react-native-litert-lm 0.3.0 → 0.3.1

package/README.md

@@ -448,8 +448,7 @@ const prompt = applyGemmaTemplate(
 | react-native-nitro-modules | 0.35.0+       |
 | Android API                | 26+ (ARM64)   |
 | iOS                        | 15.0+ (ARM64) |
-| LiteRT-LM Android SDK      | 0.9.0-alpha01 |
-| LiteRT-LM iOS Engine       | v0.9.0        |
+| LiteRT-LM Engine            | 0.9.0           |
 
 ## Platform Support
 

package/cpp/HybridLiteRTLM.cpp

@@ -18,6 +18,8 @@
 #include <chrono>
 #include <stdexcept>
 #include <sstream>
+#include <sys/stat.h>
+#include <cstdio>
 
 #ifdef __APPLE__
 #include "IOSDownloadHelper.h"
@@ -241,7 +243,7 @@ void HybridLiteRTLM::loadModelInternal(
       modelPath.c_str(),
       backend,
       visionBackend,
-      "cpu" // audio always on CPU
+      nullptr // audio executor not supported on iOS yet
     );
     if (!settings) {
       return false;
@@ -250,6 +252,10 @@ void HybridLiteRTLM::loadModelInternal(
     litert_lm_engine_settings_set_max_num_tokens(settings, static_cast<int>(maxTokens_));
     litert_lm_engine_settings_enable_benchmark(settings);
     
+    // Set cache directory to the same directory as the model file
+    std::string cacheDir = modelPath.substr(0, modelPath.find_last_of('/'));
+    litert_lm_engine_settings_set_cache_dir(settings, cacheDir.c_str());
+    
     engine_ = litert_lm_engine_create(settings);
     litert_lm_engine_settings_delete(settings);
     
@@ -275,9 +281,32 @@ void HybridLiteRTLM::loadModelInternal(
   }
   
   if (!engine_) {
+    // Collect diagnostic info
+    std::string diag = " | Diagnostics: ";
+    struct stat st;
+    if (stat(modelPath.c_str(), &st) == 0) {
+      diag += "File size: " + std::to_string(st.st_size) + " bytes";
+    } else {
+      diag += "Failed to stat file (errno: " + std::to_string(errno) + ")";
+    }
+    
+    FILE* f = fopen(modelPath.c_str(), "rb");
+    if (f) {
+      diag += ", Readable: YES";
+      fclose(f);
+    } else {
+      diag += ", Readable: NO (errno: " + std::to_string(errno) + ")";
+    }
+    
+    // Get the native error from the C API
+    const char* nativeErr = litert_lm_get_last_error();
+    if (nativeErr && nativeErr[0] != '\0') {
+      diag += " | Native error: " + std::string(nativeErr);
+    }
+
     throw std::runtime_error(
       "Failed to create LiteRT-LM engine. Tried backend '" +
-      std::string(primaryBackend) + "' and CPU fallback. Model path: " + modelPath);
+      std::string(primaryBackend) + "' and CPU fallback. Model path: " + modelPath + diag);
   }
   
   session_config_ = litert_lm_session_config_create();
@@ -484,7 +513,12 @@ std::string HybridLiteRTLM::sendMessageWithImageInternal(
     conversation_, msgJson.c_str(), nullptr);
   
   if (!response) {
-    throw std::runtime_error("LiteRT-LM: sendMessageWithImage failed");
+    std::string errMsg = "LiteRT-LM: sendMessageWithImage failed";
+    const char* nativeErr = litert_lm_get_last_error();
+    if (nativeErr && nativeErr[0] != '\0') {
+      errMsg += ": " + std::string(nativeErr);
+    }
+    throw std::runtime_error(errMsg);
   }
   
   const char* responseStr = litert_lm_json_response_get_string(response);

package/cpp/include/litert_lm_engine.h

@@ -232,11 +232,18 @@ LITERT_LM_C_API_EXPORT
 void litert_lm_engine_settings_set_num_decode_tokens(
     LiteRtLmEngineSettings* settings, int num_decode_tokens);
 
+// Returns the last error message from a failed C API call.
+// Returns an empty string if no error has occurred.
+// The returned pointer is valid until the next C API call on the same thread.
+LITERT_LM_C_API_EXPORT
+const char* litert_lm_get_last_error();
+
 // Creates a LiteRT LM Engine from the given settings. The caller is responsible
 // for destroying the engine using `litert_lm_engine_delete`.
 //
 // @param settings The engine settings.
 // @return A pointer to the created engine, or NULL on failure.
+//         Call litert_lm_get_last_error() for details on failure.
 LITERT_LM_C_API_EXPORT
 LiteRtLmEngine* litert_lm_engine_create(const LiteRtLmEngineSettings* settings);
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "react-native-litert-lm",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "High-performance LLM inference for React Native using LiteRT-LM. Optimized for Gemma 3n and other on-device language models.",
   "license": "MIT",
   "author": "Hugh Chen (https://github.com/hung-yueh)",

package/scripts/build-ios-engine.sh

@@ -57,6 +57,25 @@ fi
 
 LITERT_SRC="$BUILD_DIR/LiteRT-LM"
 
+# ---- 1b. Apply iOS-specific patches ---------------------------------------
+# These patches fix:
+# - mmap PROT_WRITE removal (iOS rejects CoW for large files)
+# - Error capture API (litert_lm_get_last_error)
+# - Engine registerer moved outside anonymous namespace (iOS linker stripping)
+# - Minijinja/Rust stub replacement (custom C++ prompt template)
+PATCHES_DIR="$PROJECT_ROOT/scripts/patches"
+if [ -d "$PATCHES_DIR" ]; then
+  for PATCH_FILE in "$PATCHES_DIR"/*.patch; do
+    if [ -f "$PATCH_FILE" ]; then
+      echo "   Applying patch: $(basename "$PATCH_FILE")..."
+      cd "$LITERT_SRC"
+      git apply --check "$PATCH_FILE" 2>/dev/null && \
+        git apply "$PATCH_FILE" || \
+        echo "   (patch already applied or conflicts, skipping)"
+    fi
+  done
+fi
+
 # ---- 2. Verify Bazel is available -----------------------------------------
 echo ""
 echo "==> Step 2: Checking Bazel..."