llama : move end-user examples to tools directory (#13249)

* llama : move end-user examples to tools directory --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2025-05-02 20:27:13 +02:00 · 2025-05-02 20:27:13 +02:00 · 1d36b3670b
commit 1d36b3670b
parent b34443923c
213 changed files with 226 additions and 190 deletions
--- a/.github/labeler.yml
+++ b/.github/labeler.yml
@ -45,7 +45,9 @@ build:
            - CMakePresets.json
 examples:
    - changed-files:
-        - any-glob-to-any-file: examples/**
+        - any-glob-to-any-file:
+            - examples/**
+            - tools/**
 devops:
    - changed-files:
        - any-glob-to-any-file:
@ -70,7 +72,7 @@ android:
 server:
    - changed-files:
        - any-glob-to-any-file:
-            - examples/server/**
+            - tools/server/**
 ggml:
    - changed-files:
        - any-glob-to-any-file:
--- a/.github/workflows/bench.yml.disabled
+++ b/.github/workflows/bench.yml.disabled
@ -27,10 +27,10 @@ on:
  push:
    branches:
      - master
-    paths: ['llama.cpp', 'ggml.c', 'ggml-backend.cpp', 'ggml-quants.c', '**/*.cu', 'examples/server/*.h*', 'examples/server/*.cpp']
+    paths: ['llama.cpp', 'ggml.c', 'ggml-backend.cpp', 'ggml-quants.c', '**/*.cu', 'tools/server/*.h*', 'tools/server/*.cpp']
  pull_request_target:
    types: [opened, synchronize, reopened]
-    paths: ['llama.cpp', 'ggml.c', 'ggml-backend.cpp', 'ggml-quants.c', '**/*.cu', 'examples/server/*.h*', 'examples/server/*.cpp']
+    paths: ['llama.cpp', 'ggml.c', 'ggml-backend.cpp', 'ggml-quants.c', '**/*.cu', 'tools/server/*.h*', 'tools/server/*.cpp']
  schedule:
    -  cron: '04 2 * * *'

@ -69,7 +69,7 @@ jobs:
      - name: Install python env
        id: pipenv
        run: |
-          cd examples/server/bench
+          cd tools/server/bench
          python3 -m venv venv
          source venv/bin/activate
          pip install -r requirements.txt
@ -79,7 +79,7 @@ jobs:
        run: |
          wget --quiet https://github.com/prometheus/prometheus/releases/download/v2.51.0/prometheus-2.51.0.linux-amd64.tar.gz
          tar xzf prometheus*.tar.gz --strip-components=1
-          ./prometheus --config.file=examples/server/bench/prometheus.yml &
+          ./prometheus --config.file=tools/server/bench/prometheus.yml &
          while ! nc -z localhost 9090; do
            sleep 0.1
          done
@ -92,7 +92,7 @@ jobs:
      - name: Install k6 and xk6-sse
        id: k6_installation
        run: |
-          cd examples/server/bench
+          cd tools/server/bench
          go install go.k6.io/xk6/cmd/xk6@latest
          xk6 build master \
              --with github.com/phymbert/xk6-sse
@ -116,7 +116,7 @@ jobs:
      - name: Download the dataset
        id: download_dataset
        run: |
-          cd examples/server/bench
+          cd tools/server/bench
          wget --quiet https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json

      - name: Server bench
@ -126,7 +126,7 @@ jobs:
        run: |
          set -eux

-          cd examples/server/bench
+          cd tools/server/bench
          source venv/bin/activate
          python bench.py \
              --runner-label ${{ env.RUNNER_LABEL }} \
@ -157,9 +157,9 @@ jobs:
          name: bench-server-${{ github.job }}-${{ env.RUNNER_LABEL }}-${{ matrix.model }}-${{ matrix.ftype }}
          compression-level: 9
          path: |
-            examples/server/bench/*.jpg
-            examples/server/bench/*.json
-            examples/server/bench/*.log
+            tools/server/bench/*.jpg
+            tools/server/bench/*.json
+            tools/server/bench/*.log

      - name: Commit status
        uses: Sibz/github-status-action@v1
@ -178,17 +178,17 @@ jobs:
        with:
          client_id: ${{secrets.IMGUR_CLIENT_ID}}
          path: |
-            examples/server/bench/prompt_tokens_seconds.jpg
-            examples/server/bench/predicted_tokens_seconds.jpg
-            examples/server/bench/kv_cache_usage_ratio.jpg
-            examples/server/bench/requests_processing.jpg
+            tools/server/bench/prompt_tokens_seconds.jpg
+            tools/server/bench/predicted_tokens_seconds.jpg
+            tools/server/bench/kv_cache_usage_ratio.jpg
+            tools/server/bench/requests_processing.jpg

      - name: Extract mermaid
        id: set_mermaid
        run: |
          set -eux

-          cd examples/server/bench
+          cd tools/server/bench
          PROMPT_TOKENS_SECONDS=$(cat prompt_tokens_seconds.mermaid)
          echo "PROMPT_TOKENS_SECONDS<<EOF" >> $GITHUB_ENV
          echo "$PROMPT_TOKENS_SECONDS" >> $GITHUB_ENV
--- a/.github/workflows/build-linux-cross.yml
+++ b/.github/workflows/build-linux-cross.yml
@ -34,6 +34,7 @@ jobs:
          cmake -B build -DCMAKE_BUILD_TYPE=Release \
                         -DGGML_OPENMP=OFF \
                         -DLLAMA_BUILD_EXAMPLES=ON \
+                         -DLLAMA_BUILD_TOOLS=ON \
                         -DLLAMA_BUILD_TESTS=OFF \
                         -DCMAKE_SYSTEM_NAME=Linux \
                         -DCMAKE_SYSTEM_PROCESSOR=riscv64 \
@ -80,6 +81,7 @@ jobs:
                         -DGGML_VULKAN=ON \
                         -DGGML_OPENMP=OFF \
                         -DLLAMA_BUILD_EXAMPLES=ON \
+                         -DLLAMA_BUILD_TOOLS=ON \
                         -DLLAMA_BUILD_TESTS=OFF \
                         -DCMAKE_SYSTEM_NAME=Linux \
                         -DCMAKE_SYSTEM_PROCESSOR=riscv64 \
@ -125,6 +127,7 @@ jobs:
                         -DGGML_VULKAN=ON \
                         -DGGML_OPENMP=OFF \
                         -DLLAMA_BUILD_EXAMPLES=ON \
+                         -DLLAMA_BUILD_TOOLS=ON \
                         -DLLAMA_BUILD_TESTS=OFF \
                         -DCMAKE_SYSTEM_NAME=Linux \
                         -DCMAKE_SYSTEM_PROCESSOR=aarch64 \
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@ -633,6 +633,7 @@ jobs:
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DLLAMA_BUILD_COMMON=OFF \
            -DLLAMA_BUILD_EXAMPLES=OFF \
+            -DLLAMA_BUILD_TOOLS=OFF \
            -DLLAMA_BUILD_TESTS=OFF \
            -DLLAMA_BUILD_SERVER=OFF \
            -DCMAKE_SYSTEM_NAME=iOS \
@ -669,6 +670,7 @@ jobs:
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DLLAMA_BUILD_COMMON=OFF \
            -DLLAMA_BUILD_EXAMPLES=OFF \
+            -DLLAMA_BUILD_TOOLS=OFF \
            -DLLAMA_BUILD_TESTS=OFF \
            -DLLAMA_BUILD_SERVER=OFF \
            -DCMAKE_SYSTEM_NAME=tvOS \
@ -699,6 +701,7 @@ jobs:
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DLLAMA_BUILD_COMMON=OFF \
            -DLLAMA_BUILD_EXAMPLES=OFF \
+            -DLLAMA_BUILD_TOOLS=OFF \
            -DLLAMA_BUILD_TESTS=OFF \
            -DLLAMA_BUILD_SERVER=OFF \
            -DCMAKE_SYSTEM_NAME=visionOS \
@ -739,6 +742,7 @@ jobs:
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DLLAMA_CURL=OFF \
            -DLLAMA_BUILD_EXAMPLES=OFF \
+            -DLLAMA_BUILD_TOOLS=OFF \
            -DLLAMA_BUILD_TESTS=OFF \
            -DLLAMA_BUILD_SERVER=OFF \
            -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64"
@ -1417,6 +1421,7 @@ jobs:
            -DGGML_METAL_EMBED_LIBRARY=ON \
            -DLLAMA_CURL=OFF \
            -DLLAMA_BUILD_EXAMPLES=OFF \
+            -DLLAMA_BUILD_TOOLS=OFF \
            -DLLAMA_BUILD_TESTS=OFF \
            -DLLAMA_BUILD_SERVER=OFF \
            -DCMAKE_SYSTEM_NAME=iOS \
--- a/.github/workflows/server.yml
+++ b/.github/workflows/server.yml
@ -15,10 +15,10 @@ on:
  push:
    branches:
      - master
-    paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/**.*']
+    paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'tools/server/**.*']
  pull_request:
    types: [opened, synchronize, reopened]
-    paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/**.*']
+    paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'tools/server/**.*']

 env:
  LLAMA_LOG_COLORS: 1
@ -74,7 +74,7 @@ jobs:
      - name: Tests dependencies
        id: test_dependencies
        run: |
-          pip install -r examples/server/tests/requirements.txt
+          pip install -r tools/server/tests/requirements.txt

      # Setup nodejs (to be used for verifying bundled index.html)
      - uses: actions/setup-node@v4
@ -84,14 +84,14 @@ jobs:
      - name: WebUI - Install dependencies
        id: webui_lint
        run: |
-          cd examples/server/webui
+          cd tools/server/webui
          npm ci

      - name: WebUI - Check code format
        id: webui_format
        run: |
          git config --global --add safe.directory $(realpath .)
-          cd examples/server/webui
+          cd tools/server/webui
          git status

          npm run format
@ -108,7 +108,7 @@ jobs:
        id: verify_server_index_html
        run: |
          git config --global --add safe.directory $(realpath .)
-          cd examples/server/webui
+          cd tools/server/webui
          git status

          npm run build
@ -161,21 +161,21 @@ jobs:
        env:
          GITHUB_ACTIONS: "true"
        run: |
-          cd examples/server/tests
+          cd tools/server/tests
          ./tests.sh

      - name: Tests (sanitizers)
        id: server_integration_tests_sanitizers
        if: ${{ matrix.sanitizer != '' }}
        run: |
-          cd examples/server/tests
+          cd tools/server/tests
          LLAMA_SANITIZE=1 ./tests.sh

      - name: Slow tests
        id: server_integration_tests_slow
        if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }}
        run: |
-          cd examples/server/tests
+          cd tools/server/tests
          SLOW_TESTS=1 ./tests.sh


@ -211,7 +211,7 @@ jobs:
      - name: Tests dependencies
        id: test_dependencies
        run: |
-          pip install -r examples/server/tests/requirements.txt
+          pip install -r tools/server/tests/requirements.txt

      - name: Copy Libcurl
        id: prepare_libcurl
@ -224,7 +224,7 @@ jobs:
        id: server_integration_tests
        if: ${{ !matrix.disabled_on_pr || !github.event.pull_request }}
        run: |
-          cd examples/server/tests
+          cd tools/server/tests
          $env:PYTHONIOENCODING = ":replace"
          pytest -v -x -m "not slow"

@ -232,6 +232,6 @@ jobs:
        id: server_integration_tests_slow
        if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }}
        run: |
-          cd examples/server/tests
+          cd tools/server/tests
          $env:SLOW_TESTS = "1"
          pytest -v -x