ipex-llm/python/llm/test/benchmark/igpu-perf/1024-128.yaml
Xu, Shuo f9a199900d
add model RWKV/v5-Eagle-7B-HF to igpu benchmark (#11528)
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-08 15:50:16 +08:00

24 lines
867 B
YAML

repo_id:
- 'THUDM/chatglm3-6b'
- 'THUDM/glm-4-9b-chat'
- 'baichuan-inc/Baichuan2-7B-Chat'
- 'baichuan-inc/Baichuan2-13B-Chat'
- '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'
- 'RWKV/v5-Eagle-7B-HF'
local_model_hub: 'path to your local model hub'
warm_up: 1
num_trials: 3
num_beams: 1 # default to greedy search
low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
batch_size: 1 # default to 1
in_out_pairs:
- '1024-128'
test_api:
- "transformer_int4_gpu_win" # on Intel GPU for Windows (catch GPU peak memory)
cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)