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 16, 22:00 UTC
[Misc] update benchmark backend for scalellm (#6018)
zhyncs committed
Jul 2, 2024 at 01:20 UTC
bb6032683687b817b026a38c5a8729c2cd861246
1 file changed
+1
benchmarks/backend_request_func.py
+1
@@ -422,4 +422,5 @@ ASYNC_REQUEST_FUNCS = {
422
"openai": async_request_openai_completions,
423
"openai-chat": async_request_openai_chat_completions,
424
"tensorrt-llm": async_request_trt_llm,
425
+ "scalellm": async_request_openai_completions,
426
}