diff --git a/python/llm/test/benchmark/igpu-perf/1024-128.yaml b/python/llm/test/benchmark/igpu-perf/1024-128.yaml
index 6d59984d..0bc60479 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128.yaml
@@ -6,7 +6,7 @@ repo_id:
   - 'internlm/internlm-chat-7b-8k'
   - 'Qwen/Qwen-7B-Chat'
   - 'BAAI/AquilaChat2-7B'
-  - '01-ai/Yi-6B'
+  # - '01-ai/Yi-6B'
   - 'meta-llama/Llama-2-7b-chat-hf'
   - 'meta-llama/Llama-2-13b-chat-hf'
   - 'WisdomShell/CodeShell-7B-Chat'
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 2b829845..679a582b 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml
@@ -1,5 +1,7 @@
 repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
+  - 'meta-llama/Meta-Llama-3-8B-Instruct'
+  - '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.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml
index d4142ce8..0ac89516 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
@@ -6,7 +6,7 @@ repo_id:
   - 'internlm/internlm-chat-7b-8k'
   - 'Qwen/Qwen-7B-Chat'
   - 'BAAI/AquilaChat2-7B'
-  - '01-ai/Yi-6B'
+  # - '01-ai/Yi-6B'
   - 'meta-llama/Llama-2-7b-chat-hf'
   - 'meta-llama/Llama-2-13b-chat-hf'
   - 'WisdomShell/CodeShell-7B-Chat'
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 2e2ec3c5..5051de78 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
@@ -1,5 +1,7 @@
 repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
+  - 'meta-llama/Meta-Llama-3-8B-Instruct'
+  - '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_loadlowbit.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit.yaml
index ea869865..a8dd75ea 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit.yaml
@@ -6,7 +6,7 @@ repo_id:
   - 'internlm/internlm-chat-7b-8k'
   - 'Qwen/Qwen-7B-Chat'
   - 'BAAI/AquilaChat2-7B'
-  - '01-ai/Yi-6B'
+  # - '01-ai/Yi-6B'
   - 'meta-llama/Llama-2-7b-chat-hf'
   - 'meta-llama/Llama-2-13b-chat-hf'
   - 'WisdomShell/CodeShell-7B-Chat'
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit_437.yaml
index 1252d1bb..345b4990 100644
--- a/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/1024-128_loadlowbit_437.yaml
@@ -1,5 +1,7 @@
 repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
+  - 'meta-llama/Meta-Llama-3-8B-Instruct'
+  - '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.yaml b/python/llm/test/benchmark/igpu-perf/2048-256.yaml
index e279ed7c..5aa79015 100644
--- a/python/llm/test/benchmark/igpu-perf/2048-256.yaml
+++ b/python/llm/test/benchmark/igpu-perf/2048-256.yaml
@@ -6,7 +6,7 @@ repo_id:
   - 'internlm/internlm-chat-7b-8k'
   - 'Qwen/Qwen-7B-Chat'
   - 'BAAI/AquilaChat2-7B'
-  - '01-ai/Yi-6B'
+  # - '01-ai/Yi-6B'
   - 'meta-llama/Llama-2-7b-chat-hf'
   - 'meta-llama/Llama-2-13b-chat-hf'
   - 'WisdomShell/CodeShell-7B-Chat'
diff --git a/python/llm/test/benchmark/igpu-perf/2048-256_437.yaml b/python/llm/test/benchmark/igpu-perf/2048-256_437.yaml
index b5569a2a..012af8aa 100644
--- a/python/llm/test/benchmark/igpu-perf/2048-256_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/2048-256_437.yaml
@@ -1,5 +1,7 @@
 repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
+  - 'meta-llama/Meta-Llama-3-8B-Instruct'
+  - '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/32-32.yaml b/python/llm/test/benchmark/igpu-perf/32-32.yaml
index 35f67366..6f4fd2f0 100644
--- a/python/llm/test/benchmark/igpu-perf/32-32.yaml
+++ b/python/llm/test/benchmark/igpu-perf/32-32.yaml
@@ -6,7 +6,7 @@ repo_id:
   - 'internlm/internlm-chat-7b-8k'
   - 'Qwen/Qwen-7B-Chat'
   - 'BAAI/AquilaChat2-7B'
-  - '01-ai/Yi-6B'
+  # - '01-ai/Yi-6B'
   - 'meta-llama/Llama-2-7b-chat-hf'
   - 'meta-llama/Llama-2-13b-chat-hf'
   - 'WisdomShell/CodeShell-7B-Chat'
diff --git a/python/llm/test/benchmark/igpu-perf/32-32_437.yaml b/python/llm/test/benchmark/igpu-perf/32-32_437.yaml
index 4ec7bae9..a4ea2adb 100644
--- a/python/llm/test/benchmark/igpu-perf/32-32_437.yaml
+++ b/python/llm/test/benchmark/igpu-perf/32-32_437.yaml
@@ -1,5 +1,7 @@
 repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
+  - 'meta-llama/Meta-Llama-3-8B-Instruct'
+  - '01-ai/Yi-6B-Chat'
 local_model_hub: 'path to your local model hub'
 warm_up: 3
 num_trials: 5