try to improve MIniCPM performance (#11552)

Co-authored-by: ATMxsp01 <[email protected]>
intel-analytics · Jul 10, 2024 · 61613b2 · 61613b2
1 parent 82f9514
commit 61613b2
Show file tree

Hide file tree

Showing 5 changed files with 10 additions and 10 deletions.
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128.yaml b/python/llm/test/benchmark/igpu-perf/1024-128.yaml
@@ -1,4 +1,6 @@
 repo_id:
+  - 'openbmb/MiniCPM-1B-sft-bf16'
+  - 'openbmb/MiniCPM-2B-sft-bf16'
   - 'THUDM/chatglm3-6b'
   - 'THUDM/glm-4-9b-chat'
   - 'baichuan-inc/Baichuan2-7B-Chat'
@@ -7,8 +9,6 @@ repo_id:
   - 'meta-llama/Llama-2-13b-chat-hf'
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
   - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - 'openbmb/MiniCPM-1B-sft-bf16'
-  - 'openbmb/MiniCPM-2B-sft-bf16'
   - 'deepseek-ai/deepseek-coder-7b-instruct-v1.5'
   - 'RWKV/v5-Eagle-7B-HF'
   - '01-ai/Yi-6B-Chat'

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
@@ -1,4 +1,6 @@
 repo_id:
+  - 'openbmb/MiniCPM-1B-sft-bf16'
+  - 'openbmb/MiniCPM-2B-sft-bf16'
   - 'THUDM/chatglm3-6b'
   - 'THUDM/glm-4-9b-chat'
   - 'baichuan-inc/Baichuan2-7B-Chat'
@@ -7,8 +9,6 @@ repo_id:
   - 'meta-llama/Llama-2-13b-chat-hf'
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
   - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - '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'

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
@@ -1,4 +1,6 @@
 repo_id:
+  - 'openbmb/MiniCPM-1B-sft-bf16'
+  - 'openbmb/MiniCPM-2B-sft-bf16'
   - 'THUDM/chatglm3-6b'
   - 'THUDM/glm-4-9b-chat'
   - 'baichuan-inc/Baichuan2-7B-Chat'
@@ -7,8 +9,6 @@ repo_id:
   - 'meta-llama/Llama-2-13b-chat-hf'
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
   - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - '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'

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
@@ -1,4 +1,6 @@
 repo_id:
+  - 'openbmb/MiniCPM-1B-sft-bf16'
+  - 'openbmb/MiniCPM-2B-sft-bf16'
   - 'THUDM/chatglm3-6b'
   - 'THUDM/glm-4-9b-chat'
   - 'baichuan-inc/Baichuan2-7B-Chat'
@@ -7,8 +9,6 @@ repo_id:
   - 'meta-llama/Llama-2-13b-chat-hf'
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
   - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - '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'

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
@@ -1,4 +1,6 @@
 repo_id:
+  - 'openbmb/MiniCPM-1B-sft-bf16'
+  - 'openbmb/MiniCPM-2B-sft-bf16'
   - 'THUDM/chatglm3-6b'
   - 'THUDM/glm-4-9b-chat'
   - 'baichuan-inc/Baichuan2-7B-Chat'
@@ -7,8 +9,6 @@ repo_id:
   - 'meta-llama/Llama-2-13b-chat-hf'
   - 'meta-llama/Meta-Llama-3-8B-Instruct'
   - 'mistralai/Mistral-7B-Instruct-v0.2'
-  - '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'