Add qwen-moe batch1 to nightly perf (#11369)

* add moe

* reduce 437 models

* rename

* fix syntax

* add moe check result

* add 430 + 437

* all modes

* 4-37-4 exclud

* revert & comment

---------

Co-authored-by: Yishuo Wang <yishuo.wang@intel.com>

.github/workflows/llm_performance_tests.yml

@@ -177,6 +177,23 @@ jobs:
           python run.py
           mv *.csv test_batch4
       
+      - name: Test on xpu(transformers==4.40.0)
+        shell: bash
+        run: |
+          source /opt/intel/oneapi/setvars.sh
+          export USE_XETLA=OFF
+          export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
+          # upgrade transformers for model Qwen/Qwen1.5-MoE-A2.7B-Chat
+          python -m pip install transformers==4.40.0
+          python -m pip install trl
+          # batch_size 1
+          cp python/llm/test/benchmark/arc-perf-transformers-440.yaml python/llm/dev/benchmark/all-in-one/config.yaml
+          cd python/llm/dev/benchmark/all-in-one
+          # change csv name
+          sed -i 's/test2_batch4/test3_batch1/g' run.py
+          python run.py
+          mv *.csv test_batch1
+
       - name: Concat csv and generate html
         shell: bash
         run: |
@@ -262,6 +279,7 @@ jobs:
           cd python/llm/dev/benchmark/all-in-one/test_batch1
           python ../../../../test/benchmark/check_results.py -c test1 -y ../../../../test/benchmark/arc-perf-test.yaml
           python ../../../../test/benchmark/check_results.py -c test2 -y ../../../../test/benchmark/arc-perf-transformers-437.yaml
+          python ../../../../test/benchmark/check_results.py -c test3 -y ../../../../test/benchmark/arc-perf-transformers-440.yaml
           find . -name "*test*.csv" -delete
           if [ ${{ github.event_name }} == "schedule" ] || [ ${{ github.event_name }} == "workflow_dispatch" ]; then
             curl -T ./*.csv ${LLM_FTP_URL}/llm/nightly_perf/gpu/

python/llm/test/benchmark/arc-perf-transformers-440.yaml

@@ -0,0 +1,16 @@
+repo_id:
+  - 'Qwen/Qwen1.5-MoE-A2.7B-Chat'
+local_model_hub: '/mnt/disk1/models'
+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:
+  - '32-32'
+  - '1024-128'
+  - '2048-256'
+test_api:
+  - "transformer_int4_fp16_gpu"  # on Intel GPU
+cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)
+task: 'continuation' # task can be 'continuation', 'QA' and 'summarize'