ipex-llm/python/llm/test/benchmark/igpu-perf/1024-128_434.yaml

13 lines
483 B
YAML

repo_id:
- 'mistralai/Mistral-7B-Instruct-v0.1'
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)