CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : speed up tests (#15836)

Browse Source 
* server : speed up tests

* clean up

* restore timeout_seconds in some places

* flake8

* explicit offline
This commit is contained in:
Xuan-Son Nguyen
2025-09-06 19:45:24 +07:00
committed by GitHub
parent 61bdfd5298
commit 3c3635d2f2
6 changed files with 90 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/tool_bench.py
View File

@@ -53,7 +53,7 @@ import typer
sys.path.insert(0, Path(__file__).parent.parent.as_posix())
if True:
from tools.server.tests.utils import ServerProcess
from tools.server.tests.unit.test_tool_call import TIMEOUT_SERVER_START, do_test_calc_result, do_test_hello_world, do_test_weather
from tools.server.tests.unit.test_tool_call import do_test_calc_result, do_test_hello_world, do_test_weather
@contextmanager
@@ -335,7 +335,7 @@ def run(
# server.debug = True
with scoped_server(server):
server.start(timeout_seconds=TIMEOUT_SERVER_START)
server.start(timeout_seconds=15 * 60)
for ignore_chat_grammar in [False]:
run(
server,