From b70b1b05604a37c1c50abd73b8a711e96da2ace6 Mon Sep 17 00:00:00 2001 From: ZePan110 Date: Wed, 11 Dec 2024 00:06:29 +0800 Subject: [PATCH 1/2] Update perf log process. Signed-off-by: ZePan110 --- evals/benchmark/stresscli/commands/config.ini | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/evals/benchmark/stresscli/commands/config.ini b/evals/benchmark/stresscli/commands/config.ini index fd195d5e..76f6b4ee 100644 --- a/evals/benchmark/stresscli/commands/config.ini +++ b/evals/benchmark/stresscli/commands/config.ini @@ -11,6 +11,14 @@ End_to_End_latency_P50 = End to End latency\(ms\),\s+P50:\s+([\d.]+) End_to_End_latency_P90 = End to End latency\(ms\),\s+P50:[\s\d.,]+P90:\s+([\d.]+) End_to_End_latency_P99 = End to End latency\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+([\d.]+) End_to_End_latency_Avg = End to End latency\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+[\s\d.,]+Avg:\s+([\d.]+) +Time_to_First_Token-TTFT_P50 = Time to First Token-TTFT\(ms\),\s+P50:\s+([\d.]+) +Time_to_First_Token-TTFT_P90 = Time to First Token-TTFT\(ms\),\s+P50:[\s\d.,]+P90:\s+([\d.]+) +Time_to_First_Token-TTFT_P99 = Time to First Token-TTFT\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+([\d.]+) +Time_to_First_Token-TTFT_Avg = Time to First Token-TTFT\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+[\s\d.,]+Avg:\s+([\d.]+) +Time_Per_Output_Token-TPOT_P50 = Time Per Output Token-TPOT\(ms\),\s+P50:\s+([\d.]+) +Time_Per_Output_Token-TPOT_P90 = Time Per Output Token-TPOT\(ms\),\s+P50:[\s\d.,]+P90:\s+([\d.]+) +Time_Per_Output_Token-TPOT_P99 = Time Per Output Token-TPOT\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+([\d.]+) +Time_Per_Output_Token-TPOT_Avg = Time Per Output Token-TPOT\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+[\s\d.,]+Avg:\s+([\d.]+) First_token_latency_P50 = First token latency\(ms\),\s+P50:\s+([\d.]+) First_token_latency_P90 = First token latency\(ms\),\s+P50:[\s\d.,]+P90:\s+([\d.]+) First_token_latency_P99 = First token latency\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+([\d.]+) From fb54000ddcfa88072722ae0cc6bb6fa63cf2d075 Mon Sep 17 00:00:00 2001 From: ZePan110 Date: Mon, 16 Dec 2024 22:13:02 +0800 Subject: [PATCH 2/2] Remove useless code Signed-off-by: ZePan110 --- evals/benchmark/stresscli/commands/config.ini | 8 -------- 1 file changed, 8 deletions(-) diff --git a/evals/benchmark/stresscli/commands/config.ini b/evals/benchmark/stresscli/commands/config.ini index 76f6b4ee..f5d144d1 100644 --- a/evals/benchmark/stresscli/commands/config.ini +++ b/evals/benchmark/stresscli/commands/config.ini @@ -19,14 +19,6 @@ Time_Per_Output_Token-TPOT_P50 = Time Per Output Token-TPOT\(ms\),\s+P50:\s+([\d Time_Per_Output_Token-TPOT_P90 = Time Per Output Token-TPOT\(ms\),\s+P50:[\s\d.,]+P90:\s+([\d.]+) Time_Per_Output_Token-TPOT_P99 = Time Per Output Token-TPOT\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+([\d.]+) Time_Per_Output_Token-TPOT_Avg = Time Per Output Token-TPOT\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+[\s\d.,]+Avg:\s+([\d.]+) -First_token_latency_P50 = First token latency\(ms\),\s+P50:\s+([\d.]+) -First_token_latency_P90 = First token latency\(ms\),\s+P50:[\s\d.,]+P90:\s+([\d.]+) -First_token_latency_P99 = First token latency\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+([\d.]+) -First_token_latency_Avg = First token latency\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+[\s\d.,]+Avg:\s+([\d.]+) -Next_token_latency_P50 = Next token latency\(ms\),\s+P50:\s+([\d.]+) -Next_token_latency_P90 = Next token latency\(ms\),\s+P50:[\s\d.,]+P90:\s+([\d.]+) -Next_token_latency_P99 = Next token latency\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+([\d.]+) -Next_token_latency_Avg = Next token latency\(ms\),\s+P50:[\s\d.,]+P90:\s+[\s\d.,]+P99:\s+[\s\d.,]+Avg:\s+([\d.]+) Average_token_latency = Average token latency\(ms\)\s+:\s+([\d.]+) locust_num_requests = \"num_requests\":\s+(\d+) locust_num_failures = \"num_failures\":\s+(\d+)