vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

common: llama_load_model_from_url using --model-url (#6098)

Browse source 
* common: llama_load_model_from_url with libcurl dependency

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Pierrick Hymbert 2024-03-17 19:12:37 +01:00 • committed by GitHub
parent cd776c37c9
commit d01b3c4c32
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
16 changed files with 397 additions and 55 deletions
Download patch file Download diff file Expand all files Collapse all files

93
examples/server/tests/features/environment.py
View file

@ -1,10 +1,12 @@
import errno
import os
import socket
import subprocess
import time
from contextlib import closing
import signal
import socket
import sys
import time
import traceback
from contextlib import closing
import psutil
def before_scenario(context, scenario):
@ -20,33 +22,40 @@ def before_scenario(context, scenario):
def after_scenario(context, scenario):
if context.server_process is None:
return
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\n")
try:
if 'server_process' not in context or context.server_process is None:
return
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\n")
if not pid_exists(context.server_process.pid):
assert False, f"Server not running pid={context.server_process.pid} ..."
if not pid_exists(context.server_process.pid):
assert False, f"Server not running pid={context.server_process.pid} ..."
server_graceful_shutdown(context)
server_graceful_shutdown(context)
# Wait few for socket to free up
time.sleep(0.05)
# Wait few for socket to free up
time.sleep(0.05)
attempts = 0
while pid_exists(context.server_process.pid) or is_server_listening(context.server_fqdn, context.server_port):
server_kill(context)
time.sleep(0.1)
attempts += 1
if attempts > 5:
server_kill_hard(context)
attempts = 0
while pid_exists(context.server_process.pid) or is_server_listening(context.server_fqdn, context.server_port):
server_kill(context)
time.sleep(0.1)
attempts += 1
if attempts > 5:
server_kill_hard(context)
except:
exc = sys.exception()
print("error in after scenario: \n")
print(exc)
print("*** print_tb: \n")
traceback.print_tb(exc.__traceback__, file=sys.stdout)
def server_graceful_shutdown(context):
@ -67,11 +76,11 @@ def server_kill_hard(context):
path = context.server_path
print(f"Server dangling exits, hard killing force {pid}={path}...\n")
if os.name == 'nt':
process = subprocess.check_output(['taskkill', '/F', '/pid', str(pid)]).decode()
print(process)
else:
os.kill(-pid, signal.SIGKILL)
try:
psutil.Process(pid).kill()
except psutil.NoSuchProcess:
return False
return True
def is_server_listening(server_fqdn, server_port):
@ -84,17 +93,9 @@ def is_server_listening(server_fqdn, server_port):
def pid_exists(pid):
"""Check whether pid exists in the current process table."""
if pid < 0:
try:
psutil.Process(pid)
except psutil.NoSuchProcess:
return False
if os.name == 'nt':
output = subprocess.check_output(['TASKLIST', '/FI', f'pid eq {pid}']).decode()
print(output)
return "No tasks are running" not in output
else:
try:
os.kill(pid, 0)
except OSError as e:
return e.errno == errno.EPERM
else:
return True
return True