Update base for Update on "qnn end to end flow"

Patch a few changes including:
- support bool tensor type
- support fp16 and fix the 8w8a quantization.
- add two non-supported ops (slice_scatter and index_put) in common_defs.py

stories model working end to end:
AOT:
fp16:
```
python -m examples.models.llama2.export_llama -kv --qnn -c stories110M.pt -p params.json
```
quantize:
```
python -m examples.models.llama2.export_llama -kv --qnn --pt2e_quantize -c stories110M.pt -p params.json
```

Runtime:
```
/llama_main --model_path=llama2_fp16_qnn_2.21.pte  --tokenizer_path=tokenizer.bin --prompt="Once"
```
Output:
```
Once upon a time, there was a boy named Tim. Tim had a pet dog named Max. Max was a big, strong dog. They liked to play and run in the park.
One day, Tim and Max went to the park to play. They saw a cat. The cat was up in a tree. Max wanted to help the cat. He tried to climb the tree, but he could not.
Then, something unexpected happened. Max started to climb the tree! He was very strong. Max helped the cat come down. The cat was happy. Tim was so proud of his pet.
```

Stories model is too small and sensitive to qunatization.

Differential Revision: [D56119738](https://our.internmc.facebook.com/intern/diff/D56119738/)

[ghstack-poisoned]

Author: cccclai

.clang-format

@@ -2,22 +2,55 @@
 Language:        Cpp
 AccessModifierOffset: -1
 AlignAfterOpenBracket: AlwaysBreak
-AlignConsecutiveMacros: None
-AlignConsecutiveAssignments: None
-AlignConsecutiveBitFields: None
-AlignConsecutiveDeclarations: None
+AlignArrayOfStructures: None
+AlignConsecutiveAssignments:
+  Enabled:         false
+  AcrossEmptyLines: false
+  AcrossComments:  false
+  AlignCompound:   false
+  AlignFunctionPointers: false
+  PadOperators:    true
+AlignConsecutiveBitFields:
+  Enabled:         false
+  AcrossEmptyLines: false
+  AcrossComments:  false
+  AlignCompound:   false
+  AlignFunctionPointers: false
+  PadOperators:    true
+AlignConsecutiveDeclarations:
+  Enabled:         false
+  AcrossEmptyLines: false
+  AcrossComments:  false
+  AlignCompound:   false
+  AlignFunctionPointers: false
+  PadOperators:    true
+AlignConsecutiveMacros:
+  Enabled:         false
+  AcrossEmptyLines: false
+  AcrossComments:  false
+  AlignCompound:   false
+  AlignFunctionPointers: false
+  PadOperators:    true
+AlignConsecutiveShortCaseStatements:
+  Enabled:         false
+  AcrossEmptyLines: false
+  AcrossComments:  false
+  AlignCaseColons: false
 AlignEscapedNewlines: Left
 AlignOperands:   DontAlign
-AlignTrailingComments: false
+AlignTrailingComments:
+  Kind:            Never
+  OverEmptyLines:  0
 AllowAllArgumentsOnNextLine: true
-AllowAllConstructorInitializersOnNextLine: true
 AllowAllParametersOfDeclarationOnNextLine: false
-AllowShortEnumsOnASingleLine: true
+AllowBreakBeforeNoexceptSpecifier: Never
 AllowShortBlocksOnASingleLine: Never
 AllowShortCaseLabelsOnASingleLine: false
+AllowShortCompoundRequirementOnASingleLine: true
+AllowShortEnumsOnASingleLine: true
 AllowShortFunctionsOnASingleLine: Empty
-AllowShortLambdasOnASingleLine: All
 AllowShortIfStatementsOnASingleLine: Never
+AllowShortLambdasOnASingleLine: All
 AllowShortLoopsOnASingleLine: false
 AlwaysBreakAfterDefinitionReturnType: None
 AlwaysBreakAfterReturnType: None
@@ -27,17 +60,18 @@ AttributeMacros:
   - __capability
 BinPackArguments: false
 BinPackParameters: false
+BitFieldColonSpacing: Both
 BraceWrapping:
   AfterCaseLabel:  false
   AfterClass:      false
   AfterControlStatement: Never
   AfterEnum:       false
+  AfterExternBlock: false
   AfterFunction:   false
   AfterNamespace:  false
   AfterObjCDeclaration: false
   AfterStruct:     false
   AfterUnion:      false
-  AfterExternBlock: false
   BeforeCatch:     false
   BeforeElse:      false
   BeforeLambdaBody: false
@@ -46,35 +80,36 @@ BraceWrapping:
   SplitEmptyFunction: true
   SplitEmptyRecord: true
   SplitEmptyNamespace: true
+BreakAdjacentStringLiterals: true
+BreakAfterAttributes: Leave
+BreakAfterJavaFieldAnnotations: false
+BreakArrays:     true
 BreakBeforeBinaryOperators: None
-BreakBeforeConceptDeclarations: true
+BreakBeforeConceptDeclarations: Always
 BreakBeforeBraces: Attach
-BreakBeforeInheritanceComma: false
-BreakInheritanceList: BeforeColon
+BreakBeforeInlineASMColon: OnlyMultiline
 BreakBeforeTernaryOperators: true
-BreakConstructorInitializersBeforeComma: false
 BreakConstructorInitializers: BeforeColon
-BreakAfterJavaFieldAnnotations: false
+BreakInheritanceList: BeforeColon
 BreakStringLiterals: false
 ColumnLimit:     80
 CommentPragmas:  '^ IWYU pragma:'
 CompactNamespaces: false
-ConstructorInitializerAllOnOneLineOrOnePerLine: true
 ConstructorInitializerIndentWidth: 4
 ContinuationIndentWidth: 4
 Cpp11BracedListStyle: true
-DeriveLineEnding: true
 DerivePointerAlignment: false
 DisableFormat:   false
+EmptyLineAfterAccessModifier: Never
 EmptyLineBeforeAccessModifier: LogicalBlock
 ExperimentalAutoDetectBinPacking: false
 FixNamespaceComments: true
 ForEachMacros:
   - FOR_EACH
   - FOR_EACH_R
   - FOR_EACH_RANGE
-StatementAttributeLikeMacros:
-  - Q_EMIT
+IfMacros:
+  - KJ_IF_MAYBE
 IncludeBlocks:   Preserve
 IncludeCategories:
   - Regex:           '^<.*\.h(pp)?>'
@@ -91,18 +126,31 @@ IncludeCategories:
     CaseSensitive:   false
 IncludeIsMainRegex: '(Test)?$'
 IncludeIsMainSourceRegex: ''
-IndentCaseLabels: true
+IndentAccessModifiers: false
 IndentCaseBlocks: false
+IndentCaseLabels: true
+IndentExternBlock: AfterExternBlock
 IndentGotoLabels: true
 IndentPPDirectives: None
-IndentExternBlock: AfterExternBlock
-IndentRequires:  false
+IndentRequiresClause: true
 IndentWidth:     2
 IndentWrappedFunctionNames: false
+InsertBraces:    false
+InsertNewlineAtEOF: false
 InsertTrailingCommas: None
+IntegerLiteralSeparator:
+  Binary:          0
+  BinaryMinDigits: 0
+  Decimal:         0
+  DecimalMinDigits: 0
+  Hex:             0
+  HexMinDigits:    0
 JavaScriptQuotes: Leave
 JavaScriptWrapImports: true
 KeepEmptyLinesAtTheStartOfBlocks: false
+KeepEmptyLinesAtEOF: false
+LambdaBodyIndentation: Signature
+LineEnding:      DeriveLF
 MacroBlockBegin: ''
 MacroBlockEnd:   ''
 MaxEmptyLinesToKeep: 1
@@ -112,53 +160,85 @@ ObjCBlockIndentWidth: 2
 ObjCBreakBeforeNestedBlockParam: true
 ObjCSpaceAfterProperty: false
 ObjCSpaceBeforeProtocolList: false
+PackConstructorInitializers: NextLine
 PenaltyBreakAssignment: 2
 PenaltyBreakBeforeFirstCallParameter: 1
 PenaltyBreakComment: 300
 PenaltyBreakFirstLessLess: 120
+PenaltyBreakOpenParenthesis: 0
+PenaltyBreakScopeResolution: 500
 PenaltyBreakString: 1000
 PenaltyBreakTemplateDeclaration: 10
 PenaltyExcessCharacter: 1000000
-PenaltyReturnTypeOnItsOwnLine: 200
 PenaltyIndentedWhitespace: 0
+PenaltyReturnTypeOnItsOwnLine: 200
 PointerAlignment: Left
+PPIndentWidth:   -1
+QualifierAlignment: Leave
+ReferenceAlignment: Pointer
 ReflowComments:  true
-SortIncludes:    true
+RemoveBracesLLVM: false
+RemoveParentheses: Leave
+RemoveSemicolon: false
+RequiresClausePosition: OwnLine
+RequiresExpressionIndentation: OuterScope
+SeparateDefinitionBlocks: Leave
+ShortNamespaceLines: 1
+SkipMacroDefinitionBody: false
+SortIncludes:    CaseSensitive
 SortJavaStaticImport: Before
-SortUsingDeclarations: true
+SortUsingDeclarations: LexicographicNumeric
 SpaceAfterCStyleCast: false
 SpaceAfterLogicalNot: false
 SpaceAfterTemplateKeyword: true
+SpaceAroundPointerQualifiers: Default
 SpaceBeforeAssignmentOperators: true
 SpaceBeforeCaseColon: false
 SpaceBeforeCpp11BracedList: false
 SpaceBeforeCtorInitializerColon: true
 SpaceBeforeInheritanceColon: true
+SpaceBeforeJsonColon: false
 SpaceBeforeParens: ControlStatements
-SpaceAroundPointerQualifiers: Default
+SpaceBeforeParensOptions:
+  AfterControlStatements: true
+  AfterForeachMacros: true
+  AfterFunctionDefinitionName: false
+  AfterFunctionDeclarationName: false
+  AfterIfMacros:   true
+  AfterOverloadedOperator: false
+  AfterPlacementOperator: true
+  AfterRequiresInClause: false
+  AfterRequiresInExpression: false
+  BeforeNonEmptyParentheses: false
 SpaceBeforeRangeBasedForLoopColon: true
+SpaceBeforeSquareBrackets: false
 SpaceInEmptyBlock: false
-SpaceInEmptyParentheses: false
 SpacesBeforeTrailingComments: 1
-SpacesInAngles:  false
-SpacesInConditionalStatement: false
+SpacesInAngles:  Never
 SpacesInContainerLiterals: true
-SpacesInCStyleCastParentheses: false
-SpacesInParentheses: false
+SpacesInLineCommentPrefix:
+  Minimum:         1
+  Maximum:         -1
+SpacesInParens:  Never
+SpacesInParensOptions:
+  InCStyleCasts:   false
+  InConditionalStatements: false
+  InEmptyParentheses: false
+  Other:           false
 SpacesInSquareBrackets: false
-SpaceBeforeSquareBrackets: false
-BitFieldColonSpacing: Both
 Standard:        Latest
+StatementAttributeLikeMacros:
+  - Q_EMIT
 StatementMacros:
   - Q_UNUSED
   - QT_REQUIRE_VERSION
 TabWidth:        8
-UseCRLF:         false
 UseTab:          Never
+VerilogBreakBetweenInstancePorts: true
 WhitespaceSensitiveMacros:
-  - STRINGIZE
-  - PP_STRINGIZE
   - BOOST_PP_STRINGIZE
-  - NS_SWIFT_NAME
   - CF_SWIFT_NAME
+  - NS_SWIFT_NAME
+  - PP_STRINGIZE
+  - STRINGIZE
 ...

backends/apple/coreml/.clang-format

@@ -1,5 +1,4 @@
 BasedOnStyle: WebKit
-BreakBeforeBraces: Attach
 AllowShortIfStatementsOnASingleLine: false
 BreakBeforeBinaryOperators: None
 BreakConstructorInitializers: BeforeColon

backends/apple/coreml/runtime/delegate/ETCoreMLDefaultModelExecutor.h

@@ -13,7 +13,8 @@
 
 NS_ASSUME_NONNULL_BEGIN
 /// The default model executor, the executor ignores logging options.
-__attribute__((objc_subclassing_restricted)) @interface ETCoreMLDefaultModelExecutor : NSObject<ETCoreMLModelExecutor>
+__attribute__((objc_subclassing_restricted))
+@interface ETCoreMLDefaultModelExecutor : NSObject<ETCoreMLModelExecutor>
 
 + (instancetype)new NS_UNAVAILABLE;
 

backends/apple/coreml/runtime/delegate/ETCoreMLModelCompiler.h

@@ -9,7 +9,8 @@
 
 NS_ASSUME_NONNULL_BEGIN
 /// A class responsible for compiling a CoreML model.
-__attribute__((objc_subclassing_restricted)) @interface ETCoreMLModelCompiler : NSObject
+__attribute__((objc_subclassing_restricted))
+@interface ETCoreMLModelCompiler : NSObject
 
 + (instancetype)new NS_UNAVAILABLE;
 

backends/apple/coreml/runtime/delegate/ETCoreMLModelLoader.h

@@ -16,7 +16,8 @@ struct ModelMetadata;
 
 NS_ASSUME_NONNULL_BEGIN
 /// A class responsible for loading a CoreML model.
-__attribute__((objc_subclassing_restricted)) @interface ETCoreMLModelLoader : NSObject
+__attribute__((objc_subclassing_restricted))
+@interface ETCoreMLModelLoader : NSObject
 
 + (instancetype)new NS_UNAVAILABLE;
 

backends/apple/coreml/runtime/delegate/ETCoreMLModelManager.h

@@ -20,7 +20,8 @@ class ModelEventLogger;
 typedef void ModelHandle;
 
 /// A class responsible for managing the models loaded by the delegate.
-__attribute__((objc_subclassing_restricted)) @interface ETCoreMLModelManager : NSObject
+__attribute__((objc_subclassing_restricted))
+@interface ETCoreMLModelManager : NSObject
 
 + (instancetype)new NS_UNAVAILABLE;
 

backends/apple/coreml/runtime/kvstore/key_value_store.cpp

@@ -53,8 +53,7 @@ get_create_store_statement(std::string_view store_name, StorageType key_storage_
 
 std::string get_create_index_statement(std::string_view store_name, std::string_view column_name) {
     std::stringstream ss;
-    ss << "CREATE INDEX IF NOT EXISTS " << column_name << "_INDEX"
-       << " ON " << store_name << "(" << column_name << ")";
+    ss << "CREATE INDEX IF NOT EXISTS " << column_name << "_INDEX" << " ON " << store_name << "(" << column_name << ")";
 
     return ss.str();
 }

backends/apple/coreml/runtime/sdk/ETCoreMLModelDebugger.h

@@ -15,7 +15,8 @@ typedef NSDictionary<ETCoreMLModelStructurePath*, MLMultiArray*> ETCoreMLModelOu
 
 NS_ASSUME_NONNULL_BEGIN
 /// A class responsible for debugging a model.
-__attribute__((objc_subclassing_restricted)) @interface ETCoreMLModelDebugger : NSObject
+__attribute__((objc_subclassing_restricted))
+@interface ETCoreMLModelDebugger : NSObject
 
 - (instancetype)init NS_UNAVAILABLE;
 

backends/apple/coreml/runtime/sdk/ETCoreMLModelProfiler.h

@@ -21,7 +21,8 @@ typedef NSDictionary<ETCoreMLModelStructurePath*, ETCoreMLOperationProfilingInfo
 
 NS_ASSUME_NONNULL_BEGIN
 /// A class responsible for profiling a model.
-__attribute__((objc_subclassing_restricted)) @interface ETCoreMLModelProfiler : NSObject
+__attribute__((objc_subclassing_restricted))
+@interface ETCoreMLModelProfiler : NSObject
 
 - (instancetype)init NS_UNAVAILABLE;
 

backends/apple/coreml/runtime/sdk/ETCoreMLModelStructurePath.h

@@ -17,7 +17,8 @@ NS_ASSUME_NONNULL_BEGIN
 ///
 /// The class is a thin wrapper over `executorchcoreml::modelstructure::path`.
 ///
-__attribute__((objc_subclassing_restricted)) @interface ETCoreMLModelStructurePath : NSObject<NSCopying>
+__attribute__((objc_subclassing_restricted))
+@interface ETCoreMLModelStructurePath : NSObject<NSCopying>
 
 - (instancetype)init NS_UNAVAILABLE;
 

backends/apple/coreml/runtime/sdk/ETCoreMLOperationProfilingInfo.h

@@ -12,7 +12,8 @@
 NS_ASSUME_NONNULL_BEGIN
 
 /// A class representing the profiling info of an operation.
-__attribute__((objc_subclassing_restricted)) @interface ETCoreMLOperationProfilingInfo : NSObject<NSCopying>
+__attribute__((objc_subclassing_restricted))
+@interface ETCoreMLOperationProfilingInfo : NSObject<NSCopying>
 
 - (instancetype)init NS_UNAVAILABLE;
 

backends/apple/coreml/runtime/sdk/ETCoreMLPair.h

@@ -9,7 +9,8 @@
 
 NS_ASSUME_NONNULL_BEGIN
 /// A class representing a pair with first and second objects.
-__attribute__((objc_subclassing_restricted)) @interface ETCoreMLPair<First, Second> : NSObject<NSCopying>
+__attribute__((objc_subclassing_restricted))
+@interface ETCoreMLPair<First, Second> : NSObject<NSCopying>
 
 - (instancetype)init NS_UNAVAILABLE;