TMP - bench workflow

.github/workflows/bench.yml

@@ -0,0 +1,70 @@
+# Benchmark
+name: Benchmark
+
+on:
+  workflow_dispatch:
+    inputs:
+      gpu-series:
+        description: 'Azure GPU series to run with'
+        required: true
+        type: choice
+        options:
+          - Standard_NC4as_T4_v3
+          - Standard_NC64as_T4_v3
+          - Standard_NC24ads_A100_v4
+          - Standard_NC48ads_A100_v4
+          - Standard_ND96asr_A100_v4
+          - Standard_NC40ads_H100_v5
+          - Standard_NC80adis_H100_v5
+  push:
+    branches:
+      - master
+    paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/tests/**.*']
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/tests/**.*']
+  schedule:
+    -  cron: '0 0 * * *'
+
+jobs:
+  server-baseline:
+    runs-on:
+      group: azure-ubuntu-runners
+      labels:
+        - Standard_NC4as_T4_v3
+    if: ${{ github.event.schedule || github.event.inputs.gpu-series == 'Standard_NC4as_T4_v3' || github.event.pull_request }}
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Dependencies
+        id: depends
+        run: |
+          apt-get update
+          apt-get -y install \
+            build-essential \
+            git \
+            cmake \
+            python3-pip \
+            wget \
+            language-pack-en \
+            libcurl4-openssl-dev
+
+      - name: Build
+        id: cmake_build
+        run: |
+          mkdir build
+          cd build
+          cmake .. \
+              -DLLAMA_NATIVE=OFF \
+              -DLLAMA_BUILD_SERVER=ON \
+              -DLLAMA_CURL=ON \
+              -DLLAMA_CUBLAS=ON \
+              -DCMAKE_CUDA_ARCHITECTURES=native \
+              -DLLAMA_FATAL_WARNINGS=OFF \
+              -DLLAMA_ALL_WARNINGS=OFF \
+              -DCMAKE_BUILD_TYPE=Release;
+          cmake --build . --config Release -j $(nproc) --target server