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 10, 07:45 UTC
[Frontend] Fix Flaky MCP Streaming Test (#32153)
Signed-off-by: Daniel Salib <danielsalib@meta.com>
daniel-salib committed
Jan 12, 2026 at 02:03 UTC
d7b2e57097dae8a620c28eddf663adad2a8329c5
1 file changed
+1
-1
tests/entrypoints/openai/responses/test_harmony.py
+1
-1
@@ -925,7 +925,7 @@ async def test_mcp_code_interpreter_streaming(client: OpenAI, model_name: str, s
925
}
926
]
927
input_text = (
928
- "Calculate 15 * 32 using python. "
928
+ "Calculate 123 * 456 using python. "
929
"The python interpreter is not stateful and you must print to see the output."
930
)
931