From 75f836f288341d998f539aa4ed5cf2ba29b399b7 Mon Sep 17 00:00:00 2001
From: Yuwen Hu <54161268+Oscilloscope98@users.noreply.github.com>
Date: Mon, 24 Jun 2024 18:08:05 +0800
Subject: [PATCH] Add extra warmup for THUDM/glm-4-9b-chat in igpu-performance
 test (#11417)

---
 .github/workflows/llm_performance_tests.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/llm_performance_tests.yml b/.github/workflows/llm_performance_tests.yml
index 57ab09b0..cddbb526 100644
--- a/.github/workflows/llm_performance_tests.yml
+++ b/.github/workflows/llm_performance_tests.yml
@@ -562,7 +562,7 @@ jobs:
         shell: bash
         run: |
           sed -i '/^\s*result = run_transformer_int4_gpu_win(repo_id, local_model_hub, in_out_pairs, warm_up, num_trials, num_beams, low_bit, cpu_embedding, batch_size, streaming)/ i\
-                  if repo_id in ["THUDM/chatglm3-6b"]:\
+                  if repo_id in ["THUDM/chatglm3-6b", "THUDM/glm-4-9b-chat"]:\
                       run_transformer_int4_gpu_win(repo_id, local_model_hub, in_out_pairs, warm_up, num_trials, num_beams, low_bit, cpu_embedding, batch_size, streaming)
           ' python/llm/dev/benchmark/all-in-one/run.py