diff --git a/cmake/CMakeLists.txt b/cmake/CMakeLists.txt
index b3d6fade02050..d5ab7f4b74a9a 100644
--- a/cmake/CMakeLists.txt
+++ b/cmake/CMakeLists.txt
@@ -68,7 +68,7 @@ option(onnxruntime_USE_QNN "Build with QNN support" OFF)
 option(onnxruntime_USE_SNPE "Build with SNPE support" OFF)
 option(onnxruntime_USE_RKNPU "Build with RKNPU support" OFF)
 option(onnxruntime_USE_DNNL "Build with DNNL support" OFF)
-option(onnxruntime_USE_JS "Build with JavaScript implemented kernels support" OFF)
+option(onnxruntime_USE_JSEP "Build with JavaScript implemented kernels support" OFF)
 option(onnxruntime_BUILD_UNIT_TESTS "Build ONNXRuntime unit tests" ON)
 option(onnxruntime_BUILD_CSHARP "Build C# library" OFF)
 option(onnxruntime_BUILD_OBJC "Build Objective-C library" OFF)
@@ -662,9 +662,9 @@ if (onnxruntime_USE_NNAPI_BUILTIN)
     list(APPEND ORT_PROVIDER_CMAKE_FLAGS -Donnxruntime_USE_NNAPI_BUILTIN=1)
     list(APPEND ONNXRUNTIME_PROVIDER_NAMES nnapi)
 endif()
-if (onnxruntime_USE_JS)
-    list(APPEND ORT_PROVIDER_FLAGS -DUSE_JS=1)
-    list(APPEND ORT_PROVIDER_CMAKE_FLAGS -Donnxruntime_USE_JS=1)
+if (onnxruntime_USE_JSEP)
+    list(APPEND ORT_PROVIDER_FLAGS -DUSE_JSEP=1)
+    list(APPEND ORT_PROVIDER_CMAKE_FLAGS -Donnxruntime_USE_JSEP=1)
     list(APPEND ONNXRUNTIME_PROVIDER_NAMES js)
 endif()
 if (onnxruntime_USE_QNN)
diff --git a/cmake/onnxruntime_providers.cmake b/cmake/onnxruntime_providers.cmake
index c253b6b9c7197..caae2aacfd582 100644
--- a/cmake/onnxruntime_providers.cmake
+++ b/cmake/onnxruntime_providers.cmake
@@ -114,7 +114,7 @@ endif()
 if(onnxruntime_USE_NNAPI_BUILTIN)
   set(PROVIDERS_NNAPI onnxruntime_providers_nnapi)
 endif()
-if(onnxruntime_USE_JS)
+if(onnxruntime_USE_JSEP)
   set(PROVIDERS_JS onnxruntime_providers_js)
 endif()
 if(onnxruntime_USE_QNN)
@@ -1067,8 +1067,8 @@ if (onnxruntime_USE_NNAPI_BUILTIN)
   endif()
 endif()
 
-if (onnxruntime_USE_JS)
-  add_compile_definitions(USE_JS=1)
+if (onnxruntime_USE_JSEP)
+  add_compile_definitions(USE_JSEP=1)
 
   file(GLOB_RECURSE onnxruntime_providers_js_cc_srcs
     "${ONNXRUNTIME_ROOT}/core/providers/js/*.h"
diff --git a/cmake/onnxruntime_unittests.cmake b/cmake/onnxruntime_unittests.cmake
index c0c50e0e11b08..6d506522a91de 100644
--- a/cmake/onnxruntime_unittests.cmake
+++ b/cmake/onnxruntime_unittests.cmake
@@ -504,7 +504,7 @@ if(onnxruntime_USE_NNAPI_BUILTIN)
   list(APPEND onnxruntime_test_providers_dependencies onnxruntime_providers_nnapi)
 endif()
 
-if(onnxruntime_USE_JS)
+if(onnxruntime_USE_JSEP)
   list(APPEND onnxruntime_test_providers_dependencies onnxruntime_providers_js)
 endif()
 
@@ -609,7 +609,7 @@ if(onnxruntime_USE_NNAPI_BUILTIN)
   list(APPEND onnxruntime_test_providers_libs onnxruntime_providers_nnapi)
 endif()
 
-if(onnxruntime_USE_JS)
+if(onnxruntime_USE_JSEP)
   list(APPEND onnxruntime_test_framework_src_patterns  ${TEST_SRC_DIR}/providers/js/*)
   list(APPEND onnxruntime_test_framework_libs onnxruntime_providers_js)
   list(APPEND onnxruntime_test_providers_dependencies onnxruntime_providers_js)
@@ -851,7 +851,7 @@ if (onnxruntime_BUILD_WEBASSEMBLY)
   if (onnxruntime_ENABLE_WEBASSEMBLY_THREADS)
     set_property(TARGET onnxruntime_test_all APPEND_STRING PROPERTY LINK_FLAGS " -s USE_PTHREADS=1 -s PROXY_TO_PTHREAD=1")
   endif()
-  if (onnxruntime_USE_JS)
+  if (onnxruntime_USE_JSEP)
     set_property(TARGET onnxruntime_test_all APPEND_STRING PROPERTY LINK_FLAGS " --pre-js \"${ONNXRUNTIME_ROOT}/wasm/js_internal_api.js\"")
   endif()
 endif()
diff --git a/cmake/onnxruntime_webassembly.cmake b/cmake/onnxruntime_webassembly.cmake
index 80a44ffb3fa63..193315f541b85 100644
--- a/cmake/onnxruntime_webassembly.cmake
+++ b/cmake/onnxruntime_webassembly.cmake
@@ -199,7 +199,7 @@ else()
   endif()
 
   set(EXPORTED_RUNTIME_METHODS "['stackAlloc','stackRestore','stackSave','UTF8ToString','stringToUTF8','lengthBytesUTF8']")
-  if (onnxruntime_USE_JS)
+  if (onnxruntime_USE_JSEP)
     set(EXPORTED_FUNCTIONS "_malloc,_free,_JsepOutput")
   else()
     set(EXPORTED_FUNCTIONS "_malloc,_free")
@@ -219,12 +219,12 @@ else()
     --no-entry
   )
 
-  if (onnxruntime_USE_JS)
+  if (onnxruntime_USE_JSEP)
     # NOTE: "-s ASYNCIFY=1" is required for JSEP to work with WebGPU
     #       This flag allows async functions to be called from sync functions, in the cost of binary size and
     #       build time. See https://emscripten.org/docs/porting/asyncify.html for more details.
 
-    target_compile_definitions(onnxruntime_webassembly PRIVATE USE_JS=1)
+    target_compile_definitions(onnxruntime_webassembly PRIVATE USE_JSEP=1)
     target_link_options(onnxruntime_webassembly PRIVATE
       --pre-js "${ONNXRUNTIME_ROOT}/wasm/js_internal_api.js"
       "SHELL:-s ASYNCIFY=1"
diff --git a/js/web/lib/wasm/jsep/backend-webgpu.ts b/js/web/lib/wasm/jsep/backend-webgpu.ts
index 849e8d3f41bbc..1589562aa9cfd 100644
--- a/js/web/lib/wasm/jsep/backend-webgpu.ts
+++ b/js/web/lib/wasm/jsep/backend-webgpu.ts
@@ -144,8 +144,10 @@ export class WebGpuBackend {
   }
 
   dispose(): void {
-    // TODO: uninitialization
-    // this.glContext.dispose();
+    // currently, we do not do anything in this function. In all known use cases, we don't have the requirement to
+    // actually dispose the WebGpuBackend instance, because it's always used as a singleton.
+    //
+    // revisit this place if we get real requirement to dispose the instance.
   }
 
   getCommandEncoder(): GPUCommandEncoder {
diff --git a/js/web/lib/wasm/jsep/init.ts b/js/web/lib/wasm/jsep/init.ts
index 4226a0ef46f57..07247e1648fac 100644
--- a/js/web/lib/wasm/jsep/init.ts
+++ b/js/web/lib/wasm/jsep/init.ts
@@ -29,7 +29,7 @@ class TensorViewImpl implements TensorView {
   }
 }
 
-class OpKernelContext implements ComputeContext {
+class ComputeContextImpl implements ComputeContext {
   readonly opKernelContext: number;
   readonly inputs: readonly TensorView[];
   get customData(): {[key: string]: unknown} {
@@ -142,7 +142,7 @@ export const init = async(module: OrtWasmModule): Promise<void> => {
         // jsepRun
         (kernel: number, contextDataOffset: number) => {
           LOG_DEBUG('verbose', () => `[WebGPU] jsepRun: kernel=${kernel}, contextDataOffset=${contextDataOffset}`);
-          const context = new OpKernelContext(module, backend, contextDataOffset);
+          const context = new ComputeContextImpl(module, backend, contextDataOffset);
           return backend.computeKernel(kernel, context);
         });
   }
diff --git a/js/web/lib/wasm/jsep/util.ts b/js/web/lib/wasm/jsep/util.ts
index cd128ad5e501d..21109fd97d3fc 100644
--- a/js/web/lib/wasm/jsep/util.ts
+++ b/js/web/lib/wasm/jsep/util.ts
@@ -4,46 +4,6 @@
 /* eslint-disable no-param-reassign */
 
 export class MatMulUtil {
-  /**
-   * Fix the input shapes for MatMul operation if they need fixing
-   * @param dimsA The shape of tensor A. Should be an array of positive integers
-   * @param dimsB The shape of tensor B. Should be an array of positive integers
-   * @returns A tuple containing the preprocessed input shapes as required by ONNX specifications
-   */
-  static preprocessInputShapes(dimsA: readonly number[], dimsB: readonly number[]):
-      [readonly number[], readonly number[]] {
-    // If the first argument is 1-D, it is promoted to a matrix by prepending
-    // a 1 to its dimensions. After matrix multiplication the prepended 1 is
-    // removed.
-    const a = (dimsA.length === 1) ? [1, dimsA[0]] : dimsA;
-
-    // If the second argument is 1-D, it is promoted to a matrix by appending
-    // a 1 to its dimensions. After matrix multiplication the appended 1 is
-    // removed.
-    const b = (dimsB.length === 1) ? [dimsB[0], 1] : dimsB;
-
-    return [a, b];
-  }
-
-  /**
-   * Fix the output shape computed for MatMul operation if it needs fixing
-   * @param outputShape The computed outputShape. Should be an array (atleast of length 2) of positive integers.
-   * This will be mutated.
-   * @param aRank The rank of tensor A.
-   * @param bRank The rank of tensor B.
-   */
-  static postprocessOutputShape(outputShape: number[], aRank: number, bRank: number): void {
-    // Remove prepended dimension if first input is 1d
-    if (aRank === 1) {
-      // outputShape = outputShape.slice(0, outputShape.length - 2).concat(outputShape.slice(outputShape.length - 1));
-      outputShape.splice(outputShape.length - 2, 1);
-    }
-    // Remove appended dimension if second input is 1d
-    if (bRank === 1) {
-      outputShape.pop();
-    }
-  }
-
   /**
    * Calculate the expected shape when matrix multiplication
    * @param a The shape of tensor A. Should be a tuple of 2 positive integers
@@ -102,39 +62,6 @@ export class BroadcastUtil {
     return cdims;
   }
 
-  /**
-   * Given the indices of a broadcasted tensor, calculate the original indices
-   * @param broadcastedIndices The given indices of the broadcasted tensor.
-   * @param originalShape The original shape of the tensor before broadcas
-   * @returns The calculated indices that maps to the original tensor.
-   */
-  static index(broadcastedIndices: readonly number[], originalShape: readonly number[]): number[] {
-    // NOTE 1: we assume the parameter broadcastedIndices is valid. ie. it should have the same
-    // length as the broadcasted shape, and for each dimension the index should
-    // not be out of range.
-    const originalIndices = new Array(originalShape.length);
-    BroadcastUtil.fillIndex(broadcastedIndices, originalShape, originalIndices);
-    return originalIndices;
-  }
-
-  /**
-   * Given the indices of a broadcasted tensor, calculate the original indices
-   * @param broadcastedIndices The given indices of the broadcasted tensor.
-   * @param originalShape The original shape of the tensor before broadcast
-   * @param originalIndices The mapping of broadcastedIndices to the originalIndices (output parameter - will be
-   *     mutated).
-   */
-  static fillIndex(broadcastedIndices: readonly number[], originalShape: readonly number[], originalIndices: number[]):
-      void {
-    // NOTE 1: we assume the parameter broadcastedIndices is valid. ie. it should have the same length as the
-    // broadcasted shape, and for each dimension the index should not be out of range.
-    // NOTE 2: we assume the parameter originalIndices has the same length as the originalShape
-    const dimOffset = broadcastedIndices.length - originalShape.length;
-    for (let i = 0; i < originalShape.length; i++) {
-      originalIndices[i] = broadcastedIndices[dimOffset + i] % originalShape[i];
-    }
-  }
-
   /**
    * Determine if a shape is unidirectional broadcastable to another shape
    * @param shape The input shape
@@ -154,27 +81,6 @@ export class BroadcastUtil {
     }
     return true;
   }
-
-  /**
-   * Determine the broadcasted dims in input shape based on the given output shape.
-   * Note that this function only returns the broadcasted dims.
-   * @param inputShape The input shape
-   * @param outputShape The output shape
-   * @returns The broadcasted dims in input shape.
-   */
-  static getBroadcastDims(inputShape: readonly number[], outputShape: readonly number[]): number[] {
-    const inRank = inputShape.length;
-    const dims: number[] = [];
-    for (let i = 0; i < inRank; i++) {
-      const dim = inRank - 1 - i;
-      const a = inputShape[dim] || 1;
-      const b = outputShape[outputShape.length - 1 - i] || 1;
-      if (b > 1 && a === 1) {
-        dims.unshift(dim);
-      }
-    }
-    return dims;
-  }
 }
 
 
@@ -240,38 +146,6 @@ export class ShapeUtil {
     return strides;
   }
 
-  static transpose(dims: readonly number[]): readonly number[] {
-    const copy = dims.slice();
-    return copy.reverse();
-  }
-
-  static indicesToOffset(indices: readonly number[], strides: readonly number[], axis?: number): number {
-    if (axis === undefined) {
-      axis = indices.length;
-    }
-    let offset = 0;
-    for (let i = 0; i < axis; ++i) {
-      offset += strides[i] * indices[i];
-    }
-    return offset;
-  }
-
-  static offsetToIndices(offset: number, strides: readonly number[]): readonly number[] {
-    const rank = strides.length;
-    if (rank === 0) {
-      return [];
-    } else if (rank === 1) {
-      return [offset * strides[0]];
-    }
-    const indices: number[] = new Array(strides.length);
-    for (let i = 0; i < indices.length - 1; ++i) {
-      indices[i] = Math.floor(offset / strides[i]);
-      offset -= indices[i] * strides[i];
-    }
-    indices[indices.length - 1] = offset;
-    return indices;
-  }
-
   /**
    * normailze axis of range [-r, r) into [0, r).
    */
@@ -286,98 +160,6 @@ export class ShapeUtil {
     return axes.map(x => this.normalizeAxis(x, tensorRank ?? axes.length));
   }
 
-  /**
-   * Increment an index into a tensor (in lexicographic ordering), wrapping around the specified upper_bound.
-   * @param index Given index to increment (Will be mutated)
-   * @param dims The dimensions of the tensor for which the given index corresponds to
-   * @param axisToIncrementOn The 1-indexed axis to increment on. If undefined, axisToIncrementOn == rank
-   */
-  static incrementIndex(index: number[], dims: readonly number[], axisToIncrementOn?: number): void {
-    if (dims.length === 0 || index.length === 0) {
-      throw new Error('Index incrementing unsupported for scalar Tensor');
-    }
-    if (axisToIncrementOn === undefined) {
-      axisToIncrementOn = dims.length;
-    } else {
-      if (axisToIncrementOn <= 0 || axisToIncrementOn > dims.length) {
-        throw new Error('Incorrect axis to increment on');
-      }
-    }
-
-    for (let k = axisToIncrementOn - 1; k >= 0; --k) {
-      index[k]++;
-      if (index[k] < dims[k]) {
-        break;
-      }
-      index[k] = 0;
-    }
-  }
-
-  /**
-   * Produces a new dimensions array based on the values in the 'originalDimensions' and 'shape' array
-   * Used in Reshape
-   * @param originalDims Original Shape array
-   * @param shapeHints array containing values to compute the new dimensions
-   * For example:
-   * originalDims = [2,2] and shapeHints = [0,-1] will return [2,2]
-   * originalDims = [2,2] and shapeHints = [4] will return [4]
-   * originalDims = [2,2] and shapeHints = [5] will throw an exception
-   * https://github.com/onnx/onnx/blob/main/docs/Operators.md#Reshape
-   */
-
-  static calculateReshapedDims(originalDims: readonly number[], shapeHints: ArrayLike<number>): number[] {
-    // reshape to a Scalar Tensor
-    if (shapeHints.length === 0) {
-      if (originalDims.length === 0 || ShapeUtil.size(originalDims) === 1) {
-        return [];
-      } else {
-        throw new Error('cannot reshape to a scalar Tensor');
-      }
-    }
-
-    const nDims = shapeHints.length;
-    const reshapedDims = new Array<number>(nDims);
-    let unknownDimension = -1;
-    let newTensorSize = 1;
-    for (let i = 0; i < nDims; i++) {
-      if (shapeHints[i] < -1) {
-        throw new Error('a dimension in shape hints cannot be less than -1');
-      }
-      if (shapeHints[i] === -1) {
-        if (unknownDimension !== -1) {
-          throw new Error('at most one dimension in shape hints can be -1');
-        }
-        unknownDimension = i;
-      } else {
-        if (shapeHints[i] === 0) {
-          if (i >= originalDims.length) {
-            throw new Error('the dimension with value zero exceeds the dimension size of the input tensor');
-          }
-          reshapedDims[i] = originalDims[i];
-        } else {
-          reshapedDims[i] = shapeHints[i];
-        }
-        newTensorSize *= reshapedDims[i];
-      }
-    }
-
-    const oldTensorSize = ShapeUtil.size(originalDims);
-    if (unknownDimension !== -1) {
-      if (oldTensorSize % newTensorSize !== 0) {
-        throw new Error(`the input tensor cannot be reshaped to the requested shape. Input shape: [${
-            originalDims}] Output shape: [${shapeHints}]`);
-      }
-      reshapedDims[unknownDimension] = oldTensorSize / newTensorSize;
-    }
-    // validate sizes from originalDims and reshapedDims match
-    else {
-      if (newTensorSize !== oldTensorSize) {
-        throw new Error('reshapedDims and originalDims don\'t have matching sizes');
-      }
-    }
-    return reshapedDims;
-  }
-
   /**
    * Sorts a given array based on the indices in the Perm array
    * Used in Transpose
@@ -413,109 +195,6 @@ export class ShapeUtil {
     }
     return shape1.every((v, i) => v === shape2[i]);
   }
-
-  /**
-   * Validates if the given `dims` or `shape` is valid in ONNX.js context and returns data size
-   * @param dims - input `dims` that needs to be checked
-   */
-  static validateDimsAndCalcSize(dims: readonly number[]): number {
-    if (dims.length > 6) {
-      throw new TypeError('Only rank 0 to 6 is supported for tensor shape.');
-    }
-    let size = 1;
-    for (const n of dims) {
-      if (!Number.isInteger(n)) {
-        throw new TypeError(`Invalid shape: ${n} is not an integer`);
-      }
-      if (n < 0 || n > 2147483647) {
-        throw new TypeError(`Invalid shape: length ${n} is not allowed`);
-      }
-      size *= n;
-    }
-    return size;
-  }
-
-  /**
-   * Determines the shape of output tensor y = flatten(x, axis)
-   * @param dims - shape of input tensor
-   * @param axis - flatten axis, in the range [-r, r]
-   */
-  static flattenShape(dims: readonly number[], axis: number): readonly number[] {
-    if (axis < 0) {
-      axis += dims.length;
-    }
-    const total = dims.reduce((x, y) => x * y, 1);
-    const right = dims.slice(axis).reduce((x, y) => x * y, 1);
-    const outputDims = [total / right, right];
-
-    return outputDims;
-  }
-
-  /**
-   * Determines the shape of output tensor y = squeeze(x, axes)
-   * @param dims - shape of input tensor
-   * @param axes - squeeze axes
-   */
-  static squeezeShape(dims: readonly number[], axes: readonly number[]): readonly number[] {
-    const outputDims = new Array<number>();
-
-    // sanity check
-    axes = ShapeUtil.normalizeAxes(axes, dims.length);
-
-    for (let i = 0; i < dims.length; i++) {
-      const inSqueezeList = axes.indexOf(i) >= 0;
-      if (inSqueezeList && dims[i] !== 1) {
-        throw new Error('squeeze an axis of size different than 1');
-      }
-
-      if ((axes.length === 0 && dims[i] > 1) || (axes.length > 0 && !inSqueezeList)) {
-        outputDims.push(dims[i]);
-      }
-    }
-
-    return outputDims;
-  }
-
-  /**
-   * Determines the shape of output tensor y = unsqueeze(x, axes)
-   * @param dims - shape of input tensor
-   * @param axes - unsqueeze axes
-   */
-  static unsqueezeShape(dims: readonly number[], axes: readonly number[]): readonly number[] {
-    const outputDims = new Array<number>(dims.length + axes.length);
-
-    // initialize the array elements to 0
-    outputDims.fill(0);
-
-    // set all axes indices to 1 in outputDims and check for duplicates
-    for (let i = 0; i < axes.length; i++) {
-      const axis = ShapeUtil.normalizeAxis(axes[i], outputDims.length);
-      if (axis >= outputDims.length) {
-        throw new Error('\'axes\' has an out of range axis');
-      }
-      if (outputDims[axis] !== 0) {
-        throw new Error('\'axes\' has a duplicate axis');
-      }
-
-      outputDims[axis] = 1;
-    }
-
-    // fill in the zero entries of outputDims with the input tensor's shape
-    let inputDimsIterator = 0;
-    for (let i = 0; i < outputDims.length; i++) {
-      if (outputDims[i] === 0) {
-        outputDims[i] = dims[inputDimsIterator++];
-      }
-    }
-
-    // sanity check assertion. 'inputDimsIterator'
-    // should be equal to the length of 'dims'
-    if (inputDimsIterator !== dims.length) {
-      throw new Error('the unsqueezed dimension could not be established');
-    }
-
-    return outputDims;
-  }
 }
 
 export class PoolConvUtil {
diff --git a/onnxruntime/core/providers/get_execution_providers.cc b/onnxruntime/core/providers/get_execution_providers.cc
index 42cc24a7964d7..f7b372d1eff74 100644
--- a/onnxruntime/core/providers/get_execution_providers.cc
+++ b/onnxruntime/core/providers/get_execution_providers.cc
@@ -102,7 +102,7 @@ constexpr ProviderInfo kProvidersInPriorityOrder[] =
         },
         {
             kJsExecutionProvider,
-#ifdef USE_JS
+#ifdef USE_JSEP
             true,
 #else
             false,
diff --git a/onnxruntime/core/providers/js/js_execution_provider.cc b/onnxruntime/core/providers/js/js_execution_provider.cc
index d1308da7f888c..df5679bda7db0 100644
--- a/onnxruntime/core/providers/js/js_execution_provider.cc
+++ b/onnxruntime/core/providers/js/js_execution_provider.cc
@@ -295,7 +295,8 @@ void JsExecutionProvider::RegisterAllocator(AllocatorManager& allocator_manager)
     if (!cpu_alloc) {
       AllocatorCreationInfo cpuAllocatorCreationInfo([&](int) {
         return std::make_unique<js::JsCPUAllocator>();
-      });
+      },
+                                                     0, false);
       cpu_alloc = CreateAllocator(cpuAllocatorCreationInfo);
       allocator_manager.InsertAllocator(cpu_alloc);
     }
diff --git a/onnxruntime/core/providers/js/js_execution_provider.h b/onnxruntime/core/providers/js/js_execution_provider.h
index ce8ec53eca1f6..3e5621ff78520 100644
--- a/onnxruntime/core/providers/js/js_execution_provider.h
+++ b/onnxruntime/core/providers/js/js_execution_provider.h
@@ -46,6 +46,8 @@ class JsExecutionProvider : public IExecutionProvider {
 
   FusionStyle GetFusionStyle() const override { return FusionStyle::FilteredGraphViewer; }
 
+  // JSEP disallow concurrent run because actual implementation (eg. WebGPU backend) relies on global states to work,
+  // and concurrent run with async function may mess up the states and cause undefined behavior.
   bool ConcurrentRunSupported() const override { return false; }
 };
 
diff --git a/onnxruntime/core/providers/js/operators/transpose.h b/onnxruntime/core/providers/js/operators/transpose.h
index f2214438c6fd1..311badbde0d11 100644
--- a/onnxruntime/core/providers/js/operators/transpose.h
+++ b/onnxruntime/core/providers/js/operators/transpose.h
@@ -16,17 +16,17 @@ class Transpose final : public JsKernel, public TransposeBase {
     std::vector<int32_t> perm;
     if (perm_specified_) {
       perm.resize(perm_.size());
-      perm[0] = gsl::narrow_cast<int32_t>(perm_.size());
       for (size_t i = 0; i < perm_.size(); ++i) {
         perm[i] = gsl::narrow_cast<int32_t>(perm_[i]);
       }
     }
-    // printf("Transpose: perm_specified_ = %d, perm.size() = %d, perm[0] = %d, perm[1] = %d, perm[2] = %d, perm[3] = %d\n",
-    //   perm_specified_, static_cast<int32_t>(perm.size()), perm[0], perm[1], perm[2], perm[3]);
     JSEP_INIT_KERNEL_ATTRIBUTE(Transpose, ({
                                  "perm" : $1 ? Array.from(HEAP32.subarray($2, $2 + $1)) : []
                                }),
+                               // $1: length of attribute "perm" (int32[])
                                gsl::narrow_cast<int32_t>(perm_specified_ ? perm_.size() : 0),
+                               // $2: index to HEAP32 of the first int32 element. calculated from right shift memory
+                               //     address by 2
                                reinterpret_cast<int32_t>(perm_specified_ && !perm.empty() ? perm.data() : nullptr) >> 2);
   }
 };
diff --git a/onnxruntime/core/providers/provider_factory_creators.h b/onnxruntime/core/providers/provider_factory_creators.h
index 261d16a4e8be5..b019ede434b83 100644
--- a/onnxruntime/core/providers/provider_factory_creators.h
+++ b/onnxruntime/core/providers/provider_factory_creators.h
@@ -46,7 +46,7 @@
 #include "core/providers/nnapi/nnapi_provider_factory_creator.h"
 #endif
 
-#if defined(USE_JS)
+#if defined(USE_JSEP)
 #include "core/providers/js/js_provider_factory_creator.h"
 #endif
 
@@ -92,4 +92,4 @@
 
 #if defined(USE_AZURE)
 #include "core/providers/azure/azure_provider_factory_creator.h"
-#endif
\ No newline at end of file
+#endif
diff --git a/onnxruntime/core/session/provider_registration.cc b/onnxruntime/core/session/provider_registration.cc
index de7c8bd6fb101..8cadccd0ef376 100644
--- a/onnxruntime/core/session/provider_registration.cc
+++ b/onnxruntime/core/session/provider_registration.cc
@@ -91,7 +91,7 @@ ORT_API_STATUS_IMPL(OrtApis::SessionOptionsAppendExecutionProvider,
     status = create_not_supported_status();
 #endif
   } else if (strcmp(provider_name, "JS") == 0) {
-#if defined(USE_JS)
+#if defined(USE_JSEP)
     options->provider_factories.push_back(JsProviderFactoryCreator::Create(provider_options));
 #else
     status = create_not_supported_status();
diff --git a/onnxruntime/wasm/api.cc b/onnxruntime/wasm/api.cc
index 47cb578f7e969..5dd0bd23353fb 100644
--- a/onnxruntime/wasm/api.cc
+++ b/onnxruntime/wasm/api.cc
@@ -363,11 +363,11 @@ int OrtRun(OrtSession* session,
            const char** input_names, const ort_tensor_handle_t* inputs, size_t input_count,
            const char** output_names, size_t output_count, ort_tensor_handle_t* outputs,
            OrtRunOptions* run_options) {
-#if defined(USE_JS)
+#if defined(USE_JSEP)
   EM_ASM({ Module["jsepRunPromise"] = new Promise(function(r) { Module.jsepRunPromiseResolve = r; }); });
 #endif
   auto status_code = CHECK_STATUS(Run, session, run_options, input_names, inputs, input_count, output_names, output_count, outputs);
-#if defined(USE_JS)
+#if defined(USE_JSEP)
   EM_ASM({ Module.jsepRunPromiseResolve($0); }, status_code);
 #endif
   return status_code;
diff --git a/tools/ci_build/build.py b/tools/ci_build/build.py
index 0bc2b0f3717dc..228f39beae84b 100644
--- a/tools/ci_build/build.py
+++ b/tools/ci_build/build.py
@@ -483,7 +483,7 @@ def convert_arg_line_to_args(self, arg_line):
     parser.add_argument(
         "--nnapi_min_api", type=int, help="Minimum Android API level to enable NNAPI, should be no less than 27"
     )
-    parser.add_argument("--use_js", action="store_true", help="Build with JavaScript kernels.")
+    parser.add_argument("--use_jsep", action="store_true", help="Build with JavaScript kernels.")
     parser.add_argument("--use_qnn", action="store_true", help="Build with QNN support.")
     parser.add_argument("--qnn_home", help="Path to QNN SDK dir.")
     parser.add_argument("--use_rknpu", action="store_true", help="Build with RKNPU.")
@@ -946,7 +946,7 @@ def generate_build_tree(
         "-Donnxruntime_USE_ARMNN=" + ("ON" if args.use_armnn else "OFF"),
         "-Donnxruntime_ARMNN_RELU_USE_CPU=" + ("OFF" if args.armnn_relu else "ON"),
         "-Donnxruntime_ARMNN_BN_USE_CPU=" + ("OFF" if args.armnn_bn else "ON"),
-        "-Donnxruntime_USE_JS=" + ("ON" if args.use_js else "OFF"),
+        "-Donnxruntime_USE_JSEP=" + ("ON" if args.use_jsep else "OFF"),
         # Training related flags
         "-Donnxruntime_ENABLE_NVTX_PROFILE=" + ("ON" if args.enable_nvtx_profile else "OFF"),
         "-Donnxruntime_ENABLE_TRAINING=" + ("ON" if args.enable_training else "OFF"),
diff --git a/tools/ci_build/github/azure-pipelines/templates/win-wasm-ci.yml b/tools/ci_build/github/azure-pipelines/templates/win-wasm-ci.yml
index 4ec339bb0fb81..786d7b77a076c 100644
--- a/tools/ci_build/github/azure-pipelines/templates/win-wasm-ci.yml
+++ b/tools/ci_build/github/azure-pipelines/templates/win-wasm-ci.yml
@@ -104,7 +104,7 @@ jobs:
       displayName: 'Build (simd + JSEP)'
       inputs:
         scriptPath: '$(Build.SourcesDirectory)\tools\ci_build\build.py'
-        arguments: '$(CommonBuildArgs) --build_dir $(Build.BinariesDirectory)\wasm_simd_jsep --enable_wasm_simd --use_js --target onnxruntime_webassembly'
+        arguments: '$(CommonBuildArgs) --build_dir $(Build.BinariesDirectory)\wasm_simd_jsep --enable_wasm_simd --use_jsep --target onnxruntime_webassembly'
         workingDirectory: '$(Build.BinariesDirectory)'
   - ${{ if eq(parameters.SkipPublish, false) }}:
     - script: |