A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[CI] Fix test_tool_id_kimi_k2 (#26787)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Oct 14, 2025 at 18:27 UTC
780eb03d9b5da36325ab5ebddbf23bec31a789df
1 file changed
+8
-5
tests/entrypoints/openai/test_completion_with_function_calling.py
+8
-5
@@ -247,10 +247,10 @@ async def test_tool_id_kimi_k2(
247
)
248
assert chat_completion.choices[0].message.tool_calls is not None
249
assert len(chat_completion.choices[0].message.tool_calls) > 0
250
- assert (
251
- chat_completion.choices[0].message.tool_calls[0].id
252
- == "functions.get_current_weather:0"
253
- )
250
+ assert chat_completion.choices[0].message.tool_calls[0].id in [
251
+ "functions.get_current_weather:0",
252
+ "functions.get_forecast:1",
253
+ ]
254
else:
255
# Streaming test
256
output_stream = await k2_client.chat.completions.create(
@@ -266,7 +266,10 @@ async def test_tool_id_kimi_k2(
266
if chunk.choices and chunk.choices[0].delta.tool_calls:
267
output.extend(chunk.choices[0].delta.tool_calls)
268
for o in output:
269
- assert o.id is None or o.id == "functions.get_current_weather:0"
269
+ assert o.id is None or o.id in [
270
+ "functions.get_current_weather:0",
271
+ "functions.get_forecast:1",
272
+ ]
273
274
275
@pytest.mark.asyncio