ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

try to improve MIniCPM performance (#11552)

Browse source 
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
This commit is contained in:
Xu, Shuo 2024-07-10 16:58:23 +08:00 committed by GitHub
parent 82f9514303
commit 61613b210c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 10 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
python/llm/test/benchmark/igpu-perf/1024-128.yaml
View file

@ -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'

4
python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16.yaml
View file

@ -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'

4
python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit.yaml
View file

@ -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'

4
python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16.yaml
View file

@ -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'

4
python/llm/test/benchmark/igpu-perf/32-32_int4_fp16.yaml
View file

@ -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'