From 58341c6279e36068d5b9980b44f11f7b972be793 Mon Sep 17 00:00:00 2001
From: Pablo Gonzalez <pablo.gonzalez@factored.ai>
Date: Wed, 13 Aug 2025 09:27:37 -0500
Subject: [PATCH] Use sample latency as the metric for llama3.1_8b_edge
 SingleStream

---
 tools/submission/submission_checker.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/submission/submission_checker.py b/tools/submission/submission_checker.py
index 021de96167..e9c931c4e9 100755
--- a/tools/submission/submission_checker.py
+++ b/tools/submission/submission_checker.py
@@ -801,6 +801,7 @@
         },
         "llama3.1-8b-edge": {
             "Offline": "result_tokens_per_second",
+            "SingleStream": "result_90.00_percentile_latency_ns",
         },
         "mixtral-8x7b": {
             "Offline": "result_tokens_per_second",