tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 20:05:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : move end-user examples to tools directory (#13249)

Browse Source 
* llama : move end-user examples to tools directory

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit is contained in:
Diego Devesa
2025-05-02 20:27:13 +02:00
committed by GitHub
parent b34443923c
commit 1d36b3670b
213 changed files with 226 additions and 190 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
scripts/tool_bench.py
View File

@ -2,7 +2,7 @@
'''
Simplistic tool call benchmarks for llama-server and ollama.
Essentially runs the tests at server/examples/server/tests/unit/test_tool_call.py N times, at different temperatures and on different backends (current llama-server, baseline llama-server and ollama),
Essentially runs the tests at server/tools/server/tests/unit/test_tool_call.py N times, at different temperatures and on different backends (current llama-server, baseline llama-server and ollama),
and plots the results of multiple runs (from same .jsonl file or multiple ones) as a success rate heatmap.
Simple usage example:
@ -51,8 +51,8 @@ import typer
sys.path.insert(0, Path(__file__).parent.parent.as_posix())
if True:
from examples.server.tests.utils import ServerProcess
from examples.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.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
@contextmanager