Merge branch 'master' of github.com:ggerganov/llama.cpp into grammar-example

* 'master' of github.com:ggerganov/llama.cpp:
  ggml-cuda : perform cublas mat mul of quantized types as f16 (ggml-org#3412)
  llama.cpp : add documentation about rope_freq_base and scale values (ggml-org#3401)
  train : fix KQ_pos allocation (ggml-org#3392)
  llama : quantize up to 31% faster on Linux and Windows with mmap (ggml-org#3206)
  readme : update hot topics + model links (ggml-org#3399)
  readme : add link to grammars app (ggml-org#3388)
  swift : fix build on xcode 15 (ggml-org#3387)
  build : enable more non-default compiler warnings (ggml-org#3200)
  ggml_tensor: update the structure comments. (ggml-org#3283)
  ggml : release the requested thread pool resource (ggml-org#3292)
  llama.cpp : split llama_context_params into model and context params (ggml-org#3301)
  ci : multithreaded builds (ggml-org#3311)
  train : finetune LORA (ggml-org#2632)
  gguf : basic type checking in gguf_get_* (ggml-org#3346)
  gguf : make token scores and types optional (ggml-org#3347)
  ci : disable freeBSD builds due to lack of VMs (ggml-org#3381)
  llama : custom attention mask + parallel decoding + no context swaps (ggml-org#3228)
  docs : mark code as Bash (ggml-org#3375)
  readme : add Mistral AI release 0.1 (ggml-org#3362)
  ggml-cuda : perform cublas fp16 matrix multiplication as fp16 (ggml-org#3370)

Author: joelkuiper

.github/workflows/build.yml

@@ -38,13 +38,13 @@ jobs:
       - name: Build
         id: make_build
         run: |
-          CC=gcc-8 make
+          CC=gcc-8 make -j $(nproc)
 
       - name: Test
         id: make_test
         run: |
-          CC=gcc-8 make tests
-          make test
+          CC=gcc-8 make tests -j $(nproc)
+          make test -j $(nproc)
 
   ubuntu-latest-cmake:
     runs-on: ubuntu-latest
@@ -66,7 +66,7 @@ jobs:
           mkdir build
           cd build
           cmake ..
-          cmake --build . --config Release
+          cmake --build . --config Release -j $(nproc)
 
       - name: Test
         id: cmake_test
@@ -101,7 +101,7 @@ jobs:
           mkdir build
           cd build
           cmake .. -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON -DCMAKE_BUILD_TYPE=${{ matrix.build_type }}
-          cmake --build . --config ${{ matrix.build_type }}
+          cmake --build . --config ${{ matrix.build_type }} -j $(nproc)
 
       - name: Test
         id: cmake_test
@@ -135,7 +135,7 @@ jobs:
           mkdir build
           cd build
           cmake -DLLAMA_MPI=ON ..
-          cmake --build . --config Release
+          cmake --build . --config Release -j $(nproc)
 
       - name: Test
         id: cmake_test
@@ -160,13 +160,13 @@ jobs:
       - name: Build
         id: make_build
         run: |
-          make
+          make -j $(sysctl -n hw.logicalcpu)
 
       - name: Test
         id: make_test
         run: |
-          make tests
-          make test
+          make tests -j $(sysctl -n hw.logicalcpu)
+          make test -j $(sysctl -n hw.logicalcpu)
 
   macOS-latest-cmake:
     runs-on: macos-latest
@@ -189,7 +189,7 @@ jobs:
           mkdir build
           cd build
           cmake -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF ..
-          cmake --build . --config Release
+          cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)
 
       - name: Test
         id: cmake_test
@@ -223,7 +223,7 @@ jobs:
             -DLLAMA_BUILD_SERVER=OFF \
             -DCMAKE_SYSTEM_NAME=iOS \
             -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0
-          cmake --build . --config Release
+          cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)
 
   macOS-latest-cmake-tvos:
     runs-on: macos-latest
@@ -251,7 +251,7 @@ jobs:
             -DLLAMA_BUILD_SERVER=OFF \
             -DCMAKE_SYSTEM_NAME=tvOS \
             -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0
-          cmake --build . --config Release
+          cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)
 
   windows-latest-cmake:
     runs-on: windows-latest
@@ -324,7 +324,7 @@ jobs:
           mkdir build
           cd build
           cmake .. ${{ matrix.defines }}
-          cmake --build . --config Release
+          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
 
       - name: Add clblast.dll
         id: add_clblast_dll
@@ -415,7 +415,7 @@ jobs:
           mkdir build
           cd build
           cmake .. -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON -DBUILD_SHARED_LIBS=ON
-          cmake --build . --config Release
+          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
 
       - name: Determine tag name
         id: tag
@@ -457,22 +457,22 @@ jobs:
           path: |
             cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip
 
-  freeBSD-latest:
-    runs-on: macos-12
-    steps:
-    - name: Clone
-      uses: actions/checkout@v3
-
-    - name: Build
-      uses: cross-platform-actions/[email protected]
-      with:
-        operating_system: freebsd
-        version: '13.2'
-        hypervisor: 'qemu'
-        run: |
-            sudo pkg update
-            sudo pkg install -y gmake automake autoconf pkgconf llvm15 clinfo clover opencl clblast openblas
-            gmake CC=/usr/local/bin/clang15 CXX=/usr/local/bin/clang++15
+#  freeBSD-latest:
+#    runs-on: macos-12
+#    steps:
+#    - name: Clone
+#      uses: actions/checkout@v3
+#
+#    - name: Build
+#      uses: cross-platform-actions/[email protected]
+#      with:
+#        operating_system: freebsd
+#        version: '13.2'
+#        hypervisor: 'qemu'
+#        run: |
+#            sudo pkg update
+#            sudo pkg install -y gmake automake autoconf pkgconf llvm15 clinfo clover opencl clblast 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' }}

.gitignore

@@ -45,13 +45,18 @@ models-mnt
 /main
 /metal
 /perplexity
+/q8dot
 /quantize
 /quantize-stats
 /result
 /save-load-state
 /server
 /simple
+/batched
+/export-lora
+/finetune
 /speculative
+/parallel
 /train-text-from-scratch
 /vdot
 build-info.h

CMakeLists.txt

@@ -414,37 +414,38 @@ endif()
 
 if (LLAMA_ALL_WARNINGS)
     if (NOT MSVC)
-        set(c_flags
-            -Wall
-            -Wextra
-            -Wpedantic
-            -Wcast-qual
-            -Wdouble-promotion
-            -Wshadow
-            -Wstrict-prototypes
-            -Wpointer-arith
-            -Wmissing-prototypes
-            -Werror=implicit-int
-            -Wno-unused-function
-        )
-        set(cxx_flags
-            -Wall
-            -Wextra
-            -Wpedantic
-            -Wcast-qual
-            -Wmissing-declarations
-            -Wno-unused-function
-            -Wno-multichar
-        )
-        if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
-            # g++ only
-            set(cxx_flags ${cxx_flags} -Wno-format-truncation -Wno-array-bounds)
+        set(warning_flags -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function)
+        set(c_flags -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int
+            -Werror=implicit-function-declaration)
+        set(cxx_flags -Wmissing-declarations -Wmissing-noreturn)
+
+        if (CMAKE_C_COMPILER_ID MATCHES "Clang")
+            set(warning_flags ${warning_flags} -Wunreachable-code-break -Wunreachable-code-return)
+            set(cxx_flags ${cxx_flags} -Wmissing-prototypes -Wextra-semi)
+
+            if (
+                (CMAKE_C_COMPILER_ID STREQUAL "Clang"      AND CMAKE_C_COMPILER_VERSION VERSION_GREATER_EQUAL 3.8.0) OR
+                (CMAKE_C_COMPILER_ID STREQUAL "AppleClang" AND CMAKE_C_COMPILER_VERSION VERSION_GREATER_EQUAL 7.3.0)
+            )
+                set(c_flags ${c_flags} -Wdouble-promotion)
+            endif()
+        elseif (CMAKE_C_COMPILER_ID STREQUAL "GNU")
+            set(c_flags ${c_flags} -Wdouble-promotion)
+            set(cxx_flags ${cxx_flags} -Wno-array-bounds)
+
+            if (CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 7.1.0)
+                set(cxx_flags ${cxx_flags} -Wno-format-truncation)
+            endif()
+            if (CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 8.1.0)
+                set(cxx_flags ${cxx_flags} -Wextra-semi)
+            endif()
         endif()
     else()
         # todo : msvc
     endif()
 
     add_compile_options(
+            ${warning_flags}
             "$<$<COMPILE_LANGUAGE:C>:${c_flags}>"
             "$<$<COMPILE_LANGUAGE:CXX>:${cxx_flags}>"
     )