codeFuse在本地推理特别慢，怎么提速

我再modelscope环境下，使用https://modelscope.cn/models/codefuse-ai/CodeFuse-StarCoder-15B/summary 里面的quickstart代码,然后部署到4个T4卡的机器上，结果出来特别慢，要10分钟以上（不包括下载和加载模型这些时间）

import torch
from modelscope import (
    AutoTokenizer, 
    AutoModelForCausalLM,
    snapshot_download
)
model_dir = snapshot_download('codefuse-ai/CodeFuse-StarCoder-15B',revision = 'v1.0.0')
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True, use_fast=False, legacy=False)
tokenizer.padding_side = "left"
tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids("<fim_pad>")
tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids("<|endoftext|>")
tokenizer.pad_token = "<fim_pad>"
tokenizer.eos_token = "<|endoftext|>"
# try 4bit loading if cuda memory not enough
model = AutoModelForCausalLM.from_pretrained(model_dir,
                                             trust_remote_code=True,
                                             load_in_4bit=False,
                                             device_map="auto",
                                             torch_dtype=torch.bfloat16)
model.eval()

HUMAN_ROLE_START_TAG = "<|role_start|>human<|role_end|>"
BOT_ROLE_START_TAG = "<|role_start|>bot<|role_end|>"

text = f"{HUMAN_ROLE_START_TAG}write a python function of quick sort.{BOT_ROLE_START_TAG}" 
inputs = tokenizer(text, return_tensors='pt', padding=True, add_special_tokens=False).to("cuda")
outputs = model.generate(
        inputs=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        max_new_tokens=512,
        top_p=0.95,
        temperature=0.1,
        do_sample=True,
        eos_token_id=tokenizer.eos_token_id,
        pad_token_id=tokenizer.pad_token_id
    )
gen_text = tokenizer.batch_decode(outputs[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(gen_text)