google-ai-edge/LiteRT-CLI

آخر نشاط مصدر مسجل: ٢٩ سبتمبر ٢٠٢٦ في ٠٤:١٥

آخر تحديث لفهرس SkillsMP: ٥ نوفمبر ٢٠٢٦ في ١٩:٥٧

skills مجمعة: ١

نجوم GitHub: ٥٠
تفرعات GitHub: ١٠

التثبيت بمساعدة مساعد ذكي

انسخ هذا الطلب إلى المساعد الذكي الذي تستخدمه.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/google-ai-edge/LiteRT-CLI.

ملف README للمستودع

مصدر ملف README للمستودع: README.md

قراءة الملف الأصلي

عرض ملف README كاملًا

# LiteRT CLI (Preview) A convenient command-line toolkit to streamline [LiteRT](https://ai.google.dev/edge/litert) related development workflows, including converting, quantizing, compiling, running, benchmarking and visualizing LiteRT (TFLite) models on various hardware (CPU / GPU / NPU) across platforms (desktop, mobile, or cloud). 🚀 [Installation](#-installation) ｜ 📓 [Try Colab](https://github.com/google-ai-edge/LiteRT-CLI/blob/main/examples/litert_cli.ipynb) | ⚡ [LiteRT 101](https://codelabs.developers.google.com/codelabs/litert-cli/101) | ⚡ [Quick start](#-quick-start) | 💡 [Commands](#-common-commands) | 🤖 [Coding agent](#-use-in-coding-agent) > [!NOTE] > > It's still an early preview under active development, thus has limited > platform and feature support, plus possible bugs. We appreciate your patience > and feedback to help us improve it. Welcome issues and PRs! LiteRT CLI is built on top of [Google AI Edge](https://ai.google.dev/edge) stacks, including [LiteRT](https://github.com/google-ai-edge/LiteRT), [LiteRT-LM](https://github.com/google-ai-edge/LiteRT-LM), [LiteRT Torch](https://github.com/google-ai-edge/LiteRT-Torch), [LiteRT Quantizer](https://github.com/google-ai-edge/LiteRT/tree/main/litert_quantizer), [Developer Device Platform](https://docs.cloud.google.com/developer-device-platform/overview), and [Model Explorer](https://ai.google.dev/edge/model-explorer). -------------------------------------------------------------------------------- ## ⚙️ Build Status Build Type | Status ------------------------- | ------ Unit Tests (Linux, macOS) | [![](https://github.com/google-ai-edge/LiteRT-CLI/actions/workflows/nightly_unittests.yml/badge.svg?branch=main)](https://github.com/google-ai-edge/LiteRT-CLI/actions/workflows/nightly_unittests.yml) Nightly Release | [![](https://github.com/google-ai-edge/LiteRT-CLI/actions/workflows/nightly_release.yml/badge.svg?branch=main)](https://github.com/google-ai-edge/LiteRT-CLI/actions/workflows/nightly_release.yml) -------------------------------------------------------------------------------- ## 🚀 Installation Please install `litert-cli-nightly` from PyPI or from local clone. LiteRT CLI will install the dependencies on-demand, based on which commands to run, to speed up initial installation. LiteRT CLI requires Python 3.10 or newer, and is verified in Python 3.13. Support for Python 3.10 is deprecated (it prints a warning) and will be removed in the next release, following its upstream end-of-life, so please use Python 3.11 or newer. We support installation using either **[uv](https://docs.astral.sh/uv/getting-started/installation/)** (recommended for ultra-fast dependency resolution) or standard **[pip](https://pip.pypa.io/)** within a Python virtual environment. ### Option 1: Use uv (recommended) `uv` is an extremely fast Python package manager written in Rust. ```bash # 1. Create a virtual environment with Python 3.13. # TIP: Sometimes setting env var `UV_INDEX_URL=https://pypi.org/simple` helps # resolve dependency resolution errors, especially inside corporate networks. uv venv --clear --python=3.13 --seed source .venv/bin/activate # 2. Install the package into the active virtual environment uv pip install litert-cli-nightly # 3. Run help command litert --help ``` ### Option 2: Use standard pip ```bash python3 -m venv .venv source .venv/bin/activate pip install -q litert-cli-nightly litert --help ``` ### Option 3: Install from local clone (for development) ```bash uv venv --clear --python=3.13 --seed source .venv/bin/activate git clone git@github.com:google-ai-edge/LiteRT-CLI.git cd LiteRT-CLI uv pip install -e . ``` ### Stable vs nightly * `litert-cli-nightly` is built every night from `main`, and depends on the nightly LiteRT packages (e.g. `ai-edge-litert-nightly`, `litert-torch-nightly`). It gets new features and fixes first. * `litert-cli` is the stable release, and depends on pinned stable versions of the LiteRT packages. Both packages provide the same `litert` command, so install only one of them in a virtual environment; don't mix them (or their nightly and stable dependencies) in the same environment. -------------------------------------------------------------------------------- ## ⚡ Quick start ### 📓 Try Colab Try [LiteRT CLI Colab](https://github.com/google-ai-edge/LiteRT-CLI/blob/main/examples/litert_cli.ipynb) to explore different features quickly. ### 📓 LiteRT 101 [LiteRT 101](https://codelabs.developers.google.com/codelabs/litert-cli/101) is a hands-on tutorial that walks you through the basics of using the LiteRT CLI tool. ### Follow command help You can always follow `litert --help` or `litert {command} --help` to find how to use the CLI tool. Check [detailed instructions for each command](#-common-commands) below. ```bash # Run help command litert --help # Download a LiteRT model litert download --help litert download litert-community/efficientnet_b1 --file "*.tflite" --output efficientnet # Run and benchmark a LiteRT model on your devices litert run --help litert run efficientnet/efficientnet_b1.tflite --desktop --cpu litert benchmark --help litert benchmark efficientnet/efficientnet_b1.tflite --android --gpu ``` ### Run LLMs You can run LLMs like Gemma4-E2B, using commands like `litert lm run`, which forwards its arguments to the LiteRT-LM CLI (`litert-lm run`), and also accepts Hugging Face repo ids. Please follow [LiteRT-LM CLI](https://ai.google.dev/edge/litert-lm/cli) for detailed instructions, and [Run and benchmark LLMs](#7-run-and-benchmark-a-generative-llm-model-using-litert-lm-cli) for what `litert lm` adds. ```bash litert lm run \ --from-huggingface-repo=litert-community/gemma-4-E2B-it-litert-lm \ gemma-4-E2B-it.litertlm \ --prompt="What is the capital of France?" # A Hugging Face repo without a .litertlm file is converted once, then cached litert lm run Qwen/Qwen3-0.6B --prompt="What is the capital of France?" ``` ### 🌟 Quick demos Check comprehensive usage examples under the [examples/](https://github.com/google-ai-edge/LiteRT-CLI/tree/main/examples) directory, which contains per-command demos and model-specific demos. If you have cloned the repo, you can run the following commands to see the demos. Note: running all demos will take time and disk space. ```bash # Run all command demos ./examples/run_commands.sh # Run specific command demos ./examples/run_commands.sh download,benchmark # Run all model demos ./examples/run_models.sh # Run a specific model demo ./examples/run_models.sh efficientnet ``` ### 🤖 Use in coding agent Add the LiteRT CLI skill [`SKILL.md`](https://github.com/google-ai-edge/LiteRT-CLI/blob/main/.agents/skills/litert_cli/SKILL.md) into your coding agent (like [Google Antigravity](https://antigravity.google/)) and try prompts such as: * *Download LiteRT model `litert-community/efficientnet_b1` and run it on CPU* * *Benchmark LiteRT model `litert-community/efficientnet_b1` on my Android GPU* * *Compile LiteRT model `litert-community/efficientnet_b1` for NPU target `sm8750`* * *Visualize LiteRT model `litert-community/efficientnet_b1`* * *Download the FP32 model `litert-community/efficientnet_b1` , quantize it to INT8 dynamic range (`--recipe dynamic_wi8_afp32`), then benchmark both the original FP32 model and the newly quantized INT8 model on the GPU of my connected Android device. Compare the average latency and report the throughput speedup.* * *Convert the model `Qwen/Qwen3-0.6B` from HuggingFace, and run it locally using the prompt 'Explain edge machine learning one sentence'* * *Download EfficientNet from huggingface repo `litert-community/efficientnet_b1`, offline compile (AOT) the model for the `sm8750` target NPU, and output the compiled model into `./models/compiled`. Then, run an on-device inference and benchmark using this newly compiled AOT model on the connected Android device's NPU (`--npu`). Confirm that the graph loads directly without dynamic JIT compilation warmup latency.* The agent will automatically install the necessary tools, including Python virtual environments, `litert-cli-nightly`, and all required dependencies. -------------------------------------------------------------------------------- ### Verified platforms Verified in Python 3.13. * **Host Machines**: * Linux (Ubuntu) * macOS (Apple Silicon): don't support `litert compile` yet. * Windows: `litert compile` and `litert convert` not supported yet. * **Android**: * CPU, GPU * NPU: Qualcomm, MediaTek (soon), Google Tensor (soon) -------------------------------------------------------------------------------- ### Optional extras The dependencies of the heavier commands are installed on first use. To install them up front, e.g. for offline machines or CI, install the extras with the package (use `litert-cli[...]` for the stable package, or `.[...]` for a local clone): Extra | Installs dependencies for ------------- | ------------------------------------------------------------ `[convert]` | `litert convert` (LiteRT Torch, PyTorch, Transformers, ...) `[quantize]` | `litert quantize` (LiteRT Quantizer) `[compile]` | `litert compile` (NPU AOT compiler SDKs) `[lm]` | `litert lm` (LiteRT-LM) `[visualize]` | `litert visualize` (`ai-edge-model-explorer`) `[all]` | All extras ```bash uv pip install "litert-cli-nightly[convert,lm]" ``` ### Environment variables Variable | Description -------------------------------------------- | ----------- `LITERT_VERBOSE` | Set to `1` to enable verbose logging. `LITERT_GCP_PROJECT` | Default GCP project for `litert benchmark --ddp`, when `--gcp-project` is not set. `LITERT_GCP_BUCKET` | Default GCS bucket for `litert benchmark --ddp`, when `--gcp-bucket` is not set. Defaults to `<project>-devicerun`. `LITERT_DISABLE_MODEL_CACHES` | Set to `1` to make `litert benchmark` run `benchmark_model` once, without the XNNPACK and GPU caches. `DDP_LITERT_VERSION` | LiteRT release of the prebuilt `benchmark_model` used on DDP devices (default `2.2.0`; e.g. `nightly`). `DDP_LITERT_LM_VERSION`, `DDP_LITERT_LM_DIR` | Version (default `latest`), or a whole `gs://` directory, of the prebuilt LiteRT-LM benchmark binary used for `.litertlm` bundles on DDP devices. `LITERT_LM_MODELS_REF` | LiteRT-LM git ref (default `main`) to read the canonical model configs from in `litert convert`; set it to a commit for reproducible conversions. `LITERT_CLI_ROOT` | Local directory for downloaded NPU SDKs and runtime libraries (default `~/.cache/litert-cli/root`). `LITERT_CLI_ANDROID_ROOT` | Working directory on the Android device (default `/data/local/tmp/litert-cli`). `HF_TOKEN` | Hugging Face token for gated or private models (or run `hf auth login`). ### Troubleshooting and tips * Always activate python virtual environment before running `litert` command, to avoid conflicts. * When `uv` fails to resolve dependencies, try to set below environment variable first: `export UV_INDEX_URL=https://pypi.org/simple`. * When run fails on GPU using `--gpu` flag, try to add both `--gpu --cpu` flags in the command, then `litert run` will try GPU first, and fall back to CPU when GPU fails. With the `--npu`, `--gpu` and `--cpu` flags the order is always NPU, then GPU, then CPU, whatever order you pass them in; use `--accelerator gpu,cpu` to choose the order explicitly. * When `litert run` fails on Android device, if the device is not detected, try to run `adb kill-server` first. * When convert a traditional PyTorch model, you need to write a script to wrap it with required functions `get_model` and `get_args`. Check the script format in [resnet18.py](https://github.com/google-ai-edge/LiteRT-CLI/blob/main/litert_cli/test_data/resnet18.py). * `litert convert <hf_id>` supports Hugging Face `AutoModelForCausalLM` LLMs, plus these model families: * LLMs and VLMs: Gemma 3, Gemma 3n, Gemma 4, LFM2, LFM2-VL, Qwen3 and Qwen3.5. * Speech-to-text: Whisper, Moonshine, Parakeet (CTC and TDT) and Qwen3-ASR. * Text-to-speech: Kokoro and Qwen3-TTS. * Text-to-image: FLUX.2 [klein] and Bonsai FLUX.2. * Any-to-any: MiniCPM-o. Use `litert convert <hf_id> --dry-run` to see the export plan for a model. Other architectures can fail to export. * For large models like LLMs, `litert convert` will take large memories and disks, and spend multiple minutes. Please make sure you have enough memory and disks, and be patient. * `litert compile` only supports running on Linux now, and it requires newer Clang version `18.x.x` or above. Try `sudo apt install clang libc++-18-dev libc++abi-18-dev`. An error file that says `libc++.so.1: cannot open shared object file` means the LLVM C++ runtime is missing. * When benchmark using `--ddp` flag, you need to 1) Enable the Device Run API of [Developer Device Platform](https://docs.cloud.google.com/developer-device-platform/overview) in a GCP project with billing enabled (the platform is in Preview, and sessions are billed to your project); 2) Login using `gcloud auth application-default login`; 3) Set your GCP project using `--gcp-project=<Your-GCP-Project>`. The devices run the prebuilt `benchmark_model` of LiteRT 2.2.0; set the environment variable `DDP_LITERT_VERSION` (for example `nightly`) to pick another release. A `.litertlm` bundle runs LiteRT-LM's prebuilt benchmark binary from `gs://litert/binaries/latest/android_arm64/litert_lm/`, with the shared libraries of that directory pushed beside it; `DDP_LITERT_LM_VERSION` picks another version there, and `DDP_LITERT_LM_DIR` a whole `gs://` directory laid out the same way. * When `litert visualize` fails to launch Model Explorer, try to run `litert visualize --stop-all` first. * Exporting environment variable `LITERT_VERBOSE=1` can enable verbose logging. * `litert clean` deletes the whole local cache (`~/.cache/litert-cli`), including all managed models (see `litert list`), the bundles converted by `litert lm`, and the downloaded binaries, plus the LiteRT CLI directory on a connected Android device. It asks for confirmation; pass `-y` to skip it. Use it to free disk space, or as a last resort for issues like an NPU library version mismatch. -------------------------------------------------------------------------------- ## 💡 Common commands ### 1. Download a model from Hugging Face Hub ```bash # Download only .tflite files litert download litert-community/MobileNet-v3-large \ --file "*.tflite" \ --output mobilenet # Download full repository litert download litert-community/MobileNet-v3-large \ --output mobilenet_full # Download models using Hugging Face ID (uses HF ID as model reference too) litert download litert-community/MobileNet-v3-large # Download models with custom model reference litert download litert-community/MobileNet-v3-large --model-ref my_model_ref ``` ### 2. Convert a PyTorch model into a LiteRT model ```bash # Automated HF Conversion (LLMs, VLMs, speech-to-text, text-to-speech, text-to-image, any-to-any) litert convert Qwen/Qwen3-0.6B --output /tmp/qwen litert convert google/gemma-4-E2B-it --output /tmp/gemma4 litert convert openai/whisper-tiny --output /tmp/whisper # Print the resolved export plan without exporting litert convert Qwen/Qwen3-1.7B --dry-run # Override recommended export settings litert convert Qwen/Qwen3-1.7B --quantize dynamic_wi4b32_afp32 \ --prefill-lengths 128,512 --cache-length 4096 --output /tmp/qwen_w4 # Explicitly select the export task (e.g. text-only export of a multimodal model) litert convert google/gemma-4-E2B-it --task text_generation --output /tmp/gemma4_text # Generic Script Injection with INT8 Dynamic Quantization litert convert my_model.py --quantize-recipe dynamic_wi8_afp32 --output /tmp/mymodel # Use a custom LlmMetadata (chat template, stop tokens) for the .litertlm bundle litert convert Qwen/Qwen3-1.7B --llm-metadata my_metadata.pbtext --output /tmp/qwen3 # Export a Hugging Face model for NPU (uncompiled, no AOT compilation) litert convert Qwen/Qwen3-0.6B --target npu:qualcomm --output /tmp/qwen_npu # AOT compile a PyTorch script model for Qualcomm SM8750 and SM8650 NPUs litert convert my_model.py --target sm8750 --target sm8650 --output /tmp/mymodel_npu ``` `litert convert` has two modes, picked from `MODEL_OR_SCRIPT`: * **Hugging Face mode** (a Hugging Face model id or a local checkpoint directory): `--target` takes a single hardware target: `cpu_gpu` (default), `cpu`, `gpu`, `npu`, or `npu:<vendor>` (e.g. `npu:qualcomm`). The NPU targets export a model for NPU without AOT compilation. `--dry-run` prints the resolved export plan (task, target and export settings) and exits. `--task` selects the export task (`auto` by default, which detects it from the checkpoint; or `text_generation`, `image_text_to_text`, `multimodal_lm`, `automatic_speech_recognition`, `text_to_speech`, `text_to_image`, `any_to_any`). * **Script mode** (a `.py` file): `--target` takes NPU SoC codenames (e.g. `sm8750`), can be repeated, and AOT-compiles the converted model for each of them. `--export-aipack <dir>` (script mode only, with `--target`) exports an AI Pack instead. For models with a canonical config in [LiteRT-LM `models/<family>`](https://github.com/google-ai-edge/LiteRT-LM/tree/main/models), such as Qwen2.5, Qwen3, Qwen3.5, LFM2 and MiniCPM5, `litert convert` tries to reuse that config. * Gated Hugging Face models (e.g. `google/gemma-3-1b-it`) need you to accept their license on Hugging Face and log in first: `hf auth login`, or set `HF_TOKEN`. * `litert lm run` and `litert lm benchmark` run LLMs only, not other models such as ASR. ### 3. Quantize a LiteRT model ```bash # Dynamic INT8 Quantization (Default) litert quantize model.tflite \ --recipe dynamic_wi8_afp32 \ --output dynamic.tflite # Weight-Only Quantization litert quantize model.tflite \ --recipe weight_only_wi8_afp32 \ --output weight_only.tflite # Static W8A8 Quantization (with calibration data) litert quantize model.tflite \ --recipe static_wi8_ai8 \ --calibration-data calib_data.py \ --output static.tflite # Custom Recipe litert quantize model.tflite \ --custom-recipe quantize_recipe.json \ --output custom_quant.tflite ``` ### 4. AOT Compile a LiteRT model for NPU > [!NOTE] > > Currently only support on Linux hosts and Qualcomm NPUs, and other NPU > supports are coming soon! ```bash # Basic compilation for specific Qualcomm NPU (e.g., sm8750), which writes # model_Qualcomm_SM8750.tflite into the current directory (or --output-dir) litert compile model.tflite --target sm8750 # Compile for multiple targets and export an AI Pack for Android litert compile model.tflite --target sm8750 --target sm8650 --export-aipack my_npu_models ``` The `--export-aipack` directory must be new or empty; the CLI never deletes an existing directory, so remove a previous AI Pack yourself before re-exporting. ### 5. Run a LiteRT model on desktop or Android ```bash # Run locally on desktop (CPU) litert run model.tflite --desktop --cpu litert run my_model_ref --desktop --cpu # Run with GPU acceleration and CPU fallback (multi-accelerator) litert run model.tflite --gpu --cpu litert run model.tflite --accelerator gpu,cpu # Run on connected Android device litert run model.tflite --android # Run on connected Android device with NPU acceleration and CPU fallback litert run model.tflite --android --npu --cpu litert run model.tflite --android --accelerator npu,cpu # Run on connected Android device with NPU AOT-compiled model litert run model_Qualcomm_SM8750.tflite --android --npu # Run multiple iterations and print output tensors litert run model.tflite \ --iterations 5 \ --print-tensors # Run with custom input formats (supports image, raw binary, numpy array) litert run model.tflite \ --input "image.png" \ --print-tensors ``` ### 6. Benchmark a LiteRT model ```bash # On the CPU and the GPU (--android, --desktop, --ddp), benchmark_model runs twice: a first process # compiles the model and writes the XNNPACK and GPU caches (no inference), then the measured process # reads them and reports the peak memory too. The GPU cache needs a benchmark_model with # --gpu_serialization_dir: the nightly binaries have it, 2.2.0 does not. If a process with the cache # flags fails, benchmark_model runs once without them, as before, and the report says so; # LITERT_DISABLE_MODEL_CACHES=1 runs it once from the start. # Without --desktop or --ddp, litert benchmark runs on a connected Android device. # Benchmark on Android (CPU side) litert benchmark my_model_ref --android --cpu litert benchmark model.tflite --android --cpu # Benchmark on Android NPU (JIT mode) litert benchmark model.tflite --android --npu # Benchmark AOT compiled model on Android NPU litert benchmark model_Qualcomm_SM8750.tflite --android --npu # Benchmark on Android GPU litert benchmark model.tflite --android --gpu # Benchmark on macOS (CPU) litert benchmark my_model_ref --desktop --cpu # Benchmark on Developer Device Platform (DDP) devices in Google Cloud. Prerequisites: # - Enable the Device Run API in your GCP project: gcloud services enable devicerun.googleapis.com # - Set up authentication by running: gcloud auth application-default login # - Find device ids by running: gcloud beta device-run devices list --project "your-gcp-project-id" litert benchmark model.tflite --ddp --gcp-project "your-gcp-project-id" litert benchmark model.tflite --ddp --device grizzly-37 --gcp-project "your-gcp-project-id" litert benchmark model.tflite --ddp --devices "grizzly-37, pa3q-35" --gpu --gcp-project "your-gcp-project-id" # A .litertlm bundle on DDP devices runs LiteRT-LM's benchmark binary twice: a warm-up process (one # iteration, a cold Init) writes the caches beside the bundle, then the measured process loads them and # runs --num-iterations times (default 5) at --prefill-tokens / --decode-tokens (default 1024 / 256). # The printed medians leave out its first --warmup-runs iterations (default 1); the summary also shows # both Init times and the peak memory. litert benchmark model.litertlm --ddp --device grizzly-37 --gpu --gcp-project "your-gcp-project-id" ``` ### 7. Run and benchmark a generative LLM model using LiteRT-LM CLI `litert lm` forwards its arguments to `litert-lm` (the `lm` extra is installed on first use), so `litert lm run ./my_model.litertlm` and `litert-lm run ./my_model.litertlm` achieve the same results. On top of that, `litert lm run` and `litert lm benchmark` also accept a Hugging Face repo id (see below), and read the `--quantize`, `--prefill-lengths`, `--cache-length` and `--reconvert` conversion options themselves. `litert lm --help` prints a short note about these before the native `litert-lm` help. Please follow the [LiteRT-LM CLI guide](https://ai.google.dev/edge/litert-lm/cli) for detailed instructions. ```bash # Run a generative LLM model, and load from hugging face litert lm run \ --from-huggingface-repo=litert-community/gemma-4-E2B-it-litert-lm \ gemma-4-E2B-it.litertlm \ --prompt="What is the capital of France?" # Or load from a local LLM model file litert lm run ./my_model.litertlm # Example with a custom prompt litert lm run ./my_model.litertlm --prompt "Hello, how are you?" # Benchmark a generative LLM model litert lm benchmark ./my_model.litertlm # Run or benchmark a Hugging Face repo by its id litert lm run Qwen/Qwen3-0.6B --prompt "What is the capital of France?" litert lm benchmark Qwen/Qwen3-0.6B # Convert with a longer KV cache (a second bundle), or rebuild the cached one litert lm run Qwen/Qwen3-0.6B --cache-length 8192 litert lm run Qwen/Qwen3-0.6B --reconvert ``` When the first argument after `run` or `benchmark` is a Hugging Face repo id (`org/name`) that is not a local path: * A repo with a `.litertlm` file runs with `--from-huggingface-repo org/name`. * A repo with a transformers checkpoint is converted once with `litert convert` (the `convert` extra is installed on first use) into `~/.cache/litert-cli/models/<org>__<name>/`, and later runs reuse the bundle. `litert lm` reads the conversion options and does not pass them to `litert-lm`: `--quantize` (default `dynamic_wi8_afp32`, `none` for fp32), `--prefill-lengths` (default `256`), `--cache-length` (default `4096`) and `--reconvert` (convert again even if a bundle is cached). ### 8. Visualize a model's architecture ```bash # Open in Model Explorer graph litert visualize model.tflite # Clean up and stop visualizer background servers litert visualize --stop-all ``` ### 9. Import a local model ```bash # Import a local file into the centralized cache litert import my_model.tflite --model-ref my_model # Import a directory and associate with a Hugging Face ID litert import ./my_model_dir --model-ref my_model --hf-id my_org_name/my_model ``` ### 10. List managed models ```bash # List all managed models litert list # Show detailed contents of a specific model using model reference. litert list my_model ``` ### 11. Delete a managed model ```bash # Delete a model from cache (asks for confirmation; -y skips it) litert delete my_model -y ``` ### 12. Clean up all caches ```bash # Delete the whole local cache, including all managed models (`litert list`) # and the bundles converted by `litert lm`, plus the LiteRT CLI directory on a # connected Android device. Asks for confirmation; -y skips it. litert clean ```

جارٍ تحميل ملف README للمستودع…

Skills في هذا المستودع

التصنيف قيد الانتظار

skill

المهنة

الوصف

آخر تحديث

litert-cli

غير مصنف

LiteRT CLI tool to download, convert, quantize, run, benchmark, and visualize LiteRT models.

لغة النص الأصلي: الإنجليزية

2026-09-29

عرض ١ من أصل ١ skills مجمعة.