flutter_gemma_litertlm

LiteRT-LM (.litertlm) on-device inference engine for flutter_gemma via dart:ffi (5 native platforms) + web. Opt-in InferenceEngineProvider. Also ships the LiteRT C API embedding backend (LiteRtEmbeddingBackend).

1.5.2 13K downloads/mo #2600 most downloaded on pub.dev DenisovAV/flutter_gemma

What this package is like to depend on

Last release 3 days ago

20 Aug 2026

Ships fairly regularly

a new release about every 2 weeks

Nearly every release is documented

notes for 15 of 15 stable releases

Nothing withdrawn

no release was ever pulled

2 months old

16 releases · first in 2026

16 releases in the last 12 months

see the full history below

Release timeline

16 releases · Jun 2026 to Aug 2026

Release Pre-release

Releases

latest 16

1.5.2 20 Aug 2026
Release notes
- Android: embeddings no longer poison the loader, fixing zero-chunk streams and SIGABRT (#447).
Open source →
1.5.1 20 Aug 2026
Release notes
- Share the host-side native library lookup with core instead of a private copy.
Open source →
1.5.0 19 Aug 2026
Release notes
- Add LiteRT embedding forward-pass + LiteRtEmbeddingBackend (moved from flutter_gemma_embeddings).
- internal: wire the new tokenizerFactory descriptor field; byte-identical vectors, no API change.
Open source →
1.4.2 16 Aug 2026
Release notes
- fix: vision + audio encoders default to CPU (fixes GPU vision hard-fail on Metal/WebGPU); overridable.
Open source →
1.4.1 15 Aug 2026
Release notes
- Fix Windows NPU: the OpenVino compiler DLLs shipped but were never bundled into the app.
- Drop the debug TBB variants that were being bundled alongside the release set.
Open source →
1.4.0 15 Aug 2026
Release notes
- Migrate to LiteRT-LM v0.16.0 (native-v0.16.0) — fixes the Android OpenCL per-turn leak (#348, #402).
- Detect the stream-callback ABI at runtime — v0.15.0 changed it with no compat path.
- Fix Windows discrete GPU: a Bazel define we passed had been removed upstream.
- Rebuild both NPU dispatch stacks from the pin instead of shipping stale prebuilts.
- Pin the macOS deployment target of libStreamProxy.dylib to 11.0 instead of the build host's.
- Native platforms only — web stays on @litert-lm/core 0.14.0 (the 0.16.0 npm publish ships no dist/).
Open source →
1.3.1 28 Jul 2026
Release notes
- Clearer engine-create error for GPU-only .litertlm models run on CPU (#390).
Open source →
1.3.0 26 Jul 2026
Release notes
- Also expose the LiteRt interpreter (LiteRtBindings) for embeddings/speech; own web litert.js.
Open source →
1.2.0 23 Jul 2026
Release notes
- 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.
Open source →
1.1.0 13 Jul 2026
Release notes
- Smooth UI during Android GPU prefill — flush the OpenCL queue every 2 ops (#364).
Open source →
1.0.4 13 Jul 2026
Release notes
- Guard native cancel against a freed conversation — fixes a use-after-free SIGSEGV on close-mid-stream (#379).
Open source →
1.0.3 12 Jul 2026
Release notes
- 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).
Open source →
1.0.2 20 Jun 2026
Release notes
- 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.
Open source →
1.0.1 19 Jun 2026
Release notes
- 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.
Open source →
1.0.0 16 Jun 2026
Release notes
- Stable 1.0.0; spec imports redirected off the dart:io mobile lib for a wasm-clean web graph.
Open source →
1.0.0-rc.1 10 Jun 2026 pre-release
Release notes
- 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).
Open source →

flutter_gemma_litertlm

What this package is like to depend on

Release timeline

Releases

Every package, every release, already written down.