From 61613b210c2754bbc05bbddcd78d68b17e69d491 Mon Sep 17 00:00:00 2001 From: "Xu, Shuo" <100334393+ATMxsp01@users.noreply.github.com> Date: Wed, 10 Jul 2024 16:58:23 +0800 Subject: [PATCH] try to improve MIniCPM performance (#11552) Co-authored-by: ATMxsp01 --- python/llm/test/benchmark/igpu-perf/1024-128.yaml | 4 ++-- python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml | 4 ++-- .../benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit.yaml | 4 ++-- python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16.yaml | 4 ++-- python/llm/test/benchmark/igpu-perf/32-32_int4_fp16.yaml | 4 ++-- 5 files changed, 10 insertions(+), 10 deletions(-) diff --git a/python/llm/test/benchmark/igpu-perf/1024-128.yaml b/python/llm/test/benchmark/igpu-perf/1024-128.yaml index 8a6ea0f4563..b51c9fac65d 100644 --- 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 index dde71704a92..f32b48c05f1 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 @@ -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 index 3ea3c609d7e..18e4ca5cbb1 100644 --- 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 index 5a52ae16d91..2fc0ddb17dc 100644 --- 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 index a03dfbf55a8..664b8cbbcc6 100644 --- 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'