chore(deps): bump flutter_gemma from 0.3.1 to 0.15.0

[dependabot]

Bumps flutter_gemma from 0.3.1 to 0.15.0.

Release notes

Sourced from flutter_gemma's releases.

Release v0.15.0

What's new in 0.15.0

• ⚡ MTP / speculative decoding for Gemma 4 — LiteRT-LM 0.11.0 enables Multi-Token Prediction on macOS / iOS / Android / Windows. New enableSpeculativeDecoding flag on getActiveModel() overrides the model default if needed.
• 🤖 Android NPU restored for .litertlm (regression fix from 0.14.0) — PreferredBackend.npu again drives Qualcomm QNN / Google Tensor / MediaTek dispatch libs through LiteRT-LM's Backend::NPU.
• 🖥️ Desktop NPU — PreferredBackend.npu accepted on macOS / Linux / Windows (#261). Same dispatch-lib requirement as Android.
• 🐧 Linux known limitation — pre-MTP Gemma 4 revision required until upstream fixes google-ai-edge/LiteRT-LM#2225. Workaround in README → Linux Setup.
• 🛠️ Hook native cache — marker-file based invalidation (.flutter_gemma_native_version) — bumps clean stale companion libs automatically.

See https://github.com/DenisovAV/flutter_gemma/blob/HEAD/CHANGELOG.md for full release notes.

native-v0.11.0-a

Native LiteRT-LM v0.11.0 (Multi-Token Prediction support).

Built from upstream tag v0.11.0 with patch_c_api.sh applied (set_max_num_images, set_litert_dispatch_lib_dir, 6-arg conversation_config_create, sampler params propagation, Apple gpu_registry dlopen path).

Apple builds: vtool minos 26.2 → 16.0 patch on libGemmaModelConstraintProvider.dylib (App Store ITMS-90208), -c opt --strip=always. Android: -Wl,-z,max-page-size=16384 (Google Play 16KB). Windows: MSVC /OPT:REF /OPT:ICF.

7 platforms: Android arm64, iOS arm64 device + sim, Linux x86_64 + arm64, macOS arm64, Windows x86_64.

Release v0.14.5

What's Changed

• 0.14.5: restore desktop tensorflowlite_c bundling via Native Assets by @​DenisovAV in DenisovAV/flutter_gemma#258

Full Changelog: DenisovAV/flutter_gemma@v0.14.4...v0.14.5

Release v0.14.4

What's Changed

• 0.14.4: fix macOS dylib loading on pub.dev (#255) + native lib size reduction by @​DenisovAV in DenisovAV/flutter_gemma#256
• 0.14.4: fix #250 modes 2 and 3 (asset install on desktop + android x86_64) by @​DenisovAV in DenisovAV/flutter_gemma#257

Full Changelog: DenisovAV/flutter_gemma@v0.14.3...v0.14.4

Native dylibs native-v0.10.2-b (size optimization)

native-v0.10.2-b — size optimization (-c opt --strip=always)

Same upstream LiteRT-LM v0.10.2 source as native-v0.10.2-a (iOS still on commit 5e0d86b for Metal accelerator ABI parity). The difference is build flags — all bazelisk build invocations now pass -c opt --strip=always (or MSVC equivalent /OPT:REF /OPT:ICF on Windows).

Aggregate size reductions vs native-v0.10.2-a:

Platform	Before	After	Δ
Android arm64 libLiteRtLm.so	53 MB	38 MB	-28%
macOS arm64 libLiteRtLm.dylib	49 MB	28 MB	-43%
iOS arm64 libLiteRtLm.dylib	51 MB	19 MB	-63%
iOS Sim arm64 libLiteRtLm.dylib	51 MB	19 MB	-63%

... (truncated)

Changelog

Sourced from flutter_gemma's changelog.

0.15.0

• LiteRT-LM 0.11.0: MTP-capable Gemma 4 + speculative decoding on macOS / iOS / Android / Windows.
• enableSpeculativeDecoding flag on getActiveModel() (null = model default; true/false to override).
• Restore Android NPU support for .litertlm (regression from 0.14.0): PreferredBackend.npu on Android .litertlm models routes through LiteRT-LM's Backend::NPU again — same as 0.13.x's Kotlin path before the FFI migration silently dropped it. Requires a Qualcomm QNN / Google Tensor / MediaTek dispatch lib on the device; without one, engine_create fails with a dispatch error. MediaPipe .task models still don't support NPU (MediaPipe SDK limitation, unchanged).
• PreferredBackend.npu on desktop (#261): macOS / Linux / Windows backend arm wired. Same dispatch-lib requirement as Android.
• Linux known limitation: post-MTP HF Gemma 4 revisions blocked upstream — libLiteRtWebGpuAccelerator.so segfaults during graph compile (filed google-ai-edge/LiteRT-LM#2225) and multi-signature vision encoder rejected by native (engine_create error). Workaround: pin pre-MTP HF revision 7fa1d78473894f7e736a21d920c3aa80f950c0db for Linux users. Other platforms unaffected.
• hook native cache: marker-file based invalidation (.flutter_gemma_native_version) — bumps clean stale companion libs automatically.

0.14.5

• Fix desktop embedding on pub.dev installs (#250 follow-up): tensorflowlite_c.{dll,so,dylib} now bundled via Native Assets — regression from 0.14.0 setup-script removal.

0.14.4

• Fix macOS dylib loading on pub.dev installs (#255).
• Fix fromAsset install on desktop (#250 mode 2).
• Fix Android x86_64 emulator crash on embedding init (#250 mode 3).
• Reduce native lib size: iOS -63%, macOS -43%, Android -28%, Linux -16-18%.

0.14.3

• Fix App Store ITMS-90208 rejection on iOS (#245): downgraded patched libGemmaModelConstraintProvider.dylib minos 26.2 → 14.0 to match the other companion dylibs.
• Fix Android Google Play 16KB page-size requirement (#253): rebuilt libLiteRtLm.so with -Wl,-z,max-page-size=16384.
• Fix Web RAG build pipeline (#251): cross-platform npm run build, bundles cache_api.js + LiteRT WASM into dist/, ships package.json + vite.config.js in pub tarball.

0.14.2

• Fix macOS install_name_tool failure (#247): dart run / build_runner / flutter test on a pure-Dart library aborted with larger updated load commands do not fit because upstream Apple companion dylibs lack -headerpad_max_install_names. Skip them from Native Assets on macOS and bundle via Podfile post_install instead.
• Fix Gemma 4 escape-token leakage in chat history (#248): <|"|> tokens from tool_calls.arguments were written to history raw, making the model echo them on later turns. Strip recursively before persist via new SdkResponseParser.cleanRawForHistory.
• Fix modelFromAsset install on desktop (#250): the large_file_handler channel call threw MissingPluginException on macOS / Windows / Linux because the package only ships Android + iOS plugins. Now catches it and falls back to the in-memory loadAsset → writeFile path. Embedding (localagents-rag) and .litertlm FFI paths additionally fail fast with a typed message on non-arm64 Android (x86_64 emulator / armeabi-v7a) instead of a generic JVM crash — see new "Platform & Architecture Support" section in README.
• macOS Podfile setup (BREAKING for macOS app projects): app projects must update macos/Podfile post_install to the new snippet (see README → macOS Setup). iOS / Linux / Windows / Android unaffected.
• Perf debug logs: [*/perf] lines break out cost of dylib load, engine_create, prefill, decode — visible via debugPrint in both debug and release builds.

0.14.1

• Web build fix (#244): 0.14.0 broke web compilation by statically importing core/ffi/litert_lm_client.dart (which imports dart:ffi) through the flutter_gemma_interface.dart → mobile/flutter_gemma_mobile.dart chain. JS/Wasm targets cannot compile dart:ffi. Added conditional imports in mobile/flutter_gemma_mobile.dart that swap litert_lm_client.dart and ffi_inference_model.dart for *_stub.dart shims on dart.library.js_interop. The web plugin (FlutterGemmaWeb) registers itself as FlutterGemmaPlugin.instance before any FFI code path runs, so the stubs' constructors (which throw UnsupportedError) are never actually invoked on web.
• App Store fix (#245, ITMS-90432): 0.14.0 dropped lib*.dylib symlinks alongside the bundled .framework/ accelerators in Runner.app/Frameworks/ so LiteRT-LM's gpu_registry could dlopen them by basename — App Store Connect rejected those builds with "Unexpected file found in Frameworks". 0.14.1 patches the upstream LiteRT-LM source (runtime/components/sampler_factory.cc and litert/runtime/accelerators/gpu_registry.cc) to load Apple platform accelerators via @executable_path/../Frameworks/<X>.framework/<X> (macOS) / @executable_path/Frameworks/<X>.framework/<X> (iOS) instead of libX.dylib. Native Assets bundles the framework bundles correctly out of the box; no host-side Podfile symlinks needed. Patch applied during local Bazel rebuild — see native/litert_lm/patch_c_api.sh section 10.
• Gemma 4 native function calling: New ModelType.gemma4 routes tool definitions to LiteRT-LM SDK via litert_lm_conversation_config_set_tools (OpenAI Chat Completions JSON). SDK applies chat_template.jinja through minja, renders native <|tool>declaration:...<tool|> tokens, and parses the model's <|tool_call>...<tool_call|> response back into structured tool_calls JSON. flutter_gemma reads the result via SdkResponseParser.extractToolCalls (handles parallel calls and the multimodal content[] path) and returns FunctionCallResponse to the app — no Dart-side prompt engineering needed.
• Escape token cleanup: Strips leftover <|"|> Gemma 4 escape tokens from string arguments (recursively, including nested maps/lists).
• example/lib/models/model.dart: Gemma 4 E2B / E4B entries switched to modelType: ModelType.gemma4.

0.14.0

• Desktop FFI rewrite: macOS, Linux, Windows now run LiteRT-LM directly via dart:ffi against the C API. Removed Kotlin/JVM gRPC server, Azul Zulu JRE 24 download, and litertlm-server.jar bundling. Engine creation ~2 s (was ~10–15 s incl. JVM cold-start)
• iOS GPU acceleration: Metal delegate for .litertlm models on iPhone (Gemma 3 1B, Gemma 3n E2B, Gemma 4 E2B). Multimodal vision + audio work on device
• Linux + Windows GPU: WebGPU/Vulkan on Linux, WebGPU/DX12 on Windows; DXC runtime (dxil.dll + dxcompiler.dll v1.9.2602) bundled in the Windows native archive — no manual install required
• Android: drop Kotlin LiteRtLm dependency — .litertlm models on Android now go through the same Dart FFI path as desktop/iOS (was com.google.ai.edge.litertlm:litertlm-android AAR before). MediaPipe stays for .task/.bin models
• iOS Simulator: CPU-only — Metal sim has 256 MB single-allocation cap, LLM weight tensors exceed it
• Unified FFI client: All five platforms (Android, iOS, macOS, Linux, Windows) share LiteRtLmFfiClient (lib/core/ffi/)
• Native log capture: stream_proxy_redirect_stderr exposes glog/abseil output on iOS/Android via temp file; helps diagnose engine init failures
• Native prebuilts: Fetched at build time via hook/build.dart from GitHub release native-v0.10.2; SHA256-verified, bundled via Native Assets
• macOS / iOS setup: requires a small post_install block in your Podfile to symlink lib*.dylib next to the bundled .frameworks — gpu_registry calls dlopen by basename. See the macOS Setup section in README for the exact snippet (iOS works via the same pattern in example/ios/Podfile)

0.13.6

• ModelType.qwen3: New model type for Qwen3 models with thinking support
• Disable Qwen3 thinking at model level: /no_think appended automatically when isThinking: false — faster TTFT

... (truncated)

Commits

• See full diff in compare view

[dependabot]

Superseded by #100.