flutter_gemma_litertlm 1.3.1

LiteRT-LM (.litertlm) on-device inference engine for flutter_gemma via dart:ffi (5 native platforms) + web. Opt-in InferenceEngineProvider.

1.3.1

• Clearer engine-create error for GPU-only .litertlm models run on CPU (#390).

1.3.0

• Also expose the LiteRt interpreter (LiteRtBindings) for embeddings/speech; own web litert.js.

1.2.0

• Migrate FFI to LiteRT-LM v0.14.0 — native per-session sampler (opaque session-config); native-v0.14.0.
• Fix #214 GPU output garbage via the v0.14.0 runtime — verified on Xclipse.
• Bump web @litert-lm/core 0.12.1 → 0.14.0 (text path; API-compatible).
• Known regression: Windows discrete GPU broken upstream (LiteRT-LM #2957) — use CPU/NPU on Windows.

1.1.0

• Smooth UI during Android GPU prefill — flush the OpenCL queue every 2 ops (#364).

1.0.4

• Guard native cancel against a freed conversation — fixes a use-after-free SIGSEGV on close-mid-stream (#379).

1.0.3

• Create the native conversation off the main isolate to avoid ANRs on multimodal models (#365).
• Serialize native conversation create on the engine mutex to prevent a heap-corrupting race (#372).
• Cancel native decode before tearing a conversation down to avoid a multi-second ANR (#364, #373).

1.0.2

• Clamp maxTokens up to 1024 (min context for .litertlm) to fix the DYNAMIC_UPDATE_SLICE crash (#318).
• Honor maxOutputTokens (session + chat) via native set_max_output_tokens; skipped on NPU.

1.0.1

• Fix PreferredBackend.npu on Android (Qualcomm) + Windows (Intel): native-v0.13.1-a restores the NPU dispatch libs omitted from 1.0.0 (#155).
• Point homepage to fluttergemma.dev. No code change.

1.0.0

• Stable 1.0.0; spec imports redirected off the dart:io mobile lib for a wasm-clean web graph.

1.0.0-rc.1

• Initial release: LiteRT-LM (.litertlm) on-device inference engine for flutter_gemma via dart:ffi.
• Provides LiteRtLmEngine (InferenceEngineProvider). Owns the shared LiteRT-LM native library.
• Android, iOS, macOS, Linux, Windows + web (@litert-lm/core, early preview).