From c727af47b192c991bfbbf5e81680b8ac86c7778b Mon Sep 17 00:00:00 2001 From: Hyunjae Woo Date: Thu, 26 Oct 2023 16:37:02 -0700 Subject: [PATCH] Fix sample output --- src/c++/perf_analyzer/docs/llm.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/c++/perf_analyzer/docs/llm.md b/src/c++/perf_analyzer/docs/llm.md index 32a78274f..107b82ccb 100644 --- a/src/c++/perf_analyzer/docs/llm.md +++ b/src/c++/perf_analyzer/docs/llm.md @@ -124,7 +124,7 @@ prompts. python profile.py -m vllm --prompt-size-range 100 500 200 --max-tokens 256 --ignore-eos # Sample output -# [ Benchmark Summary ] +# [ BENCHMARK SUMMARY ] # Prompt size: 100, Average first-token latency: 0.0388 sec, Average total token-to-token latency: 0.0066 sec # Prompt size: 300, Average first-token latency: 0.0431 sec, Average total token-to-token latency: 0.0071 sec # Prompt size: 500, Average first-token latency: 0.0400 sec, Average total token-to-token latency: 0.0070 sec