Merge pull request #6 from arthw/cherry-1220

Cherry 1220

.clang-format

@@ -0,0 +1,161 @@
+---
+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
+BinPackArguments: true
+BinPackParameters: true # 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:           '^<.*\.h>'
+    Priority:        1
+    SortPriority:    0
+  - Regex:           '^<.*'
+    Priority:        2
+    SortPriority:    0
+  - Regex:           '.*'
+    Priority:        3
+    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

@@ -17,8 +17,10 @@ Checks: >
     -clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling,
     performance-*,
     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/full-musa.Dockerfile

@@ -6,6 +6,9 @@ ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_V
 
 FROM ${BASE_MUSA_DEV_CONTAINER} AS build
 
+# MUSA architecture to build for (defaults to all supported archs)
+ARG MUSA_DOCKER_ARCH=default
+
 RUN apt-get update && \
     apt-get install -y build-essential cmake python3 python3-pip git libcurl4-openssl-dev libgomp1
 
@@ -19,7 +22,11 @@ WORKDIR /app
 
 COPY . .
 
-RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
+# Use the default MUSA archs if not specified
+RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
+        export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
+    fi && \
+    cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
     cmake --build build --config Release -j$(nproc) && \
     cp build/bin/* .
 

.devops/full.Dockerfile

@@ -3,23 +3,36 @@ ARG UBUNTU_VERSION=22.04
 FROM ubuntu:$UBUNTU_VERSION AS build
 
 RUN apt-get update && \
-    apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev libgomp1
+    apt-get install -y build-essential git cmake libcurl4-openssl-dev
+
+WORKDIR /app
+
+COPY . .
 
-COPY requirements.txt   requirements.txt
-COPY requirements       requirements
+RUN cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
+    cmake --build build -j $(nproc) && \
+    mkdir -p /app/lib && \
+    find build -name "*.so" -exec cp {} /app/lib/ \;
 
-RUN pip install --upgrade pip setuptools wheel \
-    && pip install -r requirements.txt
+FROM ubuntu:$UBUNTU_VERSION as runtime
 
 WORKDIR /app
 
-COPY . .
+RUN apt-get update && \
+    apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev libgomp1
 
-ENV LLAMA_CURL=1
+COPY requirements.txt   /app/requirements.txt
+COPY requirements       /app/requirements
+COPY .devops/tools.sh   /app/tools.sh
 
+RUN pip install --upgrade pip setuptools wheel && \
+    pip install -r /app/requirements.txt
 
-RUN make -j$(nproc)
+COPY --from=build /app/build/bin/ /app/
+COPY --from=build /app/lib/ /app/
+COPY --from=build /app/convert_hf_to_gguf.py /app/
+COPY --from=build /app/gguf-py /app/gguf-py
 
 ENV LC_ALL=C.utf8
 
-ENTRYPOINT ["/app/.devops/tools.sh"]
+ENTRYPOINT ["/app/tools.sh"]

.devops/llama-cli-musa.Dockerfile

@@ -8,14 +8,21 @@ ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU
 
 FROM ${BASE_MUSA_DEV_CONTAINER} AS build
 
+# MUSA architecture to build for (defaults to all supported archs)
+ARG MUSA_DOCKER_ARCH=default
+
 RUN apt-get update && \
     apt-get install -y build-essential git cmake
 
 WORKDIR /app
 
 COPY . .
 
-RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
+# Use the default MUSA archs if not specified
+RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
+        export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
+    fi && \
+    cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
     cmake --build build --config Release --target llama-cli -j$(nproc) && \
     mkdir -p /app/lib && \
     find build -name "*.so" -exec cp {} /app/lib \;

.devops/llama-cli.Dockerfile

@@ -3,21 +3,27 @@ ARG UBUNTU_VERSION=22.04
 FROM ubuntu:$UBUNTU_VERSION AS build
 
 RUN apt-get update && \
-    apt-get install -y build-essential git
+    apt-get install -y build-essential git cmake libcurl4-openssl-dev
 
 WORKDIR /app
 
 COPY . .
 
-RUN make -j$(nproc) llama-cli
+RUN cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
+    cmake --build build -j $(nproc) && \
+    mkdir -p /app/lib && \
+    find build -name "*.so" -exec cp {} /app/lib/ \;
 
 FROM ubuntu:$UBUNTU_VERSION AS runtime
 
+WORKDIR /app
+
 RUN apt-get update && \
-    apt-get install -y libgomp1
+    apt-get install -y libcurl4-openssl-dev libgomp1 curl
 
-COPY --from=build /app/llama-cli /llama-cli
+COPY --from=build /app/build/bin/llama-cli /app/
+COPY --from=build /app/lib/ /app/
 
 ENV LC_ALL=C.utf8
 
-ENTRYPOINT [ "/llama-cli" ]
+ENTRYPOINT [ "/app/llama-cli" ]

.devops/llama-server-musa.Dockerfile

@@ -8,14 +8,21 @@ ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU
 
 FROM ${BASE_MUSA_DEV_CONTAINER} AS build
 
+# MUSA architecture to build for (defaults to all supported archs)
+ARG MUSA_DOCKER_ARCH=default
+
 RUN apt-get update && \
     apt-get install -y build-essential git cmake libcurl4-openssl-dev
 
 WORKDIR /app
 
 COPY . .
 
-RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
+# Use the default MUSA archs if not specified
+RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
+        export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
+    fi && \
+    cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
     cmake --build build --config Release --target llama-server -j$(nproc) && \
     mkdir -p /app/lib && \
     find build -name "*.so" -exec cp {} /app/lib \;

.devops/llama-server.Dockerfile

@@ -3,27 +3,31 @@ ARG UBUNTU_VERSION=22.04
 FROM ubuntu:$UBUNTU_VERSION AS build
 
 RUN apt-get update && \
-    apt-get install -y build-essential git libcurl4-openssl-dev
+    apt-get install -y build-essential git cmake libcurl4-openssl-dev
 
 WORKDIR /app
 
 COPY . .
 
-ENV LLAMA_CURL=1
-
-RUN make -j$(nproc) llama-server
+RUN cmake -S . -B build -DGGML_BACKEND_DL=ON -DGGML_NATIVE=OFF -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_CURL=ON -DCMAKE_BUILD_TYPE=Release && \
+    cmake --build build -j $(nproc) && \
+    mkdir -p /app/lib && \
+    find build -name "*.so" -exec cp {} /app/lib/ \;
 
 FROM ubuntu:$UBUNTU_VERSION AS runtime
 
+WORKDIR /app
+
 RUN apt-get update && \
     apt-get install -y libcurl4-openssl-dev libgomp1 curl
 
-COPY --from=build /app/llama-server /llama-server
+COPY --from=build /app/build/bin/llama-server /app/
+COPY --from=build /app/lib/ /app/
 
 ENV LC_ALL=C.utf8
 # Must be set to 0.0.0.0 so it can listen to requests from host machine
 ENV LLAMA_ARG_HOST=0.0.0.0
 
 HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
 
-ENTRYPOINT [ "/llama-server" ]
+ENTRYPOINT [ "/app/llama-server" ]

.devops/nix/package.nix

@@ -31,6 +31,7 @@
   # Increases the runtime closure size by ~700M
   useMpi ? false,
   useRocm ? config.rocmSupport,
+  rocmGpuTargets ? builtins.concatStringsSep ";" rocmPackages.clr.gpuTargets,
   enableCurl ? true,
   useVulkan ? false,
   llamaVersion ? "0.0.0", # Arbitrary version, substituted by the flake
@@ -188,7 +189,7 @@ effectiveStdenv.mkDerivation (finalAttrs: {
     ]
     ++ optionals useRocm [
       (cmakeFeature "CMAKE_HIP_COMPILER" "${rocmPackages.llvm.clang}/bin/clang")
-      (cmakeFeature "CMAKE_HIP_ARCHITECTURES" (builtins.concatStringsSep ";" rocmPackages.clr.gpuTargets))
+      (cmakeFeature "CMAKE_HIP_ARCHITECTURES" rocmGpuTargets)
     ]
     ++ optionals useMetalKit [
       (lib.cmakeFeature "CMAKE_C_FLAGS" "-D__ARM_FEATURE_DOTPROD=1")

.devops/nix/python-scripts.nix

@@ -34,7 +34,7 @@ let
 
     # server tests
     openai
-    behave
+    pytest
     prometheus-client
   ];
 in