Merge remote-tracking branch 'upstream/concedo'

YellowRoseCx · May 25, 2024 · fc19589 · fc19589
2 parents 40aa182 + 6530501
commit fc19589
Show file tree

Hide file tree

Showing 141 changed files with 30,777 additions and 18,567 deletions.
diff --git a/.github/labeler.yml b/.github/labeler.yml
@@ -0,0 +1,78 @@
+# https://github.com/actions/labeler
+
+SYCL:
+    - changed-files:
+        - any-glob-to-any-file:
+            - ggml-sycl.h
+            - ggml-sycl.cpp
+            - README-sycl.md
+Nvidia GPU:
+    - changed-files:
+        - any-glob-to-any-file:
+            - ggml-cuda/**
+Vulkan:
+    - changed-files:
+        - any-glob-to-any-file:
+            - ggml_vk_generate_shaders.py
+            - ggml-vulkan*
+documentation:
+    - changed-files:
+        - any-glob-to-any-file:
+            - docs/**
+            - media/**
+testing:
+    - changed-files:
+        - any-glob-to-any-file:
+            - tests/**
+build:
+    - changed-files:
+        - any-glob-to-any-file:
+            - cmake/**
+            - CMakeLists.txt
+            - CMakePresets.json
+            - codecov.yml
+examples:
+    - changed-files:
+        - any-glob-to-any-file: examples/**
+devops:
+    - changed-files:
+        - any-glob-to-any-file:
+            - .devops/**
+            - .github/**
+            - ci/**
+python:
+    - changed-files:
+        - any-glob-to-any-file:
+            - "**/*.py"
+            - requirements/**
+            - gguf-py/**
+            - .flake8
+script:
+    - changed-files:
+        - any-glob-to-any-file:
+            - scripts/**
+android:
+    - changed-files:
+        - any-glob-to-any-file:
+            - examples/llama.android/**
+server:
+    - changed-files:
+        - any-glob-to-any-file:
+            - examples/server/**
+ggml:
+    - changed-files:
+        - any-glob-to-any-file:
+            - ggml.c
+            - ggml.h
+            - ggml-*.c
+            - ggml-*.h
+            - ggml-cuda/**
+nix:
+    - changed-files:
+        - any-glob-to-any-file:
+            - "**/*.nix"
+            - .github/workflows/nix-*.yml
+            - .devops/nix/nixpkgs-instances.nix
+embedding:
+    - changed-files:
+        - any-glob-to-any-file: examples/embedding/
diff --git a/.github/workflows/labeler.yml b/.github/workflows/labeler.yml
@@ -0,0 +1,17 @@
+name: "Pull Request Labeler"
+on:
+- pull_request_target
+
+jobs:
+  labeler:
+    permissions:
+      contents: read
+      pull-requests: write
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        repository: "ggerganov/llama.cpp"
+    - uses: actions/labeler@v5
+      with:
+        configuration-path: '.github/labeler.yml'
diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -471,6 +471,8 @@ set_target_properties(ggml_v3 PROPERTIES POSITION_INDEPENDENT_CODE ON)
 add_library(common2
             common/common.cpp
             common/common.h
+            common/sampling.cpp
+            common/sampling.h
             common/grammar-parser.h
             common/grammar-parser.cpp
             examples/llava/llava.cpp

diff --git a/CMakePresets.json b/CMakePresets.json
@@ -0,0 +1,45 @@
+{
+  "version": 4,
+  "configurePresets": [
+    {
+        "name":  "base",
+        "hidden": true,
+        "generator":   "Ninja",
+        "binaryDir":   "${sourceDir}/build-${presetName}",
+        "cacheVariables": {
+            "CMAKE_EXPORT_COMPILE_COMMANDS": "ON",
+            "CMAKE_INSTALL_RPATH": "$ORIGIN;$ORIGIN/.."
+        }
+    },
+
+    { "name": "debug",   "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "Debug" } },
+    { "name": "release", "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "RelWithDebInfo" } },
+    { "name": "static",  "hidden": true, "cacheVariables": { "LLAMA_STATIC": "ON" } },
+
+    {
+        "name": "arm64-windows-msvc", "hidden": true,
+        "architecture": { "value": "arm64",       "strategy": "external" },
+        "toolset":      { "value": "host=x86_64", "strategy": "external" },
+        "cacheVariables": {
+            "CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/arm64-windows-msvc.cmake"
+        }
+    },
+
+    {
+        "name": "arm64-windows-llvm", "hidden": true,
+        "architecture": { "value": "arm64",       "strategy": "external" },
+        "toolset":      { "value": "host=x86_64", "strategy": "external" },
+        "cacheVariables": {
+            "CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/arm64-windows-llvm.cmake"
+        }
+    },
+
+    { "name": "arm64-windows-llvm-debug"  , "inherits": [ "base", "arm64-windows-llvm",  "debug"   ] },
+    { "name": "arm64-windows-llvm-release", "inherits": [ "base", "arm64-windows-llvm",  "release" ] },
+    { "name": "arm64-windows-llvm+static-release", "inherits": [ "base", "arm64-windows-llvm",  "release", "static" ] },
+
+    { "name": "arm64-windows-msvc-debug"  , "inherits": [ "base", "arm64-windows-msvc",  "debug"   ] },
+    { "name": "arm64-windows-msvc-release", "inherits": [ "base", "arm64-windows-msvc",  "release" ] },
+    { "name": "arm64-windows-msvc+static-release", "inherits": [ "base", "arm64-windows-msvc",  "release", "static" ] }
+  ]
+}
diff --git a/Makefile b/Makefile
@@ -64,9 +64,9 @@ endif
 CUBLASLD_FLAGS =
 CUBLAS_OBJS =
 
-OBJS_FULL += ggml-alloc.o ggml-quants.o unicode.o unicode-data.o sgemm.o common.o grammar-parser.o
-OBJS_SIMPLE += ggml-alloc.o ggml-quants_noavx2.o unicode.o unicode-data.o sgemm_noavx2.o common.o grammar-parser.o
-OBJS_FAILSAFE += ggml-alloc.o ggml-quants_failsafe.o unicode.o unicode-data.o sgemm_failsafe.o common.o grammar-parser.o
+OBJS_FULL += ggml-alloc.o ggml-quants.o unicode.o unicode-data.o sgemm.o common.o sampling.o grammar-parser.o
+OBJS_SIMPLE += ggml-alloc.o ggml-quants_noavx2.o unicode.o unicode-data.o sgemm_noavx2.o common.o sampling.o grammar-parser.o
+OBJS_FAILSAFE += ggml-alloc.o ggml-quants_failsafe.o unicode.o unicode-data.o sgemm_failsafe.o common.o sampling.o grammar-parser.o
 
 #lets try enabling everything
 CFLAGS   += -pthread -s -Wno-deprecated -Wno-deprecated-declarations
@@ -499,6 +499,8 @@ llama.o: llama.cpp ggml.h ggml-alloc.h ggml-backend.h ggml-cuda.h ggml-metal.h l
 	$(CXX) $(CXXFLAGS) -c $< -o $@
 common.o: common/common.cpp common/common.h common/log.h
 	$(CXX) $(CXXFLAGS) -c $< -o $@
+sampling.o: common/sampling.cpp common/common.h common/sampling.h common/log.h
+	$(CXX) $(CXXFLAGS) -c $< -o $@
 console.o: common/console.cpp common/console.h
 	$(CXX) $(CXXFLAGS) -c $< -o $@
 grammar-parser.o: common/grammar-parser.cpp common/grammar-parser.h

diff --git a/cmake/arm64-windows-llvm.cmake b/cmake/arm64-windows-llvm.cmake
@@ -0,0 +1,16 @@
+set( CMAKE_SYSTEM_NAME Windows )
+set( CMAKE_SYSTEM_PROCESSOR arm64 )
+
+set( target arm64-pc-windows-msvc )
+
+set( CMAKE_C_COMPILER    clang )
+set( CMAKE_CXX_COMPILER  clang++ )
+
+set( CMAKE_C_COMPILER_TARGET   ${target} )
+set( CMAKE_CXX_COMPILER_TARGET ${target} )
+
+set( arch_c_flags "-march=armv8.7-a -fvectorize -ffp-model=fast" )
+set( warn_c_flags "-Wno-format -Wno-unused-variable -Wno-unused-function -Wno-gnu-zero-variadic-macro-arguments" )
+
+set( CMAKE_C_FLAGS_INIT   "${arch_c_flags} ${warn_c_flags}" )
+set( CMAKE_CXX_FLAGS_INIT "${arch_c_flags} ${warn_c_flags}" )
diff --git a/cmake/arm64-windows-msvc.cmake b/cmake/arm64-windows-msvc.cmake
@@ -0,0 +1,6 @@
+set( CMAKE_SYSTEM_NAME Windows )
+set( CMAKE_SYSTEM_PROCESSOR arm64 )
+
+set( target arm64-pc-windows-msvc )
+set( CMAKE_C_COMPILER_TARGET   ${target} )
+set( CMAKE_CXX_COMPILER_TARGET ${target} )