update several models for nightly perf test (#11643)

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

python/llm/test/benchmark/arc-perf-test-batch2.yaml

@@ -8,9 +8,12 @@ repo_id:
   - 'deepseek-ai/deepseek-coder-6.7b-instruct'
   - 'THUDM/glm-4-9b-chat'
   - 'openbmb/MiniCPM-2B-sft-bf16'
-  #- 'Qwen/Qwen-VL-Chat'
+  - 'Qwen/Qwen-VL-Chat'
   #- 'SmerkyG/rwkv-5-world-7b' #this model only fp32 is supported for now, fp16 and bf16 are not supported
   - '01-ai/Yi-6B-Chat'
+  - 'mistralai/Mistral-7B-Instruct-v0.2'
+  - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  - '01-ai/Yi-1.5-6B-Chat'
 local_model_hub: '/mnt/disk1/models'
 warm_up: 1
 num_trials: 3

python/llm/test/benchmark/arc-perf-test-batch4.yaml

@@ -8,9 +8,12 @@ repo_id:
   - 'deepseek-ai/deepseek-coder-6.7b-instruct'
   - 'THUDM/glm-4-9b-chat'
   - 'openbmb/MiniCPM-2B-sft-bf16'
-  #- 'Qwen/Qwen-VL-Chat'
+  - 'Qwen/Qwen-VL-Chat'
   #- 'SmerkyG/rwkv-5-world-7b' #this model only fp32 is supported for now, fp16 and bf16 are not supported
   - '01-ai/Yi-6B-Chat'
+  - 'mistralai/Mistral-7B-Instruct-v0.2'
+  - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  - '01-ai/Yi-1.5-6B-Chat'
 local_model_hub: '/mnt/disk1/models'
 warm_up: 1
 num_trials: 3
@@ -29,7 +32,7 @@ exclude:
   - 'baichuan-inc/Baichuan2-7B-Chat:2048'
   - 'baichuan-inc/Baichuan2-13B-Chat-4bit:1024'
   - 'baichuan-inc/Baichuan2-13B-Chat-4bit:2048'
-#  - 'Qwen/Qwen-VL-Chat:2048'
+  - 'Qwen/Qwen-VL-Chat:2048'
 #  - 'fnlp/moss-moon-003-sft-4bit:1024'
 #  - 'fnlp/moss-moon-003-sft-4bit:2048'
 task: 'continuation' # task can be 'continuation', 'QA' and 'summarize'

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

@@ -8,9 +8,12 @@ repo_id:
   - 'deepseek-ai/deepseek-coder-6.7b-instruct'
   - 'THUDM/glm-4-9b-chat'
   - 'openbmb/MiniCPM-2B-sft-bf16'
-  #- 'Qwen/Qwen-VL-Chat'
+  - 'Qwen/Qwen-VL-Chat'
   #- 'SmerkyG/rwkv-5-world-7b' #this model only fp32 is supported for now, fp16 and bf16 are not supported
   - '01-ai/Yi-6B-Chat'
+  - 'mistralai/Mistral-7B-Instruct-v0.2'
+  - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
+  - '01-ai/Yi-1.5-6B-Chat'
 local_model_hub: '/mnt/disk1/models'
 warm_up: 1
 num_trials: 3

python/llm/test/benchmark/arc-perf-transformers-437-batch2.yaml

@@ -5,6 +5,7 @@ repo_id:
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
   - 'microsoft/phi-3-vision-128k-instruct'
   - 'Qwen/Qwen2-7B-Instruct'
+  - 'microsoft/Phi-3-mini-128k-instruct'
 local_model_hub: '/mnt/disk1/models'
 warm_up: 1
 num_trials: 3

python/llm/test/benchmark/arc-perf-transformers-437-batch4.yaml

@@ -5,6 +5,7 @@ repo_id:
   - 'meta-llama/Meta-Llama-3-8B-Instruct' # mwj: need to test
   - 'microsoft/phi-3-vision-128k-instruct'
   - 'Qwen/Qwen2-7B-Instruct'
+  - 'microsoft/Phi-3-mini-128k-instruct'
 local_model_hub: '/mnt/disk1/models'
 warm_up: 1
 num_trials: 3

python/llm/test/benchmark/arc-perf-transformers-437.yaml

@@ -5,6 +5,7 @@ repo_id:
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
   - 'microsoft/phi-3-vision-128k-instruct'
   - 'Qwen/Qwen2-7B-Instruct'
+  - 'microsoft/Phi-3-mini-128k-instruct'
 local_model_hub: '/mnt/disk1/models'
 warm_up: 1
 num_trials: 3