server: ci: windows build and tests

.github/workflows/server.yml

@@ -11,6 +11,7 @@ on:
   push:
     branches:
       - master
+      - hp/server/ci/windows/init
     paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/tests/**.*']
   pull_request:
     types: [opened, synchronize, reopened]
@@ -90,3 +91,46 @@ jobs:
         run: |
           cd examples/server/tests
           PORT=8888 ./tests.sh --stop --no-skipped --no-capture --tags slow
+
+
+  server-windows:
+    runs-on: windows-latest
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Build
+        id: cmake_build
+        run: |
+          mkdir build
+          cd build
+          cmake ..  -DLLAMA_BUILD_SERVER=ON -DCMAKE_BUILD_TYPE=Release ;
+          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} --target server
+
+      - name: Python setup
+        id: setup_python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Tests dependencies
+        id: test_dependencies
+        run: |
+          pip install -r examples/server/tests/requirements.txt
+
+      - name: Tests
+        id: server_integration_tests
+        run: |
+          cd examples/server/tests
+          behave.exe --summary --stop --no-capture --exclude 'issues|wrong_usages|passkey' --tags llama.cpp
+
+      - name: Slow tests
+        id: server_integration_tests_slow
+        if: ${{ github.event.schedule != '' || github.event.inputs.slow_tests == 'true' }}
+        run: |
+          cd examples/server/tests
+          behave.exe --stop --no-skipped --no-capture --tags slow

examples/server/tests/features/environment.py

@@ -3,7 +3,7 @@ import socket
 import subprocess
 import time
 from contextlib import closing
-from signal import SIGKILL
+import signal
 
 
 def before_scenario(context, scenario):
@@ -29,31 +29,43 @@ def after_scenario(context, scenario):
                     for line in f:
                         print(line)
         if not is_server_listening(context.server_fqdn, context.server_port):
-            print("\x1b[33;101mERROR: Server stopped listening\x1b[0m")
+            print("\x1b[33;101mERROR: Server stopped listening\x1b[0m\n")
 
     if not pid_exists(context.server_process.pid):
         assert False, f"Server not running pid={context.server_process.pid} ..."
 
-    print(f"stopping server pid={context.server_process.pid} ...")
+    kill_server(context)
-    context.server_process.kill()
+
     # Wait few for socket to free up
     time.sleep(0.05)
 
     attempts = 0
     while is_server_listening(context.server_fqdn, context.server_port):
-        print(f"stopping server pid={context.server_process.pid} ...")
+        context.server_process.kill()
-        os.kill(context.server_process.pid, SIGKILL)
         time.sleep(0.1)
         attempts += 1
         if attempts > 5:
-            print(f"Server dangling exits, killing all {context.server_path} ...")
+            if os.name == 'nt':
-            process = subprocess.run(['killall', '-9', context.server_path],
+                print(f"Server dangling exits, task killing force {context.server_process.pid} ...\n")
-                                     stderr=subprocess.PIPE,
+                process = subprocess.run(['taskkill', '/F', '/pid', str(context.server_process.pid)],
-                                     universal_newlines=True)
+                                         stderr=subprocess.PIPE)
+            else:
+                print(f"Server dangling exits, killing all {context.server_path} ...\n")
+                process = subprocess.run(['killall', '-9', context.server_path],
+                                         stderr=subprocess.PIPE)
             print(process)
 
 
+def kill_server(context):
+    print(f"stopping server pid={context.server_process.pid} ...\n")
+    if os.name == 'nt':
+        os.kill(context.server_process.pid, signal.CTRL_C_EVENT)
+    else:
+        os.kill(context.server_process.pid, signal.SIGKILL)
+
+
 def is_server_listening(server_fqdn, server_port):
+    print(f"is server listening on {server_fqdn}:{server_port}...\n")
     with closing(socket.socket(socket.AF_INET, socket.SOCK_STREAM)) as sock:
         result = sock.connect_ex((server_fqdn, server_port))
         return result == 0

examples/server/tests/features/server.feature

@@ -47,7 +47,7 @@ Feature: llama.cpp server
     Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
     """
     And   a completion request with no api error
-    Then  64 tokens are predicted matching fun|Annaks|popcorns
+    Then  64 tokens are predicted matching fun|Annaks|popcorns|pictry
     And   the completion is  truncated
     And   109 prompt tokens are processed
 

examples/server/tests/features/steps/steps.py

@@ -285,17 +285,17 @@ def step_seed(context, seed):
 
 @step(u'a prefix prompt')
 def step_prompt_prefix(context):
-    context.prompt_prefix = context.text
+    context.prompt_prefix = context_text(context)
 
 
 @step(u'a junk suffix prompt')
 def step_prompt_junk_suffix(context):
-    context.prompt_junk_suffix = context.text
+    context.prompt_junk_suffix = context_text(context)
 
 
 @step(u'a suffix prompt')
 def step_prompt_suffix(context):
-    context.prompt_suffix = context.text
+    context.prompt_suffix = context_text(context)
 
 
 @step(u'{n_ga:d} group attention factor'
@@ -311,7 +311,7 @@ def step_impl(context, n_ga_w):
 
 @step(u'a passkey prompt template')
 def step_prompt_passkey(context):
-    context.prompt_passkey = context.text
+    context.prompt_passkey = context_text(context)
 
 
 @step(u'{n_prompts:d} fixed prompts')
@@ -371,7 +371,7 @@ async def step_oai_chat_completions(context, api_error):
 
 @step(u'a prompt')
 def step_a_prompt(context):
-    context.prompts.append(context.text)
+    context.prompts.append(context_text(context))
     context.n_prompts = len(context.prompts)
 
 
@@ -464,7 +464,7 @@ async def all_prompts_are_predicted(context, expected_predicted_n=None):
 @async_run_until_complete
 async def step_compute_embedding(context):
     context.n_prompts = 1
-    context.embeddings = await request_embedding(context.text, base_url=context.base_url)
+    context.embeddings = await request_embedding(context_text(context), base_url=context.base_url)
 
 
 @step(u'all embeddings are the same')
@@ -491,6 +491,7 @@ async def step_all_embeddings_are_the_same(context):
                 print(f"{msg}\n")
             assert np.isclose(similarity, 1.0, rtol=1e-05, atol=1e-08, equal_nan=False), msg
 
+
 @step(u'embeddings are generated')
 def step_assert_embeddings(context):
     assert context.n_prompts == len(context.embeddings), (f"unexpected response:\n"
@@ -504,7 +505,7 @@ def step_assert_embeddings(context):
 @async_run_until_complete
 async def step_oai_compute_embeddings(context):
     context.n_prompts = 1
-    context.embeddings = await request_oai_embeddings(context.text,
+    context.embeddings = await request_oai_embeddings(context_text(context),
                                                       base_url=context.base_url,
                                                       user_api_key=context.user_api_key,
                                                       model=context.model)
@@ -552,7 +553,7 @@ async def all_embeddings_are_generated(context):
 @step(u'tokenizing')
 @async_run_until_complete
 async def step_tokenize(context):
-    context.tokenized_text = context.text
+    context.tokenized_text = context_text(context)
     async with aiohttp.ClientSession() as session:
         async with session.post(f'{context.base_url}/tokenize',
                                 json={
@@ -1007,12 +1008,22 @@ async def completions_seed(context):
         else context.server_seed if hasattr(context, 'server_seed') else None
 
 
+def context_text(context):
+    return context.text.replace('\r', '')
+
+
 def start_server_background(context):
-    context.server_path = '../../../build/bin/server'
+    if os.name == 'nt':
+        context.server_path = '../../../build/bin/Release/server.exe'
+    else:
+        context.server_path = '../../../build/bin/server'
     if 'LLAMA_SERVER_BIN_PATH' in os.environ:
         context.server_path = os.environ['LLAMA_SERVER_BIN_PATH']
+    server_listen_addr = context.server_fqdn
+    if os.name == 'nt':
+        server_listen_addr = '0.0.0.0'
     server_args = [
-        '--host', context.server_fqdn,
+        '--host', server_listen_addr,
         '--port', context.server_port,
         '--model', context.model_file
     ]
@@ -1045,7 +1056,17 @@ def start_server_background(context):
     if 'SERVER_LOG_FORMAT_JSON' not in os.environ:
         server_args.extend(['--log-format', "text"])
     print(f"starting server with: {context.server_path} {server_args}\n")
+    flags = 0
+    if 'nt' == os.name:
+        flags |= 0x00000008  # DETACHED_PROCESS
+        flags |= 0x00000200  # CREATE_NEW_PROCESS_GROUP
+        flags |= 0x08000000  # CREATE_NO_WINDOW
+
+    pkwargs = {
+        'close_fds': True,  # close stdin/stdout/stderr on child
+        'creationflags': flags,
+    }
     context.server_process = subprocess.Popen(
         [str(arg) for arg in [context.server_path, *server_args]],
-        close_fds=True)
+        **pkwargs)
-    print(f"server pid={context.server_process.pid}")
+    print(f"server pid={context.server_process.pid}, behave pid={os.getpid()}")