feat: update llama.cpp to 9601+dfsg-1

.clang-format

@@ -0,0 +1,171 @@
+---
+Language:        Cpp
+AlignAfterOpenBracket: Align
+AlignArrayOfStructures: Left
+AlignConsecutiveAssignments: AcrossComments
+AlignConsecutiveBitFields: AcrossComments
+AlignConsecutiveDeclarations: AcrossComments
+AlignConsecutiveMacros: AcrossComments
+# AlignConsecutiveShortCaseStatements: AcrossComments
+AlignEscapedNewlines: Left # LeftWithLastLine
+AlignOperands:   Align
+AlignTrailingComments:
+  Kind: Always
+  OverEmptyLines: 1
+AllowAllArgumentsOnNextLine: true
+AllowAllParametersOfDeclarationOnNextLine: false
+# AllowBreakBeforeNoexceptSpecifier: OnlyWithParen
+AllowShortBlocksOnASingleLine: Never
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: Inline
+AllowShortIfStatementsOnASingleLine: Never
+AllowShortLambdasOnASingleLine: Inline
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakBeforeMultilineStrings: true
+# Treat CUDA keywords/attributes as "attribute macros" and avoid breaking lines inside them
+AttributeMacros:
+  - __host__
+  - __device__
+  - __global__
+  - __forceinline__
+  - __launch_bounds__
+BinPackArguments: true
+BinPackParameters: false # OnePerLine
+BitFieldColonSpacing: Both
+BreakBeforeBraces: Custom # Attach
+BraceWrapping:
+  AfterCaseLabel:  true
+  AfterClass:      false
+  AfterControlStatement: false
+  AfterEnum:       false
+  AfterFunction:   false
+  AfterNamespace:  false
+  AfterObjCDeclaration: false
+  AfterStruct:     false
+  AfterUnion:      false
+  AfterExternBlock: false
+  BeforeCatch:     false
+  BeforeElse:      false
+  BeforeLambdaBody: false
+  BeforeWhile: false
+  IndentBraces:    false
+  SplitEmptyFunction: false
+  SplitEmptyRecord: false
+  SplitEmptyNamespace: false
+# BreakAdjacentStringLiterals: true
+BreakAfterAttributes: Never
+BreakBeforeBinaryOperators: None
+BreakBeforeInlineASMColon: OnlyMultiline
+BreakBeforeTernaryOperators: false
+# BreakBinaryOperations: Never
+BreakConstructorInitializers: AfterColon
+# BreakFunctionDefinitionParameters: false
+BreakInheritanceList: AfterComma
+BreakStringLiterals: true
+# BreakTemplateDeclarations: Yes
+ColumnLimit:     120
+CommentPragmas:  '^ IWYU pragma:'
+CompactNamespaces: false
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: false
+DerivePointerAlignment: false
+DisableFormat:   false
+EmptyLineBeforeAccessModifier: Leave
+EmptyLineAfterAccessModifier: Never
+ExperimentalAutoDetectBinPacking: false
+FixNamespaceComments: true
+IncludeBlocks:   Regroup
+IncludeCategories:
+  - Regex:           '".*"'
+    Priority:        1
+    SortPriority:    0
+  - Regex:           '^<.*\.h>'
+    Priority:        2
+    SortPriority:    0
+  - Regex:           '^<.*'
+    Priority:        3
+    SortPriority:    0
+  - Regex:           '.*'
+    Priority:        4
+    SortPriority:    0
+IncludeIsMainRegex: '([-_](test|unittest))?$'
+IncludeIsMainSourceRegex: ''
+IndentAccessModifiers: false
+IndentCaseBlocks: true
+IndentCaseLabels: true
+IndentExternBlock: NoIndent
+IndentGotoLabels: false
+IndentPPDirectives: AfterHash
+IndentWidth:     4
+IndentWrappedFunctionNames: false
+InsertBraces:    true # NOTE: may lead to incorrect formatting
+InsertNewlineAtEOF: true
+JavaScriptQuotes: Leave
+JavaScriptWrapImports: true
+KeepEmptyLinesAtTheStartOfBlocks: false
+LambdaBodyIndentation: Signature
+LineEnding: LF
+MacroBlockBegin: ''
+MacroBlockEnd:   ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+ObjCBinPackProtocolList: Auto
+ObjCBlockIndentWidth: 4
+ObjCSpaceAfterProperty: true
+ObjCSpaceBeforeProtocolList: true
+PPIndentWidth: -1
+PackConstructorInitializers: CurrentLine
+PenaltyBreakAssignment: 2
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyBreakTemplateDeclaration: 10
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 200
+PointerAlignment: Middle
+QualifierAlignment: Left
+#QualifierOrder: ['static', 'inline', 'friend', 'constexpr', 'const', 'volatile', 'type', 'restrict']
+RawStringFormats:
+  - Language:        Cpp
+    Delimiters:
+      - cc
+      - CC
+      - cpp
+      - Cpp
+      - CPP
+      - 'c++'
+      - 'C++'
+    CanonicalDelimiter: ''
+ReferenceAlignment: Middle
+ReflowComments:  false # IndentOnly
+SeparateDefinitionBlocks: Always
+SortIncludes:    CaseInsensitive
+SortUsingDeclarations: LexicographicNumeric
+SpaceAfterCStyleCast: true
+SpaceAfterLogicalNot: false
+SpaceAfterTemplateKeyword: true
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeCpp11BracedList: false
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeParens: ControlStatements
+SpaceBeforeRangeBasedForLoopColon: true
+SpaceInEmptyBlock: false
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 2
+SpacesInAngles:  Never
+SpacesInContainerLiterals: true
+SpacesInLineCommentPrefix:
+  Minimum: 1
+  Maximum: -1
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+SpaceBeforeSquareBrackets: false
+Standard:        c++17
+TabWidth:        4
+UseTab:          Never
+WhitespaceSensitiveMacros: ['STRINGIZE']
+...
+

.clang-tidy

@@ -0,0 +1,28 @@
+---
+Checks: >
+    bugprone-*,
+    -bugprone-easily-swappable-parameters,
+    -bugprone-implicit-widening-of-multiplication-result,
+    -bugprone-misplaced-widening-cast,
+    -bugprone-narrowing-conversions,
+    readability-*,
+    -readability-avoid-unconditional-preprocessor-if,
+    -readability-function-cognitive-complexity,
+    -readability-identifier-length,
+    -readability-implicit-bool-conversion,
+    -readability-magic-numbers,
+    -readability-uppercase-literal-suffix,
+    -readability-simplify-boolean-expr,
+    -readability-math-missing-parentheses,
+    clang-analyzer-*,
+    -clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling,
+    performance-*,
+    -performance-enum-size,
+    portability-*,
+    -portability-simd-intrinsics,
+    misc-*,
+    -misc-const-correctness,
+    -misc-non-private-member-variables-in-classes,
+    -misc-no-recursion,
+    -misc-use-anonymous-namespace,
+FormatStyle: none

.devops/cann.Dockerfile

@@ -0,0 +1,147 @@
+# ==============================================================================
+# ARGUMENTS
+# ==============================================================================
+
+# Define the CANN base image for easier version updates later
+ARG CHIP_TYPE=910b
+ARG CANN_BASE_IMAGE=quay.io/ascend/cann:8.5.0-${CHIP_TYPE}-openeuler24.03-py3.11
+ARG BUILD_DATE=N/A
+ARG APP_VERSION=N/A
+ARG APP_REVISION=N/A
+
+# ==============================================================================
+# BUILD STAGE
+# Compile all binary files and libraries
+# ==============================================================================
+FROM ${CANN_BASE_IMAGE} AS build
+
+# -- Install build dependencies --
+RUN yum install -y gcc g++ cmake make git openssl-devel python3 python3-pip && \
+    yum clean all && \
+    rm -rf /var/cache/yum
+
+# -- Set the working directory --
+WORKDIR /app
+
+# -- Copy project files --
+COPY . .
+
+# -- Set CANN environment variables (required for compilation) --
+# Using ENV instead of `source` allows environment variables to persist across the entire image layer
+ENV ASCEND_TOOLKIT_HOME=/usr/local/Ascend/ascend-toolkit/latest
+ENV LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${LD_LIBRARY_PATH}
+ENV PATH=${ASCEND_TOOLKIT_HOME}/bin:${PATH}
+ENV ASCEND_OPP_PATH=${ASCEND_TOOLKIT_HOME}/opp
+ENV LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/runtime/lib64/stub:$LD_LIBRARY_PATH
+# ... You can add other environment variables from the original file as needed ...
+# For brevity, only core variables are listed here. You can paste the original ENV list here.
+
+# -- Build llama.cpp --
+# Use the passed CHIP_TYPE argument and add general build options
+ARG CHIP_TYPE
+RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh --force \
+    && \
+    cmake -B build \
+        -DGGML_CANN=ON \
+        -DCMAKE_BUILD_TYPE=Release \
+        -DSOC_TYPE=ascend${CHIP_TYPE} \
+        -DUSE_ACL_GRAPH=ON \
+        . && \
+    cmake --build build --config Release -j$(nproc)
+
+# -- Organize build artifacts for copying in later stages --
+# Create a lib directory to store all .so files
+RUN mkdir -p /app/lib && \
+    find build -name "*.so*" -exec cp -P {} /app/lib \;
+
+# Create a full directory to store all executables and Python scripts
+RUN mkdir -p /app/full && \
+    cp build/bin/* /app/full/ && \
+    cp *.py /app/full/ && \
+    cp -r conversion /app/full/ && \
+    cp -r gguf-py /app/full/ && \
+    cp -r requirements /app/full/ && \
+    cp requirements.txt /app/full/
+    # If you have a tools.sh script, make sure it is copied here
+    # cp .devops/tools.sh /app/full/tools.sh
+
+# ==============================================================================
+# BASE STAGE
+# Create a minimal base image with CANN runtime and common libraries
+# ==============================================================================
+FROM ${CANN_BASE_IMAGE} AS base
+
+ARG BUILD_DATE=N/A
+ARG APP_VERSION=N/A
+ARG APP_REVISION=N/A
+ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
+ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
+LABEL org.opencontainers.image.created=$BUILD_DATE \
+      org.opencontainers.image.version=$APP_VERSION \
+      org.opencontainers.image.revision=$APP_REVISION \
+      org.opencontainers.image.title="llama.cpp" \
+      org.opencontainers.image.description="LLM inference in C/C++" \
+      org.opencontainers.image.url=$IMAGE_URL \
+      org.opencontainers.image.source=$IMAGE_SOURCE
+
+# -- Install runtime dependencies --
+RUN yum install -y libgomp curl && \
+    yum clean all && \
+    rm -rf /var/cache/yum
+
+# -- Set CANN environment variables (required for runtime) --
+ENV ASCEND_TOOLKIT_HOME=/usr/local/Ascend/ascend-toolkit/latest
+ENV LD_LIBRARY_PATH=/app:${ASCEND_TOOLKIT_HOME}/lib64:${LD_LIBRARY_PATH}
+ENV PATH=${ASCEND_TOOLKIT_HOME}/bin:${PATH}
+ENV ASCEND_OPP_PATH=${ASCEND_TOOLKIT_HOME}/opp
+# ... You can add other environment variables from the original file as needed ...
+
+WORKDIR /app
+
+# Copy compiled .so files from the build stage
+COPY --from=build /app/lib/ /app
+
+# ==============================================================================
+# FINAL STAGES (TARGETS)
+# ==============================================================================
+
+### Target: full
+# Complete image with all tools, Python bindings, and dependencies
+# ==============================================================================
+FROM base AS full
+
+COPY --from=build /app/full /app
+
+# Install Python dependencies
+RUN yum install -y git python3 python3-pip && \
+    pip3 install --no-cache-dir --upgrade pip setuptools wheel && \
+    pip3 install --no-cache-dir -r requirements.txt && \
+    yum clean all && \
+    rm -rf /var/cache/yum
+
+# You need to provide a tools.sh script as the entrypoint
+ENTRYPOINT ["/app/tools.sh"]
+# If there is no tools.sh, you can set the default to start the server
+# ENTRYPOINT ["/app/llama-server"]
+
+### Target: light
+# Lightweight image containing only llama-cli and llama-completion
+# ==============================================================================
+FROM base AS light
+
+COPY --from=build /app/full/llama-cli /app/full/llama-completion /app
+
+ENTRYPOINT [ "/app/llama-cli" ]
+
+### Target: server
+# Dedicated server image containing only llama-server
+# ==============================================================================
+FROM base AS server
+
+ENV LLAMA_ARG_HOST=0.0.0.0
+
+COPY --from=build /app/full/llama-server /app
+
+HEALTHCHECK --interval=5m CMD [ "curl", "-f", "http://localhost:8080/health" ]
+
+ENTRYPOINT [ "/app/llama-server" ]