diff --git a/python/llm/test/benchmark/arc-perf-test.yaml b/python/llm/test/benchmark/arc-perf-test.yaml index 9b5246bd..580adc50 100644 --- a/python/llm/test/benchmark/arc-perf-test.yaml +++ b/python/llm/test/benchmark/arc-perf-test.yaml @@ -8,6 +8,7 @@ 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) in_out_pairs: - '32-32' - '1024-128'