kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-19 17:25:17 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][chore] Enable multiple postprocess workers tests for chat completions api (#7602)

Browse Source 
Signed-off-by: Junyi Xu <219237550+JunyiXu-nv@users.noreply.github.com>
This commit is contained in:
JunyiXu-nv 2025-09-15 12:16:44 +08:00 committed by GitHub
parent b69e3e9f99
commit a2c45d82c3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
tests/unittest/llmapi/apps/_test_openai_chat_harmony.py
View File

@ -14,10 +14,18 @@ def model():
return "gpt_oss/gpt-oss-20b/"
@pytest.fixture(scope="module",
params=[0, 2],
ids=["disable_processpool", "enable_processpool"])
def num_postprocess_workers(request):
return request.param
@pytest.fixture(scope="module")
def server(model: str):
def server(model: str, num_postprocess_workers: int):
model_path = get_model_path(model)
with RemoteOpenAIServer(model_path) as remote_server:
args = ["--num_postprocess_workers", f"{num_postprocess_workers}"]
with RemoteOpenAIServer(model_path, args) as remote_server:
yield remote_server