labels: 'TFLiteConverter'

---

### 1. System information

- OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
- TensorFlow installation (pip package or built from source):
- TensorFlow library (version, if pip package or github SHA, if built from source):

### 2. Code

Provide code to help us reproduce your issues using one of the following options:

#### Option A: Reference colab notebooks

      - name: Checkout repository for releases (skipped for nightly)
        if: ${{ github.event_name == 'push' }}
        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
      - name: Build and test pip wheel
        shell: bash
        run: |
          is_nightly=0 && tf_project_name='tensorflow_cpu_aws' && ${{ github.event_name == 'schedule' }} && is_nightly=1 && tf_project_name='tf_nightly_cpu_aws'

    The `--no-cache-dir` option tells `pip` to not save the downloaded packages locally, as that is only if `pip` was going to be run again to install the same packages, but that's not the case when working with containers.

    /// note

    The `--no-cache-dir` is only related to `pip`, it has nothing to do with Docker or containers.

    ///

    The `--upgrade` option tells `pip` to upgrade the packages if they are already installed.

)
python.toolchain(python_version = "3.10")
python.toolchain(python_version = "3.11")
python.toolchain(python_version = "3.12")
python.toolchain(python_version = "3.13")

pip = use_extension("@rules_python//python/extensions:pip.bzl", "pip")

[pip.parse(
    extra_hub_aliases = {
        "numpy": ["numpy_headers"],
    },
    hub_name = "tf_pypi",
    python_version = python_version,

        uses: actions/setup-java@v5
        with:
          distribution: 'temurin'
          java-version: 21

      - uses: actions/setup-python@v6
        with:
          python-version: 3.x

      - run: pip install mkdocs-material mkdocs-redirects

      - name: Generate Docs
        run: ./test_docs.sh

      - uses: actions/upload-artifact@v7
        with:
          name: docs

     * If error still persists then, apparently your CPU model does not support AVX instruction sets.
       * Refer [hardware requirements](https://www.tensorflow.org/install/pip#hardware-requirements).
   
   -----------------------------------------------------------------------------------------------
   
   **2. Installing **TensorFlow** (TF) CPU prebuilt binaries**
   
   

# For wheel verification, and uploading
auditwheel ~= 6.1.0
twine ~= 6.1.0
id
urllib3
requests

# For XLA
pyyaml

# For JAX
build ~= 1.2.2
# uv is faster than pip for installing Python packages.
uv ~= 0.5.30

# For running wheel verification script

    因為這個檔案不常變動，Docker 能偵測並在此步驟使用快取，也能啟用下一步的快取。

4. 安裝需求檔案中的套件相依。

    `--no-cache-dir` 選項告訴 `pip` 不要把下載的套件保存在本機，因為那只在 `pip` 之後還會再次安裝相同套件時才有用，而在使用容器時並非如此。

    /// note | 注意

    `--no-cache-dir` 只跟 `pip` 有關，與 Docker 或容器無關。

    ///

    `--upgrade` 選項告訴 `pip` 若套件已安裝則升級它們。

    因為前一步複製檔案可能被 Docker 快取偵測到，這一步也會在可用時使用 Docker 快取。

    在此步驟使用快取可以在開發期間反覆建置映像時，為你省下大量時間，而不必每次都重新下載並安裝所有相依。

However, if you use the `pip install fastapi` command, the `python-multipart` package is not included by default.

To install it manually, make sure you create a [virtual environment](../../virtual-environments.md), activate it, and then install it with:

```console
$ pip install python-multipart
```

Если вы не хотите включать опциональные зависимости `standard`, можно установить `pip install fastapi` вместо `pip install "fastapi[standard]"`.

### Без `fastapi-cloud-cli` { #without-fastapi-cloud-cli }

Если вы хотите установить FastAPI со стандартными зависимостями, но без `fastapi-cloud-cli`, установите `pip install "fastapi[standard-no-fastapi-cloud-cli]"`.