BKCL_PCIE_RING=1 PYTORCH_NO_XPU_MEMORY_CACHING=1 XMLIR_D_XPU_L3_SIZE=0 \ mpirun -n 2 --allow-run-as-root \ python3 run.py \ --max_output_len=50 \ --engine_dir=./downloads/gptneox_model/trt_engines/fp16/2-XPU/ \ --tokenizer_dir=./downloads/gptneox_model \ --performance_test_scale=1x512x256E2x512x256E4x512x256E8x512x256 \ --log_level=info