Merge branch 'ggerganov:master' into master

.github/workflows/build.yml

@@ -64,6 +64,40 @@ jobs:
           cd build
           ctest --output-on-failure
 
+  ubuntu-latest-cmake-sanitizer:
+    runs-on: ubuntu-latest
+
+    continue-on-error: true
+
+    strategy:
+      matrix:
+        sanitizer: [ADDRESS, THREAD, UNDEFINED]
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v1
+
+      - name: Dependencies
+        id: depends
+        run: |
+          sudo apt-get update
+          sudo apt-get install build-essential
+
+      - name: Build
+        id: cmake_build
+        run: |
+          mkdir build
+          cd build
+          cmake .. -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON
+          cmake --build . --config Release
+
+      - name: Test
+        id: cmake_test
+        run: |
+          cd build
+          ctest --output-on-failure
+
   macOS-latest-make:
     runs-on: macos-latest
 
@@ -112,6 +146,16 @@ jobs:
   windows-latest-cmake:
     runs-on: windows-latest
 
+    strategy:
+      matrix:
+        include:
+         - build: 'avx2'
+           defines: ''
+         - build: 'avx'
+           defines: '-DLLAMA_AVX2=OFF'
+         - build: 'avx512'
+           defines: '-DLLAMA_AVX512=ON'
+
     steps:
       - name: Clone
         id: checkout
@@ -122,11 +166,21 @@ jobs:
         run: |
           mkdir build
           cd build
-          cmake ..
+          cmake .. ${{ matrix.defines }}
           cmake --build . --config Release
 
+      - name: Check AVX512F support
+        id: check_avx512f
+        if: ${{ matrix.build == 'avx512' }}
+        continue-on-error: true
+        run: |
+          cd build
+          Set-Content -Path .\avx512f.exe -Value ([Convert]::FromBase64String('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')) -AsByteStream
+          .\avx512f.exe && echo " AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo " AVX512F: NO"
+
       - name: Test
         id: cmake_test
+        if: ${{ matrix.build != 'avx512' || env.HAS_AVX512F == '1' }} # Test AVX-512 only when possible
         run: |
           cd build
           ctest -C Release --output-on-failure
@@ -140,12 +194,39 @@ jobs:
         id: pack_artifacts
         if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
         run: |
-          7z a llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-x64.zip .\build\bin\Release\*
+          7z a llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\*
+
+      - name: Upload artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-artifact@v3
+        with:
+          path: |
+            llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip
+
+  release:
+    if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+
+    runs-on: ubuntu-latest
+
+    needs:
+      - ubuntu-latest-make
+      - ubuntu-latest-cmake
+      - macOS-latest-make
+      - macOS-latest-cmake
+      - windows-latest-cmake
+
+    steps:
+      - name: Download artifacts
+        id: download-artifact
+        uses: actions/download-artifact@v3
+
+      - name: Get commit hash
+        id: commit
+        uses: pr-mpt/actions-commit-hash@v2
 
       - name: Create release
         id: create_release
-        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: anzz1/action-create-release@v1
-        uses: zendesk/action-create-release@v1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
@@ -153,15 +234,25 @@ jobs:
 
       - name: Upload release
         id: upload_release
-        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/github-script@v3
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }} 
+          github-token: ${{secrets.GITHUB_TOKEN}}
-          asset_path: .\llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-x64.zip
+          script: |
-          asset_name: llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-x64.zip
+            const path = require('path');
-          asset_content_type: application/octet-stream
+            const fs = require('fs');
+            const release_id = '${{ steps.create_release.outputs.id }}';
+            for (let file of await fs.readdirSync('./artifact')) {
+              if (path.extname(file) === '.zip') {
+                console.log('uploadReleaseAsset', file);
+                await github.repos.uploadReleaseAsset({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  release_id: release_id,
+                  name: file,
+                  data: await fs.readFileSync(`./artifact/${file}`)
+                });
+              }
+            }
 
 #  ubuntu-latest-gcc:
 #    runs-on: ubuntu-latest

CMakeLists.txt

@@ -54,6 +54,7 @@ option(LLAMA_SANITIZE_UNDEFINED     "llama: enable undefined sanitizer"
 # instruction set specific
 option(LLAMA_AVX                    "llama: enable AVX"                                     ON)
 option(LLAMA_AVX2                   "llama: enable AVX2"                                    ON)
+option(LLAMA_AVX512                 "llama: enable AVX512"                                  OFF)
 option(LLAMA_FMA                    "llama: enable FMA"                                     ON)
 
 # 3rd party libs
@@ -75,14 +76,17 @@ find_package(Threads REQUIRED)
 if (NOT MSVC)
     if (LLAMA_SANITIZE_THREAD)
         add_compile_options(-fsanitize=thread)
+        link_libraries(-fsanitize=thread)
     endif()
 
     if (LLAMA_SANITIZE_ADDRESS)
         add_compile_options(-fsanitize=address -fno-omit-frame-pointer)
+        link_libraries(-fsanitize=address)
     endif()
 
     if (LLAMA_SANITIZE_UNDEFINED)
         add_compile_options(-fsanitize=undefined)
+        link_libraries(-fsanitize=undefined)
     endif()
 endif()
 
@@ -185,7 +189,9 @@ if (${CMAKE_SYSTEM_PROCESSOR} MATCHES "arm" OR ${CMAKE_SYSTEM_PROCESSOR} MATCHES
 elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "^(x86_64|i686|AMD64)$")
     message(STATUS "x86 detected")
     if (MSVC)
-        if (LLAMA_AVX2)
+        if (LLAMA_AVX512)
+            add_compile_options(/arch:AVX512)
+        elseif (LLAMA_AVX2)
             add_compile_options(/arch:AVX2)
         elseif (LLAMA_AVX)
             add_compile_options(/arch:AVX)
@@ -201,6 +207,12 @@ elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "^(x86_64|i686|AMD64)$")
         if (LLAMA_AVX2)
             add_compile_options(-mavx2)
         endif()
+        if (LLAMA_AVX512)
+            add_compile_options(-mavx512f)
+            # add_compile_options(-mavx512cd)
+            # add_compile_options(-mavx512dq)
+            # add_compile_options(-mavx512bw)
+        endif()
     endif()
 else()
     # TODO: support PowerPC

convert-pth-to-ggml.py

@@ -161,7 +161,7 @@ def main():
 
     for p in range(n_parts):
 
-        print(f"Processing part {p}\n")
+        print(f"Processing part {p+1} of {n_parts}\n")
 
         fname_model = f"{dir_model}/consolidated.0{p}.pth"
         fname_out = f"{dir_model}/ggml-model-{ftype_str[ftype]}.bin{'' if p == 0 else '.' + str(p)}"

examples/main/main.cpp

@@ -23,6 +23,8 @@
 extern "C" __declspec(dllimport) void* __stdcall GetStdHandle(unsigned long nStdHandle);
 extern "C" __declspec(dllimport) int __stdcall GetConsoleMode(void* hConsoleHandle, unsigned long* lpMode);
 extern "C" __declspec(dllimport) int __stdcall SetConsoleMode(void* hConsoleHandle, unsigned long dwMode);
+extern "C" __declspec(dllimport) int __stdcall SetConsoleCP(unsigned int wCodePageID);
+extern "C" __declspec(dllimport) int __stdcall SetConsoleOutputCP(unsigned int wCodePageID);
 #endif
 
 #define ANSI_COLOR_RED     "\x1b[31m"
@@ -44,17 +46,6 @@ enum console_state {
 static console_state con_st = CONSOLE_STATE_DEFAULT;
 static bool con_use_color = false;
 
-void enable_console_colors() {
-#if defined (_WIN32)
-    // Enable ANSI colors on Windows 10+
-    unsigned long dwMode = 0;
-    void* hConOut = GetStdHandle((unsigned long)-11); // STD_OUTPUT_HANDLE (-11)
-    if (hConOut && hConOut != (void*)-1 && GetConsoleMode(hConOut, &dwMode) && !(dwMode & 0x4)) {
-        SetConsoleMode(hConOut, dwMode | 0x4); // ENABLE_VIRTUAL_TERMINAL_PROCESSING (0x4)
-    }
-#endif
-}
-
 void set_console_state(console_state new_st) {
     if (!con_use_color) return;
     // only emit color code if state changed
@@ -90,6 +81,32 @@ void sigint_handler(int signo) {
 }
 #endif
 
+#if defined (_WIN32)
+void win32_console_init(void) {
+    unsigned long dwMode = 0;
+    void* hConOut = GetStdHandle((unsigned long)-11); // STD_OUTPUT_HANDLE (-11)
+    if (!hConOut || hConOut == (void*)-1 || !GetConsoleMode(hConOut, &dwMode)) {
+        hConOut = GetStdHandle((unsigned long)-12); // STD_ERROR_HANDLE (-12)
+        if (hConOut && (hConOut == (void*)-1 || !GetConsoleMode(hConOut, &dwMode))) {
+            hConOut = 0;
+        }
+    }
+    if (hConOut) {
+        // Enable ANSI colors on Windows 10+
+        if (con_use_color && !(dwMode & 0x4)) {
+            SetConsoleMode(hConOut, dwMode | 0x4); // ENABLE_VIRTUAL_TERMINAL_PROCESSING (0x4)
+        }
+        // Set console output codepage to UTF8
+        SetConsoleOutputCP(65001); // CP_UTF8
+    }
+    void* hConIn = GetStdHandle((unsigned long)-10); // STD_INPUT_HANDLE (-10)
+    if (hConIn && hConIn != (void*)-1 && GetConsoleMode(hConIn, &dwMode)) {
+        // Set console input codepage to UTF8
+        SetConsoleCP(65001); // CP_UTF8
+    }
+}
+#endif
+
 int main(int argc, char ** argv) {
     gpt_params params;
     params.model = "models/llama-7B/ggml-model.bin";
@@ -98,6 +115,15 @@ int main(int argc, char ** argv) {
         return 1;
     }
 
+
+    // save choice to use color for later
+    // (note for later: this is a slightly awkward choice)
+    con_use_color = params.use_color;
+
+#if defined (_WIN32)
+    win32_console_init();
+#endif
+
     if (params.perplexity) {
         printf("\n************\n");
         printf("%s: please use the 'perplexity' tool for perplexity calculations\n", __func__);
@@ -130,10 +156,6 @@ int main(int argc, char ** argv) {
         params.prompt = gpt_random_prompt(rng);
     }
 
-    // save choice to use color for later
-    // (note for later: this is a slightly awkward choice)
-    con_use_color = params.use_color;
-
 //    params.prompt = R"(// this function checks if the number n is prime
 //bool is_prime(int n) {)";
 
@@ -285,9 +307,6 @@ int main(int argc, char ** argv) {
     int n_consumed = 0;
 
     // the first thing we will do is to output the prompt, so set color accordingly
-    if (params.use_color) {
-        enable_console_colors();
-    }
     set_console_state(CONSOLE_STATE_PROMPT);
 
     std::vector<llama_token> embd;