root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-11 21:39:52 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

Revert "server bench: fix bench not waiting for model load (#7284)" (#7334)

Browse Source 
This reverts commit 583fd6b000.
This commit is contained in:
Pierrick Hymbert 2024-05-16 20:43:45 +02:00 committed by GitHub
parent 9afdffe70e
commit 24ecb58168
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
examples/server/bench/bench.py
View File

@ -293,14 +293,13 @@ def start_server_background(args):
def is_server_listening(server_fqdn, server_port):
try:
url = f"{server_fqdn}:{server_port}/health"
if not url.startswith("http://"):
url = f"http://{url}"
result = requests.get(url)
return result.status_code == 200
except Exception:
return False
with closing(socket.socket(socket.AF_INET, socket.SOCK_STREAM)) as sock:
result = sock.connect_ex((server_fqdn, server_port))
_is_server_listening = result == 0
if _is_server_listening:
print(f"server is listening on {server_fqdn}:{server_port}...")
return _is_server_listening
def escape_metric_name(metric_name):
return re.sub('[^A-Z0-9]', '_', metric_name.upper())