llama.cpp/examples/server/tests/unit/test_infill.py
Xuan Son Nguyen 45abe0f74e
server : replace behave with pytest (#10416)
* server : replace behave with pytest

* fix test on windows

* misc

* add more tests

* more tests

* styling

* log less, fix embd test

* added all sequential tests

* fix coding style

* fix save slot test

* add parallel completion test

* fix parallel test

* remove feature files

* update test docs

* no cache_prompt for some tests

* add test_cache_vs_nocache_prompt
2024-11-26 16:20:18 +01:00

36 lines
1.2 KiB
Python

import pytest
from utils import *
server = ServerPreset.tinyllama_infill()
@pytest.fixture(scope="module", autouse=True)
def create_server():
global server
server = ServerPreset.tinyllama_infill()
def test_infill_without_input_extra():
global server
server.start()
res = server.make_request("POST", "/infill", data={
"prompt": "Complete this",
"input_prefix": "#include <cstdio>\n#include \"llama.h\"\n\nint main() {\n int n_threads = llama_",
"input_suffix": "}\n",
})
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()
res = server.make_request("POST", "/infill", data={
"prompt": "Complete this",
"input_extra": [{
"filename": "llama.h",
"text": "LLAMA_API int32_t llama_n_threads();\n"
}],
"input_prefix": "#include <cstdio>\n#include \"llama.h\"\n\nint main() {\n int n_threads = llama_",
"input_suffix": "}\n",
})
assert res.status_code == 200
assert match_regex("(cuts|Jimmy|mom|came|into|the|room)+", res.body["content"])