[ADD] add 5 new models for igpu-perf (#11524)

intel · Jul 8, 2024 · 5a57e54 · 5a57e54
1 parent 64cfed6
commit 5a57e54
Show file tree

Hide file tree

Showing 10 changed files with 25 additions and 0 deletions.
diff --git a/python/llm/test/benchmark/igpu-perf/1024-128.yaml b/python/llm/test/benchmark/igpu-perf/1024-128.yaml
@@ -6,6 +6,10 @@ repo_id:
   - 'meta-llama/Llama-2-7b-chat-hf'
   - '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'
 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_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_437.yaml
@@ -2,6 +2,7 @@ repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
   - 'Qwen/Qwen2-7B-Instruct'
   - 'microsoft/Phi-3-mini-4k-instruct'
+  - 'microsoft/Phi-3-mini-128k-instruct'
 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
@@ -6,6 +6,10 @@ repo_id:
   - 'meta-llama/Llama-2-7b-chat-hf'
   - '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'
 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_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml
@@ -2,6 +2,7 @@ repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
   - 'Qwen/Qwen2-7B-Instruct'
   - 'microsoft/Phi-3-mini-4k-instruct'
+  - 'microsoft/Phi-3-mini-128k-instruct'
 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.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit.yaml
@@ -6,6 +6,10 @@ repo_id:
   - 'meta-llama/Llama-2-7b-chat-hf'
   - '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'
 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_437.yaml b/python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_437.yaml
@@ -2,6 +2,7 @@ repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
   - 'Qwen/Qwen2-7B-Instruct'
   - 'microsoft/Phi-3-mini-4k-instruct'
+  - 'microsoft/Phi-3-mini-128k-instruct'
 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.yaml b/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16.yaml
@@ -6,6 +6,10 @@ repo_id:
   - 'meta-llama/Llama-2-7b-chat-hf'
   - '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'
 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_437.yaml b/python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_437.yaml
@@ -2,6 +2,7 @@ repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
   - 'Qwen/Qwen2-7B-Instruct'
   - 'microsoft/Phi-3-mini-4k-instruct'
+  - 'microsoft/Phi-3-mini-128k-instruct'
 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_int4_fp16.yaml b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16.yaml
@@ -6,6 +6,10 @@ repo_id:
   - 'meta-llama/Llama-2-7b-chat-hf'
   - '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'
 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_437.yaml b/python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_437.yaml
@@ -2,6 +2,7 @@ repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
   - 'Qwen/Qwen2-7B-Instruct'
   - 'microsoft/Phi-3-mini-4k-instruct'
+  - 'microsoft/Phi-3-mini-128k-instruct'
 local_model_hub: 'path to your local model hub'
 warm_up: 3
 num_trials: 5