Hug ile birlikte (Hug zaten Falcon'a dayandığından) **FastAPI**'ın fonksiyonlarda `cevap` parametresi belirtmesinde ilham kaynağı oldu.

    FastAPI'da opsiyonel olmasına rağmen, daha çok header'lar, çerezler ve alternatif durum kodları belirlemede kullanılıyor.

### <a href="https://moltenframework.com/" class="external-link" target="_blank">Molten</a>

**FastAPI**'ı geliştirmenin ilk aşamalarında Molten'ı keşfettim. Pek çok ortak fikrimiz vardı:

  %213 = "tf.Mul"(%212, %12) {device = ""} : (tensor<i64>, tensor<1xi64>) -> tensor<1xi64>
  %214 = "tf.Tile"(%213, %211) {device = ""} : (tensor<1xi64>, tensor<1xi64>) -> tensor<?xi64>
  %215 = "tf.Cumsum"(%214, %14) {device = "", exclusive = false, reverse = false} : (tensor<?xi64>, tensor<i32>) -> tensor<?xi64>
  %216 = "tf.ConcatV2"(%11, %215, %3) {device = ""} : (tensor<1xi64>, tensor<?xi64>, tensor<i32>) -> tensor<?xi64>

  // CHECK: mhlo.constant dense<> : tensor<0xf32>
  %1 = "tf.Cumsum"(%arg0, %0) : (tensor<0xf32>, tensor<i32>) -> tensor<0xf32>
  func.return %1 : tensor<0xf32>
}

// -----

// CHECK-LABEL: func @cumsum_dynamic
func.func @cumsum_dynamic(%arg0: tensor<?xf32>, %arg1: tensor<i32>) -> tensor<?xf32> {
  // CHECK: "tf.Cumsum"
  %0 = "tf.Cumsum"(%arg0, %arg1) : (tensor<?xf32>, tensor<i32>) -> tensor<?xf32>

  NON_MAX_SUPPRESSION_V4 = 120,
  NON_MAX_SUPPRESSION_V5 = 121,
  SCATTER_ND = 122,
  SELECT_V2 = 123,
  DENSIFY = 124,
  SEGMENT_SUM = 125,
  BATCH_MATMUL = 126,
  PLACEHOLDER_FOR_GREATER_OP_CODES = 127,
  CUMSUM = 128,
  CALL_ONCE = 129,
  BROADCAST_TO = 130,
  RFFT2D = 131,
  CONV_3D = 132,
  IMAG=133,
  REAL=134,
  COMPLEX_ABS=135,
  HASHTABLE = 136,
  HASHTABLE_FIND = 137,
  HASHTABLE_IMPORT = 138,

      "Conv2D",
      "Conv2DBackpropFilter",
      "Conv2DBackpropInput",
      "Conv3D",
      "Conv3DBackpropFilterV2",
      "Conv3DBackpropInputV2",
      "Cross",
      "Cumprod",
      "Cumsum",
      "CumulativeLogsumexp",
      "DenseBincount",
      "DataFormatDimMap",
      "DataFormatVecPermute",
      "DepthToSpace",
      "DepthwiseConv2dNative",

      return TF::ArraysAreCastCompatible(l, r);
    }

  }];
}

def TFL_CumsumOp: TFL_Op<"cumsum", [
    Pure,
    PredOpTrait<"input and output must have same element type",
      TFL_TCresVTEtIsSameAsOp<0, 0>>,
    TFL_OperandHasRank<1, 0>]> {
  let summary = "Cumsum operator";

  let description = [{
    Compute the cumulative sum of the tensor x along axis.
  }];

performed instead:

```python
tf.cumsum([a, b, c], exclusive=True)  # => [0, a, a + b]
```

By setting the `reverse` kwarg to `True`, the cumsum is performed in the
opposite direction:

```python
tf.cumsum([a, b, c], reverse=True)  # => [a + b + c, b + c, c]
```

This is more efficient than using separate `tf.reverse` ops.

    "tf.Yield"(%arg1) : (tensor<f32>) -> ()
  }) {is_stateless = false} : (tensor<i32>) -> tensor<i1>
  func.return
}

// -----

// Test valid tf.Cumsum
func.func @testCumsum(%arg: tensor<8x16xf32>, %axis: tensor<i32>) -> tensor<8x16xf32> {
  %0 = "tf.Cumsum"(%arg, %axis) : (tensor<8x16xf32>, tensor<i32>) -> tensor<8x16xf32>
  func.return %0 : tensor<8x16xf32>
}

// -----

// CHECK-DAG:       %[[VAL_2:.*]] = "tf.Const"() <{value = dense<0> : tensor<i64>}> : () -> tensor<i64>
// CHECK:           %[[VAL_3:.*]] = "tf.Cumsum"(%[[VAL_0]], %[[VAL_2]]) <{exclusive = false, reverse = false}> : (tensor<4x12xf32>, tensor<i64>) -> tensor<4x12xf32>
// CHECK:           return %[[VAL_3]] : tensor<4x12xf32>
// CHECK:         }

hoteles hotels hotelwithflight.com hotmail house house.museum how hoyanger.no hoylandet.no hr hr.eu.org hra.health hs.kr hs.run hs.zone hsbc ht httpbin.org hu hu.com hu.eu.org hu.net hughes huissier-justice.fr humanities.museum hungry.jp hurdal.no hurum.no hvaler.no hyatt hyllestad.no hyogo.jp hyuga.miyazaki.jp hyundai hzc.io hábmer.no hámmárfeasta.no hápmir.no häkkinen.fi hå.no hægebostad.no hønefoss.no høyanger.no høylandet.no i.bg i.ng i.ph i.se i234.me ia.us iamallama.com ibara.okayama.jp...