Add Yi-6B and StableLM to iGPU perf test (#11546)

* Add transformer4.38.2 test to igpu benchmark (#11529) * add transformer4.38.1 test to igpu benchmark * use transformers4.38.2 & fix csv name error in 4.38 workflow * add model Yi-6B-Chat & remove temporarily most models --------- Co-authored-by: ATMxsp01 <[email protected]> * filter some errorlevel (#11541) Co-authored-by: ATMxsp01 <[email protected]> * Restore the temporarily removed models in iGPU-perf (#11544) * filter some errorlevel * restore the temporarily removed models in iGPU-perf --------- Co-authored-by: ATMxsp01 <[email protected]> --------- Co-authored-by: Xu, Shuo <[email protected]> Co-authored-by: ATMxsp01 <[email protected]>
intel-analytics · Jul 9, 2024 · 8982ab7 · 8982ab7
1 parent 7dc6756
commit 8982ab7
Show file tree

Hide file tree

Showing 11 changed files with 194 additions and 4 deletions.
diff --git a/.github/workflows/llm_performance_tests.yml b/.github/workflows/llm_performance_tests.yml
@@ -679,6 +679,29 @@ jobs:
           if %ERRORLEVEL% neq 0 (exit /b 1)
 
           call conda deactivate
+          
+      - name: Prepare igpu perf test for transformers 4.38 (32-32 int4+fp16)
+        shell: bash
+        run: |
+          sed -i 's/{today}_test2/{today}_test3/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_438.yaml
+
+      - name: Test on igpu for transformers 4.38 (32-32 int4+fp16)
+        shell: cmd
+        run: |
+          call conda activate igpu-perf
+          pip install transformers==4.38.2
+
+          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_438.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)
+
+          call conda deactivate
 
       - name: Concat csv and generate html (32-32 int4+fp16)
         shell: cmd
@@ -703,7 +726,7 @@ 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}_test2/{today}_test1/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/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)
@@ -747,6 +770,29 @@ jobs:
           if %ERRORLEVEL% neq 0 (exit /b 1)
 
           call conda deactivate
+          
+      - name: Prepare igpu perf test for transformers 4.38 (1024-128 int4+fp16)
+        shell: bash
+        run: |
+          sed -i 's/{today}_test2/{today}_test3/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_438.yaml
+
+      - name: Test on igpu for transformers 4.38 (1024-128 int4+fp16)
+        shell: cmd
+        run: |
+          call conda activate igpu-perf
+          pip install transformers==4.38.2
+
+          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_438.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)
+
+          call conda deactivate
 
       - name: Concat csv and generate html (1024-128 int4+fp16)
         shell: cmd
@@ -770,7 +816,7 @@ 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}_test2/{today}_test1/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/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)
@@ -814,6 +860,29 @@ jobs:
           if %ERRORLEVEL% neq 0 (exit /b 1)
 
           call conda deactivate
+          
+      - name: Prepare igpu perf test for transformers 4.38 (2048-256 int4+fp16)
+        shell: bash
+        run: |
+          sed -i 's/{today}_test2/{today}_test3/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_438.yaml
+
+      - name: Test on igpu for transformers 4.38 (2048-256 int4+fp16)
+        shell: cmd
+        run: |
+          call conda activate igpu-perf
+          pip install transformers==4.38.2
+
+          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_438.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)
+
+          call conda deactivate
 
       - name: Concat csv and generate html (2048-256 int4+fp16)
         shell: cmd
@@ -837,7 +906,7 @@ jobs:
         shell: bash
         run: |
           sed -i 's/2048-256/1024-128/g' python/llm/dev/benchmark/all-in-one/run.py
-          sed -i 's/{today}_test2/{today}_test1/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/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit.yaml
 
       - name: Test on igpu (load_low_bit 1024-128 int4+fp16)
@@ -882,6 +951,29 @@ jobs:
 
           call conda deactivate
 
+      - name: Prepare igpu perf test for transformers 4.38 (load_low_bit 1024-128 int4+fp16)
+        shell: bash
+        run: |
+          sed -i 's/{today}_test2/{today}_test3/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_438.yaml
+
+      - name: Test on igpu for transformers 4.38 (load_low_bit 1024-128 int4+fp16)
+        shell: cmd
+        run: |
+          call conda activate igpu-perf
+          pip install transformers==4.38.2
+
+          set SYCL_CACHE_PERSISTENT=1
+          set BIGDL_LLM_XMX_DISABLED=1
+
+          cd python\llm\dev\benchmark\all-in-one
+          move ..\..\..\test\benchmark\igpu-perf\1024-128_int4_fp16_loadlowbit_438.yaml config.yaml
+          set PYTHONIOENCODING=utf-8
+          python run.py >> %CSV_SAVE_PATH%\1024-128_int4_fp16_loadlowbit\log\%LOG_FILE% 2>&1
+          if %ERRORLEVEL% neq 0 (exit /b 1)
+
+          call conda deactivate
+
       - name: Concat csv and generate html (load_low_bit 1024-128 int4+fp16)
         shell: cmd
         run: |
@@ -903,7 +995,7 @@ jobs:
       - name: Prepare igpu perf test (1024-128)
         shell: bash
         run: |
-          sed -i 's/{today}_test2/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
+          sed -i 's/{today}_test3/{today}_test1/g' python/llm/dev/benchmark/all-in-one/run.py
           sed -i "s/path to your local model hub/$MODEL_HUB_DIR/g" python/llm/test/benchmark/igpu-perf/1024-128.yaml
 
       - name: Test on igpu (1024-128)
@@ -948,6 +1040,29 @@ jobs:
 
           call conda deactivate
 
+      - name: Prepare igpu perf test for transformers 4.38 (1024-128)
+        shell: bash
+        run: |
+          sed -i 's/{today}_test2/{today}_test3/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_438.yaml
+
+      - name: Test on igpu for transformers 4.38 (1024-128)
+        shell: cmd
+        run: |
+          call conda activate igpu-perf
+          pip install transformers==4.38.2
+
+          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_438.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)
+
+          call conda deactivate
+
       - name: Concat csv and generate html (1024-128)
         shell: cmd
         run: |

diff --git a/python/llm/test/benchmark/igpu-perf/1024-128.yaml b/python/llm/test/benchmark/igpu-perf/1024-128.yaml
@@ -11,6 +11,7 @@ repo_id:
   - 'openbmb/MiniCPM-2B-sft-bf16'
   - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
   - 'RWKV/v5-Eagle-7B-HF'
+  - '01-ai/Yi-6B-Chat'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
 num_trials: 3

diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_438.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_438.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'stabilityai/stablelm-zephyr-3b'
+  #- 'google/gemma-7b-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
@@ -10,6 +10,7 @@ repo_id:
   - 'openbmb/MiniCPM-1B-sft-bf16'
   - 'openbmb/MiniCPM-2B-sft-bf16'
   - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  - '01-ai/Yi-6B-Chat'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
 num_trials: 3

diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_438.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_438.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'stabilityai/stablelm-zephyr-3b'
+  #- 'google/gemma-7b-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
@@ -10,6 +10,7 @@ repo_id:
   - 'openbmb/MiniCPM-1B-sft-bf16'
   - 'openbmb/MiniCPM-2B-sft-bf16'
   - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  - '01-ai/Yi-6B-Chat'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
 num_trials: 3

diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_438.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_438.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'stabilityai/stablelm-zephyr-3b'
+  #- 'google/gemma-7b-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
@@ -10,6 +10,7 @@ repo_id:
   - 'openbmb/MiniCPM-1B-sft-bf16'
   - 'openbmb/MiniCPM-2B-sft-bf16'
   - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  - '01-ai/Yi-6B-Chat'
 local_model_hub: 'path to your local model hub'
 warm_up: 1
 num_trials: 3

diff --git a/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_438.yaml b/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_438.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'stabilityai/stablelm-zephyr-3b'
+  #- 'google/gemma-7b-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/32-32_int4_fp16.yaml b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16.yaml
@@ -10,6 +10,7 @@ repo_id:
   - 'openbmb/MiniCPM-1B-sft-bf16'
   - 'openbmb/MiniCPM-2B-sft-bf16'
   - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  - '01-ai/Yi-6B-Chat'
 local_model_hub: 'path to your local model hub'
 warm_up: 3
 num_trials: 5

diff --git a/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_438.yaml b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_438.yaml
@@ -0,0 +1,14 @@
+repo_id:
+  - 'stabilityai/stablelm-zephyr-3b'
+  #- 'google/gemma-7b-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)