qwen2.5 run error

import xfastertransformer as xft
from transformers import AutoTokenizer, TextStreamer

MODEL_PATH="~/llms/model_xft"

TOKEN_PATH="~/llms/model_hf"

INPUT_PROMPT="what is apple?"

tokenizer = AutoTokenizer.from_pretrained(TOKEN_PATH, use_fast=True, padding_side="left", trust_remote_code=True)
streamer = TextStreamer(tokenizer, skip_special_tokens=True, skip_prompt=False)

input_ids = tokenizer(INPUT_PROMPT, return_tensors="pt", padding=False).input_ids
model = xft.AutoModel.from_pretrained(MODEL_PATH, dtype="bf16")
generated_ids = model.generate(input_ids, max_length=200, streamer=streamer)

[INFO] SeqLen > FLASH_ATTN_THRESHOLD(8192) will enable FlashAttn.
[INFO] ENABLE_TUNED_COMM is enabled for faster reduceAdd.
[INFO] ENABLE_KV_TRANS is enabled for faster decoding.
[INFO] SINGLE_INSTANCE MODE.
Process finished with exit code 132 (interrupted by signal 4: SIGILL)