AttributeError: partially initialized module 'deepspeed' has no attribute 'init_inference'

To Reproduce
inference script:
`import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
import deepspeed

model_name = "/home/pzl/models/Qwen2.5-3B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

ds_engine = deepspeed.init_inference(model,
mp_size=1,
dtype=torch.half,
replace_with_kernel_inject=True)

input_text = "DeepSpeed is?"
inputs = tokenizer(input_text, return_tensors="pt")

with torch.no_grad():
outputs = ds_engine.module.generate(**inputs, max_length=10)

output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(output_text)
`
Expected behavior
get the correct result

ds_report output

Screenshots

System info (please complete the following information):

• OS: Ubuntu 22.04
• GPU count and types 0
• Python 3.10

Start by reproducing the provided inference script, focusing on the deepspeed.init_inference entry point and capturing the full traceback and installed environment details. Done means the cause of the AttributeError is identified and the script completes with the expected generated output, with any required configuration documented.