NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
pub.dev · #3059 most downloaded on pub.dev
LiteRT (formerly TensorFlow Lite) Flutter plugin. Drop-in on-device ML inference with bundled native libraries for supported native platforms and web runtimes.
Last release 9 days ago
28 Sep 2026
Release timing varies
gaps range from 8 days to 2 months
Nearly every release is documented
notes for 60 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
7 months old
88 releases · first in 2026
One column per month.
Add shared ML utility functions
sigmoid, sigmoidClipped, clip, clamp01, argSortDesc, median, normalizeRadians (math utilities)iouXYXY, nms (non-maximum suppression)computeLetterboxParams, computeAspectPadParams, LetterboxParams, AspectPadParams (image preprocessing)bgrBytesToRgbFloat32, bgrBytesToSignedFloat32, fillNHWC4DFromBgrBytes (image-to-tensor conversion)allocTensorShape, createOutputBuffers, zeroOutputBuffers, createNHWCTensor4D, fillNHWC4D, flattenDynamicTensor (tensor allocation)decodeDetectionOutputs, transpose2D, concat0, ensure2D, xywhToXyxy (model output decoding)postProcessDetections, Detection, decodeAndSplitOutputs (end-to-end detection post-processing with NMS)Fix package layout to follow Pub conventions
Add PerformanceConfig and PerformanceMode,
PerformanceConfig and PerformanceMode,InterpreterFactory and InterpreterPoolgenerateAnchors() and SSDAnchorOptionsscaleFromLetterbox() utility for letterbox-to-original coordinate mappingAdd SignatureRunner for on-device training workflows (train, infer, get_weights, set_weights signatures)
SignatureRunner for on-device training workflows (train, infer, get_weights, set_weights signatures)flutter_litert_flex (Linux x86_64, built from TF 2.20.0 source). All three desktop platforms (macOS, Windows, Linux) now fully support on-device training with SELECT_TF_OPS models and checkpoint save/restore.Interpreter.signatureCount, signatureKeys, getSignatureKey(), getSignatureRunner()SignatureRunner.cancel(), getInputTensors(), getOutputTensors(), lastNativeInferenceDurationMicroSecondsAdd native dylibs to SPM Package.swift
Improve Custom Ops documentation
Upgrade Linux TFLite native library from 2.9.3 to 2.20.0 (built from source via CMake + Ninja + GCC x86_64)
tflite_flutterexample directory for a working example (the binary segmentation model selfie_segmenter.tflite uses custom ops)web_example directory for a working example* Update dependencies
* Update documentation
* Web support (experimental)
* Register iOS pluginClass
Add missing null check in interpreter teardown path on macOS
Improve IsolateInterpreter shutdown reliability on iOS to prevent rare use-after-free when closing during active inference
Add Swift Package Manager (SPM) support for iOS and macOS
Upgrade Windows TFLite native library from 2.18.0 to 2.20.0 (built from source via CMake + Ninja + MSVC x64)
Fix iOS: download xcframeworks at pod install time so static linking works on first build
Fix macOS: bundle native libraries in pub package so flutter test works without manual setup
flutter test works without manual setupFix iOS and macOS podspec compatibility with Ruby 3.4+ (Prism parser)
Upgrade iOS TensorFlow Lite from 2.17.0 (CocoaPods) to 2.20.0 (built from source via Bazel)
* Improved documentation
Upgrade macOS TFLite native library from 2.17.1 to 2.20.0 (latest stable, universal binary: arm64 + x86_64)
TfLiteOperatorCreate now takes 4 params, TfLiteOperatorCreateWithData removed, new kTfLiteOutputShapeNotKnown status, new builtin ops)Upgrade macOS TFLite native library from 2.11.0 to 2.17.1 (universal binary: arm64 + x86_64)
TfLiteOperator API replacing TfLiteRegistrationExternal)Bundle libtensorflowlite_c-win.dll from flutter_litert Windows plugin instead of downstream packages
libtensorflowlite_c-win.dll from flutter_litert Windows plugin instead of downstream packagesFix Windows: build and bundle custom ops DLL (tflite_custom_ops.dll) for MediaPipe models
Fix Linux: build and bundle custom ops library (libtflite_custom_ops.so) so MediaPipe models with custom ops (e.g. selfie segmentation) work on Linux
* Update AndroidManifest.xml
Fix IsolateInterpreter thread-safety bug causing intermittent native crashes when hardware delegates are active
Initial release, forked from tflite_flutter_custom v1.2.5
Your coding agent can read these notes before it upgrades. Set up the MCP server →