root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-13 04:00:16 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

updated server test to handle 503 HTML

Browse Source
This commit is contained in:
VJHack 2024-09-11 22:54:52 -05:00
parent 9d3424a3c1
commit 5ca179c899
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
examples/server/tests/features/steps/steps.py
View File

@ -1208,7 +1208,10 @@ async def wait_for_slots_status(context,
while True:
async with await session.get(f'{base_url}/slots', params=params) as slots_response:
status_code = slots_response.status
slots = await slots_response.json()
try:
slots = await slots_response.json()
except:
slots = await slots_response.text()
if context.debug:
print(f"slots responses {slots}\n")
if status_code == 503 and status_code == expected_http_status_code:
@ -1372,4 +1375,4 @@ def start_server_background(context):
thread_stderr = threading.Thread(target=server_log, args=(context.server_process.stderr, sys.stderr))
thread_stderr.start()
print(f"server pid={context.server_process.pid}, behave pid={os.getpid()}")
print(f"server pid={context.server_process.pid}, behave pid={os.getpid()}")