Merge branch 'master' into amd-warp-reduce

Author: mofosyne

.devops/main-intel.Dockerfile

@@ -10,14 +10,12 @@ WORKDIR /app
 
 COPY . .
 
-RUN mkdir build && \
-    cd build && \
-    if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
+RUN if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
         echo "LLAMA_SYCL_F16 is set" && \
         export OPT_SYCL_F16="-DLLAMA_SYCL_F16=ON"; \
     fi && \
-    cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx ${OPT_SYCL_F16} && \
-    cmake --build . --config Release --target main
+    cmake -B build -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx ${OPT_SYCL_F16} && \
+    cmake --build build --config Release --target main
 
 FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime
 

.devops/main-vulkan.Dockerfile

@@ -14,10 +14,8 @@ RUN wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key
 # Build it
 WORKDIR /app
 COPY . .
-RUN mkdir build && \
-    cd build && \
-    cmake .. -DLLAMA_VULKAN=1 && \
-    cmake --build . --config Release --target main
+RUN cmake -B build -DLLAMA_VULKAN=1 && \
+    cmake --build build --config Release --target main
 
 # Clean up
 WORKDIR /

.devops/server-intel.Dockerfile

@@ -10,14 +10,12 @@ WORKDIR /app
 
 COPY . .
 
-RUN mkdir build && \
-    cd build && \
-    if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
+RUN if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
         echo "LLAMA_SYCL_F16 is set" && \
         export OPT_SYCL_F16="-DLLAMA_SYCL_F16=ON"; \
     fi && \
-    cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON ${OPT_SYCL_F16} && \
-    cmake --build . --config Release --target server
+    cmake -B build -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON ${OPT_SYCL_F16} && \
+    cmake --build build --config Release --target server
 
 FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime
 

.devops/server-vulkan.Dockerfile

@@ -18,10 +18,8 @@ RUN apt-get update && \
 # Build it
 WORKDIR /app
 COPY . .
-RUN mkdir build && \
-    cd build && \
-    cmake .. -DLLAMA_VULKAN=1 -DLLAMA_CURL=1 && \
-    cmake --build . --config Release --target server
+RUN cmake -B build -DLLAMA_VULKAN=1 -DLLAMA_CURL=1 && \
+    cmake --build build --config Release --target server
 
 # Clean up
 WORKDIR /

.flake8

@@ -1,3 +1,17 @@
 [flake8]
 max-line-length = 125
-ignore = W503
+ignore = E203,E211,E221,E225,E231,E241,E251,E261,E266,E501,E701,E704,W503
+exclude =
+    # Do not traverse examples
+    examples,
+    # Do not include package initializers
+    __init__.py,
+    # No need to traverse our git directory
+    .git,
+    # There's no value in checking cache directories
+    __pycache__,
+    # No need to include the build path
+    build,
+    # This contains builds that we don't want to check
+    dist  # This is generated with `python build .` for package releases
+# max-complexity = 10

.github/workflows/bench.yml

@@ -32,7 +32,7 @@ on:
     -  cron: '04 2 * * *'
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}-${{ github.event.inputs.sha }}
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}-${{ github.event.inputs.sha }}
   cancel-in-progress: true
 
 jobs:
@@ -52,7 +52,19 @@ jobs:
             ftype: q4_0
             pr_comment_enabled: "true"
 
-    if: ${{ github.event.inputs.gpu-series == 'Standard_NC4as_T4_v3' || github.event.schedule || github.event.pull_request || github.head_ref == 'master' || github.ref_name == 'master' || github.event.push.ref == 'refs/heads/master' }}
+    if: |
+      inputs.gpu-series == 'Standard_NC4as_T4_v3'
+      || (
+        github.event_name == 'schedule'
+        && github.ref_name == 'master'
+        && github.repository_owner == 'ggerganov'
+      )
+      || github.event_name == 'pull_request_target'
+      || (
+        github.event_name == 'push'
+        && github.event.ref == 'refs/heads/master'
+        && github.repository_owner == 'ggerganov'
+      )
     steps:
       - name: Clone
         id: checkout
@@ -96,9 +108,7 @@ jobs:
         id: cmake_build
         run: |
           set -eux
-          mkdir build
-          cd build
-          cmake .. \
+          cmake -B build \
               -DLLAMA_NATIVE=OFF \
               -DLLAMA_BUILD_SERVER=ON \
               -DLLAMA_CURL=ON \
@@ -109,7 +119,7 @@ jobs:
               -DLLAMA_FATAL_WARNINGS=OFF \
               -DLLAMA_ALL_WARNINGS=OFF \
               -DCMAKE_BUILD_TYPE=Release;
-          cmake --build . --config Release -j $(nproc) --target server
+          cmake --build build --config Release -j $(nproc) --target server
 
       - name: Download the dataset
         id: download_dataset

.github/workflows/build.yml

@@ -32,6 +32,8 @@ jobs:
       - name: Clone
         id: checkout
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
       - name: Dependencies
         id: depends
@@ -52,7 +54,7 @@ jobs:
         id: cmake_test
         run: |
           cd build
-          ctest -L main --verbose --timeout 900
+          ctest -L 'main|curl' --verbose --timeout 900
 
       - name: Determine tag name
         id: tag
@@ -88,6 +90,8 @@ jobs:
       - name: Clone
         id: checkout
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
       - name: Dependencies
         id: depends
@@ -101,7 +105,9 @@ jobs:
           sysctl -a
           mkdir build
           cd build
-          cmake -DLLAMA_FATAL_WARNINGS=ON -DLLAMA_METAL_EMBED_LIBRARY=ON -DLLAMA_CURL=ON ..
+          # Metal is disabled due to intermittent failures with Github runners not having a GPU:
+          # https://github.com/ggerganov/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313
+          cmake -DLLAMA_FATAL_WARNINGS=ON -DLLAMA_METAL=OFF -DLLAMA_CURL=ON ..
           cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)
 
       - name: Test
@@ -204,26 +210,28 @@ jobs:
       - name: Clone
         id: checkout
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
       - name: Dependencies
         id: depends
         run: |
           sudo apt-get update
-          sudo apt-get install build-essential
+          sudo apt-get install build-essential libcurl4-openssl-dev
 
       - name: Build
         id: cmake_build
         run: |
           mkdir build
           cd build
-          cmake .. -DLLAMA_FATAL_WARNINGS=ON
+          cmake .. -DLLAMA_FATAL_WARNINGS=ON -DLLAMA_CURL=ON
           cmake --build . --config Release -j $(nproc)
 
       - name: Test
         id: cmake_test
         run: |
           cd build
-          ctest -L main --verbose --timeout 900
+          ctest -L 'main|curl' --verbose --timeout 900
 
       - name: Test llama2c conversion
         id: llama2c_test
@@ -236,6 +244,33 @@ jobs:
           ./bin/convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
           ./bin/main -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
 
+      - name: Determine tag name
+        id: tag
+        shell: bash
+        run: |
+          BUILD_NUMBER="$(git rev-list --count HEAD)"
+          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
+          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
+            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
+          else
+            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
+            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Pack artifacts
+        id: pack_artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        run: |
+          cp LICENSE ./build/bin/
+          zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-x64.zip ./build/bin/*
+
+      - name: Upload artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-artifact@v4
+        with:
+          path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-x64.zip
+          name: llama-bin-ubuntu-x64.zip
+
 #  ubuntu-latest-cmake-sanitizer:
 #    runs-on: ubuntu-latest
 #
@@ -558,6 +593,63 @@ jobs:
         run: |
             make swift
 
+  windows-msys2:
+    runs-on: windows-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - { sys: UCRT64,  env: ucrt-x86_64,  build: Release }
+          - { sys: CLANG64, env: clang-x86_64, build: Release }
+
+    steps:
+      - name: Clone
+        uses: actions/checkout@v4
+
+      - name: Setup ${{ matrix.sys }}
+        uses: msys2/setup-msys2@v2
+        with:
+          update: true
+          msystem: ${{matrix.sys}}
+          install: >-
+            base-devel
+            mingw-w64-${{matrix.env}}-toolchain
+            mingw-w64-${{matrix.env}}-cmake
+            mingw-w64-${{matrix.env}}-openblas
+
+      - name: Build using make
+        shell: msys2 {0}
+        run: |
+            make -j $(nproc)
+
+      - name: Clean after building using make
+        shell: msys2 {0}
+        run: |
+            make clean
+
+      - name: Build using make w/ OpenBLAS
+        shell: msys2 {0}
+        run: |
+            make LLAMA_OPENBLAS=1 -j $(nproc)
+
+      - name: Build using CMake
+        shell: msys2 {0}
+        run: |
+            cmake -B build
+            cmake --build build --config ${{ matrix.build }} -j $(nproc)
+
+      - name: Clean after building using CMake
+        shell: msys2 {0}
+        run: |
+            rm -rf build
+
+      - name: Build using CMake w/ OpenBLAS
+        shell: msys2 {0}
+        run: |
+            cmake -B build -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
+            cmake --build build --config ${{ matrix.build }} -j $(nproc)
+
   windows-latest-cmake:
     runs-on: windows-latest
 
@@ -938,6 +1030,12 @@ jobs:
       - name: Download artifacts
         id: download-artifact
         uses: actions/download-artifact@v4
+        with:
+          path: ./artifact
+
+      - name: Move artifacts
+        id: move_artifacts
+        run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release
 
       - name: Create release
         id: create_release
@@ -956,15 +1054,15 @@ jobs:
             const path = require('path');
             const fs = require('fs');
             const release_id = '${{ steps.create_release.outputs.id }}';
-            for (let file of await fs.readdirSync('./artifact')) {
+            for (let file of await fs.readdirSync('./artifact/release')) {
               if (path.extname(file) === '.zip') {
                 console.log('uploadReleaseAsset', file);
                 await github.repos.uploadReleaseAsset({
                   owner: context.repo.owner,
                   repo: context.repo.repo,
                   release_id: release_id,
                   name: file,
-                  data: await fs.readFileSync(`./artifact/${file}`)
+                  data: await fs.readFileSync(`./artifact/release/${file}`)
                 });
               }
             }

.github/workflows/close-issue.yml

@@ -12,7 +12,7 @@ jobs:
     steps:
       - uses: actions/stale@v5
         with:
-          exempt-issue-labels: "refactor,help wanted,good first issue,research"
+          exempt-issue-labels: "refactor,help wanted,good first issue,research,bug"
           days-before-issue-stale: 30
           days-before-issue-close: 14
           stale-issue-label: "stale"

.github/workflows/docker.yml

@@ -91,14 +91,20 @@ jobs:
             echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
           fi
 
+      - name: Downcase github.repository_owner
+        run: |
+          echo "repository_owner_lowercase=${GITHUB_REPOSITORY_OWNER@L}" >> $GITHUB_ENV
+        env:
+          GITHUB_REPOSITORY_OWNER: '${{ github.repository_owner }}'
+
       - name: Build and push Docker image (versioned)
         if: github.event_name == 'push'
         uses: docker/build-push-action@v4
         with:
           context: .
           push: true
           platforms: ${{ matrix.config.platforms }}
-          tags: "ghcr.io/${{ github.repository_owner }}/llama.cpp:${{ matrix.config.tag }}-${{ env.COMMIT_SHA }}"
+          tags: "ghcr.io/${{ env.repository_owner_lowercase }}/llama.cpp:${{ matrix.config.tag }}-${{ env.COMMIT_SHA }}"
           file: ${{ matrix.config.dockerfile }}
 
       - name: Build and push Docker image (tagged)
@@ -107,5 +113,5 @@ jobs:
           context: .
           push: ${{ github.event_name == 'push' }}
           platforms: ${{ matrix.config.platforms }}
-          tags: "ghcr.io/${{ github.repository_owner }}/llama.cpp:${{ matrix.config.tag }},ghcr.io/${{ github.repository_owner }}/llama.cpp:${{ matrix.config.tag }}-${{ steps.tag.outputs.name }}"
+          tags: "ghcr.io/${{ env.repository_owner_lowercase }}/llama.cpp:${{ matrix.config.tag }},ghcr.io/${{ env.repository_owner_lowercase }}/llama.cpp:${{ matrix.config.tag }}-${{ steps.tag.outputs.name }}"
           file: ${{ matrix.config.dockerfile }}

.github/workflows/python-lint.yml

@@ -20,5 +20,4 @@ jobs:
       - name: flake8 Lint
         uses: py-actions/flake8@v2
         with:
-            ignore: "E203,E211,E221,E225,E231,E241,E251,E261,E266,E501,E701,E704,W503"
-            exclude: "examples/*,examples/*/**,*/**/__init__.py"
+            plugins: "flake8-no-print"