diff --git a/.github/workflows/llm_performance_tests.yml b/.github/workflows/llm_performance_tests.yml
index 9185e4282d5..2f6de2d5afe 100644
--- a/.github/workflows/llm_performance_tests.yml
+++ b/.github/workflows/llm_performance_tests.yml
@@ -714,6 +714,33 @@ jobs:
 
           call conda deactivate
 
+      - name: Prepare igpu perf test for transformers 4.43 (32-32 int4+fp16)
+        shell: bash
+        run: |
+          sed -i 's/{today}_test3/{today}_test4/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_443.yaml
+
+      - name: Test on igpu for transformers 4.43 (32-32 int4+fp16)
+        shell: cmd
+        run: |
+          call conda activate igpu-perf
+          pip install transformers==4.43.1
+          pip install trl
+
+          set SYCL_CACHE_PERSISTENT=1
+          set BIGDL_LLM_XMX_DISABLED=1
+
+          cd python\llm\dev\benchmark\all-in-one
+          move ..\..\..\test\benchmark\igpu-perf\32-32_int4_fp16_443.yaml config.yaml
+          set PYTHONIOENCODING=utf-8
+          python run.py >> %CSV_SAVE_PATH%\32-32_int4_fp16\log\%LOG_FILE% 2>&1
+          if %ERRORLEVEL% neq 0 if %ERRORLEVEL% neq -1073740791 (exit /b 1)
+          python ..\..\..\test\benchmark\igpu-perf\check_csv_results.py --yaml-file config.yaml --suffix test4
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+
+          pip uninstall trl
+          call conda deactivate
+
       - name: Concat csv and generate html (32-32 int4+fp16)
         shell: cmd
         run: |
@@ -737,7 +764,7 @@ jobs:
         shell: bash
         run: |
           sed -i 's/32-32/1024-128/g' python/llm/dev/benchmark/all-in-one/run.py
-          sed -i 's/{today}_test3/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i 's/{today}_test4/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
           sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml
 
       - name: Test on igpu (1024-128 int4+fp16)
@@ -811,6 +838,33 @@ jobs:
 
           call conda deactivate
 
+      - name: Prepare igpu perf test for transformers 4.43 (1024-128 int4+fp16)
+        shell: bash
+        run: |
+          sed -i 's/{today}_test3/{today}_test4/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_443.yaml
+
+      - name: Test on igpu for transformers 4.43 (1024-128 int4+fp16)
+        shell: cmd
+        run: |
+          call conda activate igpu-perf
+          pip install transformers==4.43.1
+          pip install trl
+
+          set SYCL_CACHE_PERSISTENT=1
+          set BIGDL_LLM_XMX_DISABLED=1
+
+          cd python\llm\dev\benchmark\all-in-one
+          move ..\..\..\test\benchmark\igpu-perf\1024-128_int4_fp16_443.yaml config.yaml
+          set PYTHONIOENCODING=utf-8
+          python run.py >> %CSV_SAVE_PATH%\1024-128_int4_fp16\log\%LOG_FILE% 2>&1
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+          python ..\..\..\test\benchmark\igpu-perf\check_csv_results.py --yaml-file config.yaml --suffix test4
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+
+          pip uninstall trl
+          call conda deactivate
+
       - name: Concat csv and generate html (1024-128 int4+fp16)
         shell: cmd
         run: |
@@ -833,7 +887,7 @@ jobs:
         shell: bash
         run: |
           sed -i 's/1024-128/2048-256/g' python/llm/dev/benchmark/all-in-one/run.py
-          sed -i 's/{today}_test3/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i 's/{today}_test4/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
           sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16.yaml
 
       - name: Test on igpu (2048-256 int4+fp16)
@@ -907,6 +961,33 @@ jobs:
 
           call conda deactivate
 
+      - name: Prepare igpu perf test for transformers 4.43 (2048-256 int4+fp16)
+        shell: bash
+        run: |
+          sed -i 's/{today}_test3/{today}_test4/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_443.yaml
+
+      - name: Test on igpu for transformers 4.43 (2048-256 int4+fp16)
+        shell: cmd
+        run: |
+          call conda activate igpu-perf
+          pip install transformers==4.43.1
+          pip install trl
+
+          set SYCL_CACHE_PERSISTENT=1
+          set BIGDL_LLM_XMX_DISABLED=1
+
+          cd python\llm\dev\benchmark\all-in-one
+          move ..\..\..\test\benchmark\igpu-perf\2048-256_int4_fp16_443.yaml config.yaml
+          set PYTHONIOENCODING=utf-8
+          python run.py >> %CSV_SAVE_PATH%\2048-256_int4_fp16\log\%LOG_FILE% 2>&1
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+          python ..\..\..\test\benchmark\igpu-perf\check_csv_results.py --yaml-file config.yaml --suffix test4
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+
+          pip uninstall trl
+          call conda deactivate
+
       - name: Concat csv and generate html (2048-256 int4+fp16)
         shell: cmd
         run: |
@@ -929,7 +1010,7 @@ jobs:
         shell: bash
         run: |
           sed -i 's/2048-256/3072-384/g' python/llm/dev/benchmark/all-in-one/run.py
-          sed -i 's/{today}_test3/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i 's/{today}_test4/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
           sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16.yaml
       
       - name: Test on igpu (3072-384 int4+fp16)
@@ -1003,6 +1084,33 @@ jobs:
 
           call conda deactivate
 
+      - name: Prepare igpu perf test for transformers 4.43 (3072-384 int4+fp16)
+        shell: bash
+        run: |
+          sed -i 's/{today}_test3/{today}_test4/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_443.yaml
+
+      - name: Test on igpu for transformers 4.43 (3072-384 int4+fp16)
+        shell: cmd
+        run: |
+          call conda activate igpu-perf
+          pip install transformers==4.43.1
+          pip install trl
+
+          set SYCL_CACHE_PERSISTENT=1
+          set BIGDL_LLM_XMX_DISABLED=1
+
+          cd python\llm\dev\benchmark\all-in-one
+          move ..\..\..\test\benchmark\igpu-perf\3072-384_int4_fp16_438.yaml config.yaml
+          set PYTHONIOENCODING=utf-8
+          python run.py >> %CSV_SAVE_PATH%\3072-384_int4_fp16\log\%LOG_FILE% 2>&1
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+          python ..\..\..\test\benchmark\igpu-perf\check_csv_results.py --yaml-file config.yaml --suffix test4
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+
+          pip uninstall trl
+          call conda deactivate
+
       - name: Concat csv and generate html (3072-384 int4+fp16)
         shell: cmd
         run: |
@@ -1025,7 +1133,7 @@ jobs:
         shell: bash
         run: |
           sed -i 's/3072-384/4096-512/g' python/llm/dev/benchmark/all-in-one/run.py
-          sed -i 's/{today}_test3/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i 's/{today}_test4/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
           sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16.yaml
       
       - name: Test on igpu (4096-512 int4+fp16)
@@ -1099,6 +1207,36 @@ jobs:
 
           call conda deactivate
 
+      # NOTE: Gemma2 not working for 4096-512. 
+      #       When it works, uncomment this section and remember to change "'s/{today}_test3/{today}_test1/g'" in next section.
+      
+      #- name: Prepare igpu perf test for transformers 4.43 (4096-512 int4+fp16)
+      #  shell: bash
+      #  run: |
+      #    sed -i 's/{today}_test3/{today}_test4/g' python/llm/dev/benchmark/all-in-one/run.py
+      #    sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_443.yaml
+
+      #- name: Test on igpu for transformers 4.43 (4096-512 int4+fp16)
+      #  shell: cmd
+      #  run: |
+      #    call conda activate igpu-perf
+      #    pip install transformers==4.43.1
+      #    pip install trl
+      #
+      #    set SYCL_CACHE_PERSISTENT=1
+      #    set BIGDL_LLM_XMX_DISABLED=1
+      #
+      #    cd python\llm\dev\benchmark\all-in-one
+      #    move ..\..\..\test\benchmark\igpu-perf\4096-512_int4_fp16_443.yaml config.yaml
+      #    set PYTHONIOENCODING=utf-8
+      #    python run.py >> %CSV_SAVE_PATH%\4096-512_int4_fp16\log\%LOG_FILE% 2>&1
+      #    if %ERRORLEVEL% neq 0 (exit /b 1)
+      #    python ..\..\..\test\benchmark\igpu-perf\check_csv_results.py --yaml-file config.yaml --suffix test4
+      #    if %ERRORLEVEL% neq 0 (exit /b 1)
+      #    
+      #    pip uninstall trl
+      #    call conda deactivate
+
       - name: Concat csv and generate html (4096-512 int4+fp16)
         shell: cmd
         run: |
@@ -1195,6 +1333,33 @@ jobs:
 
           call conda deactivate
 
+      - name: Prepare igpu perf test for transformers 4.43 (load_low_bit 1024-128 int4+fp16)
+        shell: bash
+        run: |
+          sed -i 's/{today}_test3/{today}_test4/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_443.yaml
+
+      - name: Test on igpu for transformers 4.43 (load_low_bit 1024-128 int4+fp16)
+        shell: cmd
+        run: |
+          call conda activate igpu-perf
+          pip install transformers==4.43.1
+          pip install trl
+
+          set SYCL_CACHE_PERSISTENT=1
+          set BIGDL_LLM_XMX_DISABLED=1
+
+          cd python\llm\dev\benchmark\all-in-one
+          move ..\..\..\test\benchmark\igpu-perf\1024-128_int4_fp16_loadlowbit_443.yaml config.yaml
+          set PYTHONIOENCODING=utf-8
+          python run.py >> %CSV_SAVE_PATH%\1024-128_int4_fp16_loadlowbit\log\%LOG_FILE% 2>&1
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+          python ..\..\..\test\benchmark\igpu-perf\check_csv_results.py --yaml-file config.yaml --suffix test4
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+
+          pip uninstall trl
+          call conda deactivate
+
       - name: Concat csv and generate html (load_low_bit 1024-128 int4+fp16)
         shell: cmd
         run: |
@@ -1216,7 +1381,7 @@ jobs:
       - name: Prepare igpu perf test (1024-128)
         shell: bash
         run: |
-          sed -i 's/{today}_test3/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i 's/{today}_test4/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
           sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/1024-128.yaml
 
       - name: Test on igpu (1024-128)
@@ -1290,6 +1455,33 @@ jobs:
 
           call conda deactivate
 
+      - name: Prepare igpu perf test for transformers 4.43 (1024-128)
+        shell: bash
+        run: |
+          sed -i 's/{today}_test3/{today}_test4/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/1024-128_443.yaml
+
+      - name: Test on igpu for transformers 4.43 (1024-128)
+        shell: cmd
+        run: |
+          call conda activate igpu-perf
+          pip install transformers==4.43.1
+          pip install trl
+
+          set SYCL_CACHE_PERSISTENT=1
+          set BIGDL_LLM_XMX_DISABLED=1
+
+          cd python\llm\dev\benchmark\all-in-one
+          move ..\..\..\test\benchmark\igpu-perf\1024-128_443.yaml config.yaml
+          set PYTHONIOENCODING=utf-8
+          python run.py >> %CSV_SAVE_PATH%\1024-128\log\%LOG_FILE% 2>&1
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+          python ..\..\..\test\benchmark\igpu-perf\check_csv_results.py --yaml-file config.yaml --suffix test4
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+
+          pip uninstall trl
+          call conda deactivate
+
       - name: Concat csv and generate html (1024-128)
         shell: cmd
         run: |
diff --git a/python/llm/test/benchmark/concat_csv.py b/python/llm/test/benchmark/concat_csv.py
index 908f71f1aed..442eab7cc9a 100644
--- a/python/llm/test/benchmark/concat_csv.py
+++ b/python/llm/test/benchmark/concat_csv.py
@@ -36,7 +36,7 @@ def main():
 
     merged_df = pd.concat([pd.read_csv(file, index_col=0) for file in csv_files], ignore_index=True)
     merged_df.reset_index(drop=True, inplace=True)
-    merged_csv = csv_files[0].replace("_test1", "").replace("_test2", "").replace("_test3", "")
+    merged_csv = csv_files[0].replace("_test1", "").replace("_test2", "").replace("_test3", "").replace("_test4", "")
     merged_df.to_csv(merged_csv)
 
 if __name__ == "__main__":
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128.yaml b/python/llm/test/benchmark/igpu-perf/1024-128.yaml
index b0bd5f30c20..98fab56cbc4 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128.yaml
@@ -1,17 +1,17 @@
 repo_id:
-  - 'THUDM/chatglm3-6b'
-  - 'THUDM/glm-4-9b-chat'
-  - 'baichuan-inc/Baichuan2-7B-Chat'
-  - 'baichuan-inc/Baichuan2-13B-Chat'
-  - 'meta-llama/Llama-2-7b-chat-hf'
-  - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
-  - 'RWKV/v5-Eagle-7B-HF'
-  - '01-ai/Yi-6B-Chat'
-  - 'Qwen/Qwen-VL-Chat'
-  - 'openbmb/MiniCPM-1B-sft-bf16'
+  #- 'THUDM/chatglm3-6b'
+  #- 'THUDM/glm-4-9b-chat'
+  #- 'baichuan-inc/Baichuan2-7B-Chat'
+  #- 'baichuan-inc/Baichuan2-13B-Chat'
+  #- 'meta-llama/Llama-2-7b-chat-hf'
+  #- 'meta-llama/Llama-2-13b-chat-hf'
+  #- 'meta-llama/Meta-Llama-3-8B-Instruct'
+  #- 'mistralai/Mistral-7B-Instruct-v0.2'
+  #- 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  #- 'RWKV/v5-Eagle-7B-HF'
+  #- '01-ai/Yi-6B-Chat'
+  #- 'Qwen/Qwen-VL-Chat'
+  #- 'openbmb/MiniCPM-1B-sft-bf16'
   - 'openbmb/MiniCPM-2B-sft-bf16'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml
index b87e6c2c865..cc0a24821e1 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml
@@ -1,9 +1,9 @@
 repo_id:
-  - 'Qwen/Qwen1.5-7B-Chat'
-  - 'Qwen/Qwen2-1.5B-Instruct'
-  - 'Qwen/Qwen2-7B-Instruct'
-  - 'microsoft/Phi-3-mini-4k-instruct'
-  - 'microsoft/Phi-3-mini-128k-instruct'
+  # - 'Qwen/Qwen1.5-7B-Chat'
+  # - 'Qwen/Qwen2-1.5B-Instruct'
+  # - 'Qwen/Qwen2-7B-Instruct'
+  # - 'microsoft/Phi-3-mini-4k-instruct'
+  # - 'microsoft/Phi-3-mini-128k-instruct'
   - 'microsoft/phi-3-vision-128k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_443.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_443.yaml
new file mode 100644
index 00000000000..4667ff34c3a
--- /dev/null
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_443.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'google/gemma-2-2b-it'
+  - 'google/gemma-2-9b-it'
+local_model_hub: 'path to your local model hub'
+warm_up: 1
+num_trials: 3
+num_beams: 1 # default to greedy search
+low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
+batch_size: 1 # default to 1
+in_out_pairs:
+  - '1024-128'
+test_api:
+  - "transformer_int4_gpu_win" # on Intel GPU for Windows (catch GPU peak memory)
+cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml
index 39d575680ab..60b3bffc61c 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml
@@ -1,16 +1,16 @@
 repo_id:
-  - 'THUDM/chatglm3-6b'
-  - 'THUDM/glm-4-9b-chat'
-  - 'baichuan-inc/Baichuan2-7B-Chat'
-  - 'baichuan-inc/Baichuan2-13B-Chat'
-  - 'meta-llama/Llama-2-7b-chat-hf'
-  - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
-  - '01-ai/Yi-6B-Chat'
-  - 'Qwen/Qwen-VL-Chat'
-  - 'openbmb/MiniCPM-1B-sft-bf16'
+  #- 'THUDM/chatglm3-6b'
+  #- 'THUDM/glm-4-9b-chat'
+  #- 'baichuan-inc/Baichuan2-7B-Chat'
+  #- 'baichuan-inc/Baichuan2-13B-Chat'
+  #- 'meta-llama/Llama-2-7b-chat-hf'
+  #- 'meta-llama/Llama-2-13b-chat-hf'
+  #- 'meta-llama/Meta-Llama-3-8B-Instruct'
+  #- 'mistralai/Mistral-7B-Instruct-v0.2'
+  #- 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  #- '01-ai/Yi-6B-Chat'
+  #- 'Qwen/Qwen-VL-Chat'
+  #- 'openbmb/MiniCPM-1B-sft-bf16'
   - 'openbmb/MiniCPM-2B-sft-bf16'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml
index d7172186bb3..ff58a625bbb 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml
@@ -1,9 +1,9 @@
 repo_id:
-  - 'Qwen/Qwen1.5-7B-Chat'
-  - 'Qwen/Qwen2-1.5B-Instruct'
-  - 'Qwen/Qwen2-7B-Instruct'
-  - 'microsoft/Phi-3-mini-4k-instruct'
-  - 'microsoft/Phi-3-mini-128k-instruct'
+  # - 'Qwen/Qwen1.5-7B-Chat'
+  # - 'Qwen/Qwen2-1.5B-Instruct'
+  # - 'Qwen/Qwen2-7B-Instruct'
+  # - 'microsoft/Phi-3-mini-4k-instruct'
+  # - 'microsoft/Phi-3-mini-128k-instruct'
   - 'microsoft/phi-3-vision-128k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_443.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_443.yaml
new file mode 100644
index 00000000000..2f4bbd2270d
--- /dev/null
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_443.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'google/gemma-2-2b-it'
+  - 'google/gemma-2-9b-it'
+local_model_hub: 'path to your local model hub'
+warm_up: 1
+num_trials: 3
+num_beams: 1 # default to greedy search
+low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
+batch_size: 1 # default to 1
+in_out_pairs:
+  - '1024-128'
+test_api:
+  - "transformer_int4_fp16_gpu_win" # on Intel GPU for Windows, use fp16 for non-linear layer
+cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit.yaml
index 2730e465d47..dd5304c6695 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit.yaml
@@ -1,16 +1,16 @@
 repo_id:
-  - 'THUDM/chatglm3-6b'
-  - 'THUDM/glm-4-9b-chat'
-  - 'baichuan-inc/Baichuan2-7B-Chat'
-  - 'baichuan-inc/Baichuan2-13B-Chat'
-  - 'meta-llama/Llama-2-7b-chat-hf'
-  - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
-  - '01-ai/Yi-6B-Chat'
-  - 'Qwen/Qwen-VL-Chat'
-  - 'openbmb/MiniCPM-1B-sft-bf16'
+  #- 'THUDM/chatglm3-6b'
+  #- 'THUDM/glm-4-9b-chat'
+  #- 'baichuan-inc/Baichuan2-7B-Chat'
+  #- 'baichuan-inc/Baichuan2-13B-Chat'
+  #- 'meta-llama/Llama-2-7b-chat-hf'
+  #- 'meta-llama/Llama-2-13b-chat-hf'
+  #- 'meta-llama/Meta-Llama-3-8B-Instruct'
+  #- 'mistralai/Mistral-7B-Instruct-v0.2'
+  #- 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  #- '01-ai/Yi-6B-Chat'
+  #- 'Qwen/Qwen-VL-Chat'
+  #- 'openbmb/MiniCPM-1B-sft-bf16'
   - 'openbmb/MiniCPM-2B-sft-bf16'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_437.yaml
index 3839d0d2951..3d48cf9b9f3 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_437.yaml
@@ -1,9 +1,9 @@
 repo_id:
-  - 'Qwen/Qwen1.5-7B-Chat'
-  - 'Qwen/Qwen2-1.5B-Instruct'
-  - 'Qwen/Qwen2-7B-Instruct'
-  - 'microsoft/Phi-3-mini-4k-instruct'
-  - 'microsoft/Phi-3-mini-128k-instruct'
+  # - 'Qwen/Qwen1.5-7B-Chat'
+  # - 'Qwen/Qwen2-1.5B-Instruct'
+  # - 'Qwen/Qwen2-7B-Instruct'
+  # - 'microsoft/Phi-3-mini-4k-instruct'
+  # - 'microsoft/Phi-3-mini-128k-instruct'
   - 'microsoft/phi-3-vision-128k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_443.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_443.yaml
new file mode 100644
index 00000000000..8d8e16c5c42
--- /dev/null
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_443.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'google/gemma-2-2b-it'
+  - 'google/gemma-2-9b-it'
+local_model_hub: 'path to your local model hub'
+warm_up: 1
+num_trials: 3
+num_beams: 1 # default to greedy search
+low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
+batch_size: 1 # default to 1
+in_out_pairs:
+  - '1024-128'
+test_api:
+  - "transformer_int4_fp16_loadlowbit_gpu_win" # on Intel GPU for Windows (catch GPU peak memory)
+cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)
diff --git a/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16.yaml b/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16.yaml
index c53e6283919..850912f7a5f 100644
--- a/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16.yaml
+++ b/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16.yaml
@@ -1,16 +1,16 @@
 repo_id:
-  - 'THUDM/chatglm3-6b'
-  - 'THUDM/glm-4-9b-chat'
-  - 'baichuan-inc/Baichuan2-7B-Chat'
-  - 'baichuan-inc/Baichuan2-13B-Chat'
-  - 'meta-llama/Llama-2-7b-chat-hf'
-  - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
-  - '01-ai/Yi-6B-Chat'
-  - 'Qwen/Qwen-VL-Chat'
-  - 'openbmb/MiniCPM-1B-sft-bf16'
+  #- 'THUDM/chatglm3-6b'
+  #- 'THUDM/glm-4-9b-chat'
+  #- 'baichuan-inc/Baichuan2-7B-Chat'
+  #- 'baichuan-inc/Baichuan2-13B-Chat'
+  #- 'meta-llama/Llama-2-7b-chat-hf'
+  #- 'meta-llama/Llama-2-13b-chat-hf'
+  #- 'meta-llama/Meta-Llama-3-8B-Instruct'
+  #- 'mistralai/Mistral-7B-Instruct-v0.2'
+  #- 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  #- '01-ai/Yi-6B-Chat'
+  #- 'Qwen/Qwen-VL-Chat'
+  #- 'openbmb/MiniCPM-1B-sft-bf16'
   - 'openbmb/MiniCPM-2B-sft-bf16'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_437.yaml b/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_437.yaml
index d6ee670ea29..229d8ec35f9 100644
--- a/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_437.yaml
@@ -1,9 +1,9 @@
 repo_id:
-  - 'Qwen/Qwen1.5-7B-Chat'
-  - 'Qwen/Qwen2-1.5B-Instruct'
-  - 'Qwen/Qwen2-7B-Instruct'
-  - 'microsoft/Phi-3-mini-4k-instruct'
-  - 'microsoft/Phi-3-mini-128k-instruct'
+  # - 'Qwen/Qwen1.5-7B-Chat'
+  # - 'Qwen/Qwen2-1.5B-Instruct'
+  # - 'Qwen/Qwen2-7B-Instruct'
+  # - 'microsoft/Phi-3-mini-4k-instruct'
+  # - 'microsoft/Phi-3-mini-128k-instruct'
   - 'microsoft/phi-3-vision-128k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_443.yaml b/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_443.yaml
new file mode 100644
index 00000000000..3f8e554d19d
--- /dev/null
+++ b/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_443.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'google/gemma-2-2b-it'
+  - 'google/gemma-2-9b-it'
+local_model_hub: 'path to your local model hub'
+warm_up: 1
+num_trials: 3
+num_beams: 1 # default to greedy search
+low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
+batch_size: 1 # default to 1
+in_out_pairs:
+  - '2048-256'
+test_api:
+  - "transformer_int4_fp16_gpu_win" # on Intel GPU for Windows (catch GPU peak memory)
+cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)
diff --git a/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16.yaml b/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16.yaml
index 47b9839a789..14adf06075b 100644
--- a/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16.yaml
+++ b/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16.yaml
@@ -1,15 +1,15 @@
 repo_id:
-  - 'THUDM/chatglm3-6b'
-  - 'THUDM/glm-4-9b-chat'
-  - 'baichuan-inc/Baichuan2-7B-Chat'
-  - 'meta-llama/Llama-2-7b-chat-hf'
-  - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
-  - '01-ai/Yi-6B-Chat'
-  - 'Qwen/Qwen-VL-Chat'
-  - 'openbmb/MiniCPM-1B-sft-bf16'
+  #- 'THUDM/chatglm3-6b'
+  #- 'THUDM/glm-4-9b-chat'
+  #- 'baichuan-inc/Baichuan2-7B-Chat'
+  #- 'meta-llama/Llama-2-7b-chat-hf'
+  #- 'meta-llama/Llama-2-13b-chat-hf'
+  #- 'meta-llama/Meta-Llama-3-8B-Instruct'
+  #- 'mistralai/Mistral-7B-Instruct-v0.2'
+  #- 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  #- '01-ai/Yi-6B-Chat'
+  #- 'Qwen/Qwen-VL-Chat'
+  #- 'openbmb/MiniCPM-1B-sft-bf16'
   - 'openbmb/MiniCPM-2B-sft-bf16'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_437.yaml b/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_437.yaml
index ddbf1cf4d19..ea08a7a120f 100644
--- a/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_437.yaml
@@ -1,9 +1,9 @@
 repo_id:
-  - 'Qwen/Qwen1.5-7B-Chat'
-  - 'Qwen/Qwen2-1.5B-Instruct'
-  - 'Qwen/Qwen2-7B-Instruct'
-  - 'microsoft/Phi-3-mini-4k-instruct'
-  - 'microsoft/Phi-3-mini-128k-instruct'
+  # - 'Qwen/Qwen1.5-7B-Chat'
+  # - 'Qwen/Qwen2-1.5B-Instruct'
+  # - 'Qwen/Qwen2-7B-Instruct'
+  # - 'microsoft/Phi-3-mini-4k-instruct'
+  # - 'microsoft/Phi-3-mini-128k-instruct'
   - 'microsoft/phi-3-vision-128k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_443.yaml b/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_443.yaml
new file mode 100644
index 00000000000..ac1a4d6511a
--- /dev/null
+++ b/python/llm/test/benchmark/igpu-perf/3072-384_int4_fp16_443.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'google/gemma-2-2b-it'
+  - 'google/gemma-2-9b-it'
+local_model_hub: 'path to your local model hub'
+warm_up: 1
+num_trials: 3
+num_beams: 1 # default to greedy search
+low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
+batch_size: 1 # default to 1
+in_out_pairs:
+  - '3072-384'
+test_api:
+  - "transformer_int4_fp16_gpu_win" # on Intel GPU for Windows (catch GPU peak memory)
+cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)
diff --git a/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16.yaml b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16.yaml
index 39115e0231b..23d46b79201 100644
--- a/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16.yaml
+++ b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16.yaml
@@ -1,16 +1,16 @@
 repo_id:
-  - 'THUDM/chatglm3-6b'
-  - 'THUDM/glm-4-9b-chat'
-  - 'baichuan-inc/Baichuan2-7B-Chat'
-  - 'baichuan-inc/Baichuan2-13B-Chat'
-  - 'meta-llama/Llama-2-7b-chat-hf'
-  - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
-  - '01-ai/Yi-6B-Chat'
-  - 'Qwen/Qwen-VL-Chat'
-  - 'openbmb/MiniCPM-1B-sft-bf16'
+  #- 'THUDM/chatglm3-6b'
+  #- 'THUDM/glm-4-9b-chat'
+  #- 'baichuan-inc/Baichuan2-7B-Chat'
+  #- 'baichuan-inc/Baichuan2-13B-Chat'
+  #- 'meta-llama/Llama-2-7b-chat-hf'
+  #- 'meta-llama/Llama-2-13b-chat-hf'
+  #- 'meta-llama/Meta-Llama-3-8B-Instruct'
+  #- 'mistralai/Mistral-7B-Instruct-v0.2'
+  #- 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  #- '01-ai/Yi-6B-Chat'
+  #- 'Qwen/Qwen-VL-Chat'
+  #- 'openbmb/MiniCPM-1B-sft-bf16'
   - 'openbmb/MiniCPM-2B-sft-bf16'
 local_model_hub: 'path to your local model hub'
 warm_up: 3
diff --git a/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_437.yaml b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_437.yaml
index 1a969165267..e7f6d4673fd 100644
--- a/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_437.yaml
@@ -1,9 +1,9 @@
 repo_id:
-  - 'Qwen/Qwen1.5-7B-Chat'
-  - 'Qwen/Qwen2-1.5B-Instruct'
-  - 'Qwen/Qwen2-7B-Instruct'
-  - 'microsoft/Phi-3-mini-4k-instruct'
-  - 'microsoft/Phi-3-mini-128k-instruct'
+  # - 'Qwen/Qwen1.5-7B-Chat'
+  # - 'Qwen/Qwen2-1.5B-Instruct'
+  # - 'Qwen/Qwen2-7B-Instruct'
+  # - 'microsoft/Phi-3-mini-4k-instruct'
+  # - 'microsoft/Phi-3-mini-128k-instruct'
   - 'microsoft/phi-3-vision-128k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 3
diff --git a/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_443.yaml b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_443.yaml
new file mode 100644
index 00000000000..a02b19b1cf2
--- /dev/null
+++ b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_443.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'google/gemma-2-2b-it'
+  - 'google/gemma-2-9b-it'
+local_model_hub: 'path to your local model hub'
+warm_up: 3
+num_trials: 5
+num_beams: 1 # default to greedy search
+low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
+batch_size: 1 # default to 1
+in_out_pairs:
+  - '32-32'
+test_api:
+  - "transformer_int4_fp16_gpu_win" # on Intel GPU for Windows (catch GPU peak memory)
+cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)
diff --git a/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16.yaml b/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16.yaml
index 26e128a564c..04e22f983c0 100644
--- a/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16.yaml
+++ b/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16.yaml
@@ -1,14 +1,14 @@
 repo_id:
-  - 'THUDM/chatglm3-6b'
-  - 'THUDM/glm-4-9b-chat'
-  - 'baichuan-inc/Baichuan2-7B-Chat'
-  - 'meta-llama/Llama-2-7b-chat-hf'
-  - 'meta-llama/Llama-2-13b-chat-hf'
-  - 'meta-llama/Meta-Llama-3-8B-Instruct'
-  - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
-  - '01-ai/Yi-6B-Chat'
-  - 'openbmb/MiniCPM-1B-sft-bf16'
+  #- 'THUDM/chatglm3-6b'
+  #- 'THUDM/glm-4-9b-chat'
+  #- 'baichuan-inc/Baichuan2-7B-Chat'
+  #- 'meta-llama/Llama-2-7b-chat-hf'
+  #- 'meta-llama/Llama-2-13b-chat-hf'
+  #- 'meta-llama/Meta-Llama-3-8B-Instruct'
+  #- 'mistralai/Mistral-7B-Instruct-v0.2'
+  #- 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  #- '01-ai/Yi-6B-Chat'
+  #- 'openbmb/MiniCPM-1B-sft-bf16'
   - 'openbmb/MiniCPM-2B-sft-bf16'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_437.yaml b/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_437.yaml
index c85da867aa2..e08cd4ec921 100644
--- a/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_437.yaml
@@ -1,9 +1,9 @@
 repo_id:
-  - 'Qwen/Qwen1.5-7B-Chat'
-  - 'Qwen/Qwen2-1.5B-Instruct'
-  - 'Qwen/Qwen2-7B-Instruct'
-  - 'microsoft/Phi-3-mini-4k-instruct'
-  - 'microsoft/Phi-3-mini-128k-instruct'
+  # - 'Qwen/Qwen1.5-7B-Chat'
+  # - 'Qwen/Qwen2-1.5B-Instruct'
+  # - 'Qwen/Qwen2-7B-Instruct'
+  # - 'microsoft/Phi-3-mini-4k-instruct'
+  # - 'microsoft/Phi-3-mini-128k-instruct'
   - 'microsoft/phi-3-vision-128k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
diff --git a/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_443.yaml b/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_443.yaml
new file mode 100644
index 00000000000..53467812ac7
--- /dev/null
+++ b/python/llm/test/benchmark/igpu-perf/4096-512_int4_fp16_443.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'google/gemma-2-2b-it'
+  - 'google/gemma-2-9b-it'
+local_model_hub: 'path to your local model hub'
+warm_up: 1
+num_trials: 3
+num_beams: 1 # default to greedy search
+low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
+batch_size: 1 # default to 1
+in_out_pairs:
+  - '4096-512'
+test_api:
+  - "transformer_int4_fp16_gpu_win" # on Intel GPU for Windows (catch GPU peak memory)
+cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)