth = example::KvBitWidth::kWidth8;
+      if (module->method_names()->count("get_kv_io_bit_width") > 0) {
+        kv_bitwidth = static_cast<example::KvBitWidth>(
+            module->get("get_kv_io_bit_width")
+                .get()
+                .toScalar()
+                .to<int64_t>());
+      }
+
+      if (kv_bitwidth == example::KvBitWidth::kWidth8) {
+        runner_ = std::make_unique<example::Runner<uint8_t>>(
+            std::move(module),
+            decoder_model.c_str(),
+            model_path->toStdString().c_str(),
+            tokenizer_path->toStdString().c_str(),
+            "",
+            "",
+            temperature_);
+      } else if (kv_bitwidth == example::KvBitWidth::kWidth16) {
+        runner_ = std::make_unique<example::Runner<uint16_t>>(
+            std::move(module),
+            decoder_model.c_str(),
+            model_path->toStdString().c_str(),
+            tokenizer_path->toStdString().c_str(),
+            "",
+            "",
+            temperature_);
+      } else {
+        ET_CHECK_MSG(
+            false,
+            "Unsupported kv bitwidth: %ld",
+            static_cast<int64_t>(kv_bitwidth));
+      }
       model_type_category_ = MODEL_TYPE_CATEGORY_LLM;
 #endif
 #if defined(EXECUTORCH_BUILD_MEDIATEK)