From f8296b46e4b834b275b9fd519a01e9a2daf14f97 Mon Sep 17 00:00:00 2001
From: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Date: Tue, 7 Jan 2025 20:57:04 -0600
Subject: [PATCH] [Misc] sort torch profiler table by kernel timing (#11813)

Signed-off-by: Isotr0py <2037008807@qq.com>
---
 benchmarks/benchmark_latency.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/benchmarks/benchmark_latency.py b/benchmarks/benchmark_latency.py
index 0a14aedd5feba..e669ce4db299d 100644
--- a/benchmarks/benchmark_latency.py
+++ b/benchmarks/benchmark_latency.py
@@ -52,7 +52,7 @@ def run_to_completion(profile_dir: Optional[str] = None):
                 llm.generate(dummy_prompts,
                              sampling_params=sampling_params,
                              use_tqdm=False)
-            print(p.key_averages())
+            print(p.key_averages().table(sort_by="self_cuda_time_total"))
         else:
             start_time = time.perf_counter()
             llm.generate(dummy_prompts,