-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build . --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
-# TODO: tmp disabled. see for possible re-enable:
-# https://github.com/ggerganov/llama.cpp/pull/10525
-# macOS-latest-swift:
-# runs-on: macos-latest
-#
-# strategy:
-# matrix:
-# destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS']
-#
-# steps:
-# - name: Clone
-# id: checkout
-# uses: actions/checkout@v4
-#
-# - name: Dependencies
-# id: depends
-# continue-on-error: true
-# run: |
-# brew update
-#
-# - name: xcodebuild for swift package
-# id: xcodebuild
-# run: |
-# xcodebuild -scheme llama -destination "${{ matrix.destination }}"
-#
-# - name: Build Swift Example
-# id: make_build_swift_example
-# run: |
-# make swift
+ macOS-latest-swift:
+ runs-on: macos-latest
+
+ strategy:
+ matrix:
+ destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS']
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v4
+
+ - name: Dependencies
+ id: depends
+ continue-on-error: true
+ run: |
+ brew update
+
+ - name: Build llama.cpp with CMake
+ id: cmake_build
+ run: |
+ sysctl -a
+ mkdir build
+ cd build
+ cmake -G Xcode .. \
+ -DGGML_METAL_USE_BF16=ON \
+ -DGGML_METAL_EMBED_LIBRARY=ON \
+ -DLLAMA_BUILD_EXAMPLES=OFF \
+ -DLLAMA_BUILD_TESTS=OFF \
+ -DLLAMA_BUILD_SERVER=OFF \
+ -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64"
+ cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)
+ sudo cmake --install . --config Release
+
+ - name: xcodebuild for swift package
+ id: xcodebuild
+ run: |
+ xcodebuild -scheme llama-Package -destination "${{ matrix.destination }}"
windows-msys2:
runs-on: windows-latest
- name: Checkout code
uses: actions/checkout@v4
+ - name: Build
+ id: cmake_build
+ run: |
+ sysctl -a
+ mkdir build
+ cd build
+ cmake -G Xcode .. \
+ -DGGML_METAL_USE_BF16=ON \
+ -DGGML_METAL_EMBED_LIBRARY=ON \
+ -DLLAMA_BUILD_EXAMPLES=OFF \
+ -DLLAMA_BUILD_TESTS=OFF \
+ -DLLAMA_BUILD_SERVER=OFF \
+ -DCMAKE_SYSTEM_NAME=iOS \
+ -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
+ -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
+ cmake --build . --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
+ sudo cmake --install . --config Release
+
+ - name: xcodebuild for swift package
+ id: xcodebuild
+ run: |
+ xcodebuild -scheme llama-Package -destination 'generic/platform=iOS'
+
- name: Build Xcode project
run: xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' build
./gradlew build --no-daemon
-# freeBSD-latest:
-# runs-on: macos-12
-# steps:
-# - name: Clone
-# uses: actions/checkout@v4
-#
-# - name: Build
-# uses: cross-platform-actions/action@v0.19.0
-# with:
-# operating_system: freebsd
-# version: '13.2'
-# hypervisor: 'qemu'
-# run: |
-# sudo pkg update
-# sudo pkg install -y gmake automake autoconf pkgconf llvm15 openblas
-# gmake CC=/usr/local/bin/clang15 CXX=/usr/local/bin/clang++15 -j `sysctl -n hw.ncpu`
-
release:
if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
import PackageDescription
-var sources = [
- "src/llama.cpp",
- "src/llama-vocab.cpp",
- "src/llama-grammar.cpp",
- "src/llama-sampling.cpp",
- "src/unicode.cpp",
- "src/unicode-data.cpp",
- "ggml/src/ggml.c",
- "ggml/src/ggml-alloc.c",
- "ggml/src/ggml-backend.cpp",
- "ggml/src/ggml-backend-reg.cpp",
- "ggml/src/ggml-cpu/ggml-cpu.c",
- "ggml/src/ggml-cpu/ggml-cpu.cpp",
- "ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp",
- "ggml/src/ggml-cpu/ggml-cpu-hbm.cpp",
- "ggml/src/ggml-cpu/ggml-cpu-quants.c",
- "ggml/src/ggml-cpu/ggml-cpu-traits.cpp",
- "ggml/src/ggml-threading.cpp",
- "ggml/src/ggml-quants.c",
-]
-
-var resources: [Resource] = []
-var linkerSettings: [LinkerSetting] = []
-var cSettings: [CSetting] = [
- .unsafeFlags(["-Wno-shorten-64-to-32", "-O3", "-DNDEBUG"]),
- .unsafeFlags(["-fno-objc-arc"]),
- .headerSearchPath("ggml/src"),
- .headerSearchPath("ggml/src/ggml-cpu"),
- // NOTE: NEW_LAPACK will required iOS version 16.4+
- // We should consider add this in the future when we drop support for iOS 14
- // (ref: ref: https://developer.apple.com/documentation/accelerate/1513264-cblas_sgemm?language=objc)
- // .define("ACCELERATE_NEW_LAPACK"),
- // .define("ACCELERATE_LAPACK_ILP64")
- .define("GGML_USE_CPU"),
-]
-
-
-#if canImport(Darwin)
-sources.append("ggml/src/ggml-common.h")
-sources.append("ggml/src/ggml-metal/ggml-metal.m")
-resources.append(.process("ggml/src/ggml-metal/ggml-metal.metal"))
-linkerSettings.append(.linkedFramework("Accelerate"))
-cSettings.append(
- contentsOf: [
- .define("GGML_USE_ACCELERATE"),
- .define("GGML_USE_METAL"),
- ]
-)
-#endif
-
-#if os(Linux)
- cSettings.append(.define("_GNU_SOURCE"))
-#endif
-
let package = Package(
name: "llama",
platforms: [
.library(name: "llama", targets: ["llama"]),
],
targets: [
- .target(
- name: "llama",
- path: ".",
- exclude: [
- "build",
- "cmake",
- "examples",
- "scripts",
- "models",
- "tests",
- "CMakeLists.txt",
- "Makefile",
- "ggml/src/ggml-metal-embed.metal"
- ],
- sources: sources,
- resources: resources,
- publicHeadersPath: "spm-headers",
- cSettings: cSettings,
- linkerSettings: linkerSettings
- )
- ],
- cxxLanguageStandard: .cxx17
+ .systemLibrary(name: "llama", pkgConfig: "llama"),
+ ]
)
--- /dev/null
+#pragma once
+
+#include <llama.h>
+
--- /dev/null
+module llama [system] {
+ header "llama.h"
+ link "llama"
+ export *
+}
Name: llama
Description: Port of Facebook's LLaMA model in C/C++
Version: @PROJECT_VERSION@
-Libs: -L${libdir} -lllama
+Libs: -L${libdir} -lggml -lggml-base -lllama
Cflags: -I${includedir}
llama_kv_cache_clear(context)
- let t_pp_start = ggml_time_us()
+ let t_pp_start = DispatchTime.now().uptimeNanoseconds / 1000;
if llama_decode(context, batch) != 0 {
print("llama_decode() failed during prompt")
}
llama_synchronize(context)
- let t_pp_end = ggml_time_us()
+ let t_pp_end = DispatchTime.now().uptimeNanoseconds / 1000;
// bench text generation
llama_kv_cache_clear(context)
- let t_tg_start = ggml_time_us()
+ let t_tg_start = DispatchTime.now().uptimeNanoseconds / 1000;
for i in 0..<tg {
llama_batch_clear(&batch)
llama_synchronize(context)
}
- let t_tg_end = ggml_time_us()
+ let t_tg_end = DispatchTime.now().uptimeNanoseconds / 1000;
llama_kv_cache_clear(context)
objects = {
/* Begin PBXBuildFile section */
+ 1809696D2D05A39F00400EE8 /* llama in Frameworks */ = {isa = PBXBuildFile; productRef = 1809696C2D05A39F00400EE8 /* llama */; };
549479CB2AC9E16000E0F78B /* Metal.framework in Frameworks */ = {isa = PBXBuildFile; fileRef = 549479CA2AC9E16000E0F78B /* Metal.framework */; };
79E1D9CD2B4CD16E005F8E46 /* InputButton.swift in Sources */ = {isa = PBXBuildFile; fileRef = 79E1D9CC2B4CD16E005F8E46 /* InputButton.swift */; };
7FA3D2B32B2EA2F600543F92 /* DownloadButton.swift in Sources */ = {isa = PBXBuildFile; fileRef = 7FA3D2B22B2EA2F600543F92 /* DownloadButton.swift */; };
8A3F84242AC4C891005E2EE8 /* models in Resources */ = {isa = PBXBuildFile; fileRef = 8A3F84232AC4C891005E2EE8 /* models */; };
8A907F332AC7138A006146EA /* LibLlama.swift in Sources */ = {isa = PBXBuildFile; fileRef = 8A907F322AC7134E006146EA /* LibLlama.swift */; };
8A9F7C4D2AC332EE008AE1EA /* LlamaState.swift in Sources */ = {isa = PBXBuildFile; fileRef = 8A9F7C4C2AC332EE008AE1EA /* LlamaState.swift */; };
- DF810E132B4A5BA200301144 /* llama in Frameworks */ = {isa = PBXBuildFile; productRef = DF810E122B4A5BA200301144 /* llama */; };
F1FE20E22B465ECA00B45541 /* LoadCustomButton.swift in Sources */ = {isa = PBXBuildFile; fileRef = F1FE20E12B465EC900B45541 /* LoadCustomButton.swift */; };
/* End PBXBuildFile section */
isa = PBXFrameworksBuildPhase;
buildActionMask = 2147483647;
files = (
- DF810E132B4A5BA200301144 /* llama in Frameworks */,
+ 1809696D2D05A39F00400EE8 /* llama in Frameworks */,
549479CB2AC9E16000E0F78B /* Metal.framework in Frameworks */,
8A39BE0A2AC7601100BFEB40 /* Accelerate.framework in Frameworks */,
);
);
name = llama.swiftui;
packageProductDependencies = (
- DF810E122B4A5BA200301144 /* llama */,
+ 1809696C2D05A39F00400EE8 /* llama */,
);
productName = llama.swiftui;
productReference = 8A1C83732AC328BD0096AF73 /* llama.swiftui.app */;
/* End XCConfigurationList section */
/* Begin XCSwiftPackageProductDependency section */
- DF810E122B4A5BA200301144 /* llama */ = {
+ 1809696C2D05A39F00400EE8 /* llama */ = {
isa = XCSwiftPackageProductDependency;
productName = llama;
};
overview / pkg / ggml / sources / llama.cpp / commitdiff