---
name: TensorFlow Lite Op Request
about: Use this template for reporting Lite ops you are using or missing
labels: 'comp:lite'

---

**System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
- TensorFlow installed from (source or binary):
- TensorFlow version (or github SHA if from source):


**Provide the text output from tflite_convert**

```
# Copy and paste here
```

        exclude:
          # exclude combos where all are empty.
          - ldap: ""
            etcd: ""
            openid: ""
          # exclude combos where both ldap and openid IDPs are specified.
          - ldap: "localhost:389"
            openid: "http://127.0.0.1:5556/dex"

    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-go@v5
        with:

    protected BadFuture(ListenableFuture<Integer> delegate) {
      super(delegate);
    }

    @Override
    public Integer get() {
      throw new RuntimeException("Oops");
    }
  }

    protected BadFuture(ListenableFuture<Integer> delegate) {
      super(delegate);
    }

    @Override
    public Integer get() {
      throw new RuntimeException("Oops");
    }
  }

		adminRouter.Methods(http.MethodPut).Path(adminVersion+"/set-user-status").HandlerFunc(adminMiddleware(adminAPI.SetUserStatus)).Queries("accessKey", "{accessKey:.*}").Queries("status", "{status:.*}")

		// Service accounts ops
		adminRouter.Methods(http.MethodPut).Path(adminVersion + "/add-service-account").HandlerFunc(adminMiddleware(adminAPI.AddServiceAccount))

					f, err := os.OpenFile(filePath, os.O_WRONLY|os.O_SYNC, 0)
					if err != nil {
						t.Fatalf("Failed to open %s: %s\n", filePath, err)
					}
					f.WriteString("oops") // Will cause bitrot error
					f.Close()
					break
				}
			}

			rQuorum := len(errs) - z.serverPools[0].sets[0].defaultParityCount

fi

pattern="$1"
if [ "$pattern" = "" ]; then
	pattern=.
fi

./make.bash || exit 1
GOROOT="$(cd .. && pwd)"

gettargets() {
	../bin/go tool dist list | sed -e 's|/|-|' |
		grep -E -v '^(android|ios)' # need C toolchain even for cross-compiling
	echo linux-arm-arm5
}

selectedtargets() {
	gettargets | grep -E "$pattern"
}

# put linux first in the target list to get all the architectures up front.

- Model produces wrong results and/or has lesser accuracy.
- Model produces correct results, but it is slower than expected.

### 4. (optional) RNN conversion support
If converting TF RNN to TFLite fused RNN ops, please prefix [RNN] in the title.

### 5. (optional) Any other info / logs

name: TensorFlow Lite Other Issue description: Use this template to report any
issue in TensorFlow Lite that is not about Converters, Play Services or Ops
body: - type: dropdown id: issue-type attributes: label: Issue Type description:
What type of issue would you like to report? multiple: false options: - Bug -
Build/Install - Performance - Support - Feature Request - Documentation Feature
Request - Documentation Bug - Others validations: required: true - type:

				}
			case testWriteTo:
				f := &testFile{ops: tf.ops}
				got, err := fr.WriteTo(f)
				if _, ok := err.(testError); ok {
					t.Errorf("test %d.%d, WriteTo(): %v", i, j, err)
				} else if got != tf.wantCnt || err != tf.wantErr {
					t.Errorf("test %d.%d, WriteTo() = (%d, %v), want (%d, %v)", i, j, got, err, tf.wantCnt, tf.wantErr)
				}
				if len(f.ops) > 0 {