# CUDA WHEEL
test:linux_cuda_wheel_test_filters --test_tag_filters=gpu,requires-gpu,-no_gpu,-no_oss,-tf_tosa,-oss_excluded,-oss_serial,-benchmark-test,-no_cuda11,-no_oss_py38,-no_oss_py39,-no_oss_py310,-no_oss_py313
test:linux_cuda_wheel_test_filters --build_tag_filters=gpu,requires-gpu,-no_gpu,-no_oss,-tf_tosa,-oss_excluded,-oss_serial,-benchmark-test,-no_cuda11,-no_oss_py38,-no_oss_py39,-no_oss_py310,-no_oss_py313

        `XNNPACK` delegate automatically when the model has a `fp32` operation.
*   GPU
    *   Allow GPU acceleration starting with internal graph nodes
    *   Experimental support for quantized models with the Android GPU delegate
    *   Add GPU delegate whitelist.
    *   Rename GPU whitelist -> compatibility (list).
    *   Improve GPU compatibility list entries from crash reports.
*   NNAPI
    *   Set default value for

  // threadpool of GPU event mgr, as that can trigger more callbacks to be
  // scheduled on that same threadpool, causing a deadlock in cases where the
  // caller of event_mgr->ThenExecute() blocks on the completion of the callback
  // (as in the case of ConstOp kernel creation on GPU, which involves copying a
  // CPU tensor to GPU).

        with:
          api-level: ${{ matrix.api-level }}
          arch: ${{ matrix.api-level == '34' && 'x86_64' || 'x86' }}
          force-avd-creation: false
          emulator-options: -no-window -gpu swiftshader_indirect -noaudio -no-boot-anim -camera-back none
          disable-animations: false
          script: echo "Generated AVD snapshot for caching."

      - name: Run Tests

And then, right after the `yield`, we unload the model. This code will be executed **after** the application **finishes handling requests**, right before the *shutdown*. This could, for example, release resources like memory or a GPU.

/// tip

The `shutdown` would happen when you are **stopping** the application.

Maybe you need to start a new version, or you just got tired of running it. 🤷

///

)

config_setting(
    name = "with_xla_support",
    define_values = {"with_xla_support": "true"},
    visibility = ["//visibility:public"],
)

# By default, XLA GPU is compiled into tensorflow when building with
# --config=cuda even when `with_xla_support` is false. The config setting
# here allows us to override the behavior if needed.
config_setting(
    name = "no_xla_deps_in_cuda",

- sigs.k8s.io/kustomize/kyaml: v0.17.1 → v0.18.1
- sigs.k8s.io/structured-merge-diff/v4: v4.4.1 → v4.4.2

### Removed
- bazil.org/fuse: 371fbbd
- cloud.google.com/go/storage: v1.0.0
- dmitri.shuralyov.com/gpu/mtl: 666a987
- github.com/BurntSushi/xgb: [27f1227](https://github.com/BurntSushi/xgb/tree/27f1227)
- github.com/Microsoft/hcsshim: [v0.8.26](https://github.com/Microsoft/hcsshim/tree/v0.8.26)

- golang.org/x/lint: 1621716 → d0100b6
- honnef.co/go/tools: v0.0.1-2019.2.3 → ea95bdf

### Removed
- cloud.google.com/go/storage: v1.0.0
- dmitri.shuralyov.com/gpu/mtl: 666a987
- github.com/BurntSushi/xgb: [27f1227](https://github.com/BurntSushi/xgb/tree/27f1227)
- github.com/armon/go-metrics: [f0300d1](https://github.com/armon/go-metrics/tree/f0300d1)