Copie este prompt para o assistente de IA que você usa.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/google-ai-edge/litert-samples.Carregando o README do repositório…
Mostrando 12 de 12 skills coletadas.
Compiles LiteRT (.tflite) models ahead-of-time for Google Tensor TPUs (Tensor G5 on Pixel 10, Tensor G6 on Pixel 11) locally on Linux x86_64 or remotely via Google Colab (--colab on macOS, Windows, or ARM hosts), benchmarks them on a USB-attached Pixel with…
Idioma do texto original: inglês
Convert a Hugging Face LLM or vision-language model checkpoint into a .litertlm bundle that runs on the LiteRT-LM runtime with verified quality - classify the architecture against known runtime walls, pick the recipe family (dense, reasoning, hybrid SSM,…
Idioma do texto original: inglês
Prove a converted or quantized LiteRT model on the actual device via the CompiledModel API - confirm GPU residency, compare device output against the source model, and diagnose device-only failures such as silent CPU fallback, whole-graph compile ceilings,…
Idioma do texto original: inglês
Creates an Android app that runs an open text LLM on the device, on the CPU or the GPU, with the LiteRT-LM Kotlin API. LiteRT-LM is the recommended replacement for the MediaPipe LLM Inference API (com.google.mediapipe:tasks-genai), which is in…
Idioma do texto original: inglês
Say which models, backends and accelerators this app is running and how much memory the device has.
Idioma do texto original: inglês
Measure a LiteRT .tflite model with `benchmark_model` on Developer Device Platform (DDP) lab phones through `litert benchmark --ddp`, or on the Mac you run it from, and turn the session into rows of the performance leaderboard under benchmark/leaderboard -…
Idioma do texto original: inglês
Configures and implements LiteRT (.tflite) on-device inference on Android in Kotlin using the CompiledModel API on CPU and GPU. Use this skill for any Android LiteRT or .tflite task, including Gradle setup, image classification or vision/audio/embedding…
Idioma do texto original: inglês
Convert a PyTorch or Hugging Face model into a LiteRT model that runs fully on the GPU via the CompiledModel API with verified-correct output, and lay it out as a model recipe. Use when converting a new model, or when a converted model is rejected by the GPU,…
Idioma do texto original: inglês
Get the current local time, date and day of the week.
Idioma do texto original: inglês
Rapidly migrate an Android application from legacy TensorFlow Lite (TFLite) to the modern LiteRT CompiledModel API (2.x) in Open Source GitHub repositories, keeping the TensorFlow Lite Support Library as LiteRT Support (litert-support 2.3.0). Covers buffer…
Idioma do texto original: inglês
Build a new Android app (Kotlin, Compose) around a verified LiteRT model using the CompiledModel API - the app architecture, the inference-layer lifecycle rules, model delivery, and the UI traps that masquerade as model bugs. Use when turning a converted and…
Idioma do texto original: inglês
Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load,…
Idioma do texto original: inglês
Não foi possível carregar o README. Você ainda pode explorar os Skills do repositório abaixo.