repo_id:
  - 'meta-llama/Llama-2-7b-chat-hf'
  - 'meta-llama/Llama-2-13b-chat-hf'
  - 'THUDM/chatglm2-6b'
  - 'THUDM/chatglm3-6b'
  - 'baichuan-inc/Baichuan2-7B-Chat'
  - 'baichuan-inc/Baichuan2-13B-Chat'
  - 'Qwen/Qwen-14B-Chat'
local_model_hub: '/mnt/disk1/models'
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:
  - '32-32'
  - '1024-128'
  - '2048-256'
test_api:
  - "transformer_int4"
  # - "native_int4"
  # - "optimize_model"
  # - "pytorch_autocast_bf16"
  # - "ipex_fp16_gpu" # on Intel GPU
  # - "transformer_int4_gpu"  # on Intel GPU
  # - "optimize_model_gpu"  # on Intel GPU
  # - "deepspeed_transformer_int4_cpu" # on Intel SPR Server
  # - "transformer_int4_gpu_win" # on Intel GPU for Windows (catch GPU peak memory)
cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)