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 9, 10:00 UTC
[fix] tesdt mcp_tool_calling_streaming with a more complex math question (#32769)
Signed-off-by: Daniel Salib <danielsalib@meta.com>
daniel-salib committed
Jan 29, 2026 at 02:25 UTC
8688c3d460cecdf245775624707f91a5a275038e
1 file changed
+1
-1
tests/entrypoints/openai/responses/test_mcp_tools.py
+1
-1
@@ -221,7 +221,7 @@ class TestMCPEnabled:
221
"server_label": "code_interpreter",
222
}
223
]
224
- input_text = "What is 13 * 24? Use python to calculate the result."
224
+ input_text = "What is 123 * 456? Use python to calculate the result."
225
226
stream_response = await mcp_enabled_client.responses.create(
227
model=model_name,