From 5d2156e8934b07d71d5b925682cd38e0724e4bec Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Tue, 30 Dec 2025 14:00:36 +0200
Subject: [PATCH] ci : add server workflow with backend sampling

---
 .github/workflows/server.yml | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/.github/workflows/server.yml b/.github/workflows/server.yml
index f9e2a79af7..5694feb2c9 100644
--- a/.github/workflows/server.yml
+++ b/.github/workflows/server.yml
@@ -41,6 +41,10 @@ jobs:
         include:
           - build_type: Release
             sanitizer: ""
+            extra_args: ""
+          - build_type: Release
+            sanitizer: ""
+            extra_args: "LLAMA_ARG_BACKEND_SAMPLING=1"
       fail-fast: false # While -DLLAMA_SANITIZE_THREAD=ON is broken
 
     steps:
@@ -65,6 +69,12 @@ jobs:
           fetch-depth: 0
           ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
 
+      - name: Build
+        id: cmake_build
+        run: |
+          cmake -B build -DLLAMA_CURL=OFF -DLLAMA_BUILD_BORINGSSL=ON
+          cmake --build build --config ${{ matrix.build_type }} -j ${env:NUMBER_OF_PROCESSORS} --target llama-server
+
       - name: Python setup
         id: setup_python
         uses: actions/setup-python@v5
@@ -76,6 +86,14 @@ jobs:
         run: |
           pip install -r tools/server/tests/requirements.txt
 
+      - name: Tests
+        id: server_integration_tests
+        if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) && matrix.build_type == 'Release' }}
+        run: |
+          cd tools/server/tests
+          export ${{ matrix.extra_args }}
+          pytest -v -x -m "not slow"
+
   server-windows:
     runs-on: windows-2022