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

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

Browse source
This commit is contained in:
Jun Wang 2024-07-08 11:12:15 +08:00 committed by GitHub
parent 64cfed602d
commit 5a57e54400
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 25 additions and 0 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

@ -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

1
python/llm/test/benchmark/igpu-perf/1024-128_437.yaml
View file

@ -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

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

@ -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

1
python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_437.yaml
View file

@ -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

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

@ -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

1
python/llm/test/benchmark/igpu-perf/1024-128_int4_fp16_loadlowbit_437.yaml
View file

@ -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

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

@ -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

1
python/llm/test/benchmark/igpu-perf/2048-256_int4_fp16_437.yaml
View file

@ -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

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

@ -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

1
python/llm/test/benchmark/igpu-perf/32-32_int4_fp16_437.yaml
View file

@ -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