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 15, 19:45 UTC
[BugFix]Fix performance serving benchmark when enable profiling (#14737)
Signed-off-by: wangli <wangli858794774@gmail.com>
Li Wang committed
Mar 14, 2025 at 15:02 UTC
09269b31274952bc5fff73023d108e00eb891068
1 file changed
+1
-1
benchmarks/backend_request_func.py
+1
-1
@@ -333,7 +333,7 @@ async def async_request_openai_chat_completions(
333
) -> RequestFuncOutput:
334
api_url = request_func_input.api_url
335
assert api_url.endswith(
336
- "chat/completions"
336
+ ("chat/completions", "profile")
337
), "OpenAI Chat Completions API URL must end with 'chat/completions'."
338
339
async with aiohttp.ClientSession(trust_env=True,