tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-17 21:51:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

server : better security control for public deployments (#9776)

Browse Source 
* server : more explicit endpoint access settings

* protect /props endpoint

* fix tests

* update server docs

* fix typo

* fix tests
This commit is contained in:
Xuan Son Nguyen
2024-10-08 13:27:04 +02:00
committed by GitHub
parent fa42aa6d89
commit 458367a906
8 changed files with 126 additions and 116 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/tests/features/steps/steps.py
View File

@@ -1299,7 +1299,8 @@ async def wait_for_slots_status(context,
async with aiohttp.ClientSession(timeout=DEFAULT_TIMEOUT_SECONDS) as session:
while True:
async with await session.get(f'{base_url}/slots', params=params) as slots_response:
headers = {'Authorization': f'Bearer {context.server_api_key}'}
async with await session.get(f'{base_url}/slots', params=params, headers=headers) as slots_response:
status_code = slots_response.status
slots = await slots_response.json()
if context.debug:
@@ -1387,6 +1388,7 @@ def start_server_background(context):
context.server_path = os.environ['LLAMA_SERVER_BIN_PATH']
server_listen_addr = context.server_fqdn
server_args = [
'--slots', # requires to get slot status via /slots endpoint
'--host', server_listen_addr,
'--port', context.server_port,
]