mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-04 09:32:00 +00:00
525213d2f5
* server: tests: init scenarios - health and slots endpoints - completion endpoint - OAI compatible chat completion requests w/ and without streaming - completion multi users scenario - multi users scenario on OAI compatible endpoint with streaming - multi users with total number of tokens to predict exceeds the KV Cache size - server wrong usage scenario, like in Infinite loop of "context shift" #3969 - slots shifting - continuous batching - embeddings endpoint - multi users embedding endpoint: Segmentation fault #5655 - OpenAI-compatible embeddings API - tokenize endpoint - CORS and api key scenario * server: CI GitHub workflow --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
68 lines
2.3 KiB
Python
68 lines
2.3 KiB
Python
import os
|
|
import socket
|
|
import subprocess
|
|
import time
|
|
from contextlib import closing
|
|
from signal import SIGKILL
|
|
|
|
|
|
def before_scenario(context, scenario):
|
|
print(f"\x1b[33;42mStarting new scenario: {scenario.name}!\x1b[0m")
|
|
port = 8080
|
|
if 'PORT' in os.environ:
|
|
port = int(os.environ['PORT'])
|
|
if is_server_listening("localhost", port):
|
|
assert False, "Server already started"
|
|
|
|
|
|
def after_scenario(context, scenario):
|
|
if scenario.status == "failed":
|
|
if 'GITHUB_ACTIONS' in os.environ:
|
|
print(f"\x1b[33;101mSCENARIO FAILED: {scenario.name} server logs:\x1b[0m\n\n")
|
|
if os.path.isfile('llama.log'):
|
|
with closing(open('llama.log', 'r')) as f:
|
|
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")
|
|
|
|
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} ...")
|
|
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} ...")
|
|
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} ...")
|
|
process = subprocess.run(['killall', '-9', context.server_path],
|
|
stderr=subprocess.PIPE,
|
|
universal_newlines=True)
|
|
print(process)
|
|
|
|
|
|
def is_server_listening(server_fqdn, server_port):
|
|
with closing(socket.socket(socket.AF_INET, socket.SOCK_STREAM)) as sock:
|
|
result = sock.connect_ex((server_fqdn, server_port))
|
|
return result == 0
|
|
|
|
|
|
def pid_exists(pid):
|
|
"""Check whether pid exists in the current process table."""
|
|
import errno
|
|
if pid < 0:
|
|
return False
|
|
try:
|
|
os.kill(pid, 0)
|
|
except OSError as e:
|
|
return e.errno == errno.EPERM
|
|
else:
|
|
return True
|