biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Frontend] Refactor prompt processing (#4028)

Browse Source 
Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
Cyrus Leung
2024-07-23 01:13:53 +08:00
committed by GitHub
parent 89c1c6a196
commit 739b61a348
24 changed files with 699 additions and 391 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/engine/output_processor/test_stop_checker.py
View File

@@ -35,8 +35,8 @@ def sequence_with_eos(text: str, eos_token: str,
@pytest.mark.parametrize(["text_wo_eos", "eos_token", "eos_token_id"], [
("This text ends with EOS token", "</s>", 2),
])
@pytest.mark.parametrize("ignore_eos", [True, False, None])
@pytest.mark.parametrize("include_stop_str_in_output", [True, False, None])
@pytest.mark.parametrize("ignore_eos", [True, False])
@pytest.mark.parametrize("include_stop_str_in_output", [True, False])
@pytest.mark.skip_global_cleanup
def test_stop_on_eos_token(text_wo_eos: str, eos_token: str, eos_token_id: int,
ignore_eos: bool, include_stop_str_in_output: bool):

5
tests/entrypoints/openai/test_serving_chat.py
View File

@@ -32,7 +32,10 @@ async def _async_serving_chat_init():
model_config,
served_model_names=[MODEL_NAME],
response_role="assistant",
chat_template=CHAT_TEMPLATE)
chat_template=CHAT_TEMPLATE,
lora_modules=None,
prompt_adapters=None,
request_logger=None)
return serving_completion