tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-02 05:15:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : add more test cases (#10569)

Browse Source 
* server : add split model test

* add test speculative

* add invalid cases
This commit is contained in:
Xuan Son Nguyen
2024-11-29 21:48:56 +01:00
committed by GitHub
parent 3a8e9af402
commit b782e5c7d4
6 changed files with 186 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
examples/server/tests/unit/test_infill.py
View File

@ -8,6 +8,7 @@ def create_server():
global server
server = ServerPreset.tinyllama_infill()
def test_infill_without_input_extra():
global server
server.start()
@ -19,6 +20,7 @@ def test_infill_without_input_extra():
assert res.status_code == 200
assert match_regex("(One|day|she|saw|big|scary|bird)+", res.body["content"])
def test_infill_with_input_extra():
global server
server.start()
@ -33,3 +35,23 @@ def test_infill_with_input_extra():
})
assert res.status_code == 200
assert match_regex("(cuts|Jimmy|mom|came|into|the|room)+", res.body["content"])
@pytest.mark.parametrize("input_extra", [
{},
{"filename": "ok"},
{"filename": 123},
{"filename": 123, "text": "abc"},
{"filename": 123, "text": 456},
])
def test_invalid_input_extra_req(input_extra):
global server
server.start()
res = server.make_request("POST", "/infill", data={
"prompt": "Complete this",
"input_extra": [input_extra],
"input_prefix": "#include <cstdio>\n#include \"llama.h\"\n\nint main() {\n int n_threads = llama_",
"input_suffix": "}\n",
})
assert res.status_code == 400
assert "error" in res.body