chatglm4 多显卡部署

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


import os
os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'
#加上这行之后又恢复以前的速度了!
device = "cuda"


print("是否可用：", torch.cuda.is_available())        # 查看GPU是否可用
print("GPU数量：", torch.cuda.device_count())        # 查看GPU数量
print("torch方法查看CUDA版本：", torch.version.cuda)  # torch方法查看CUDA版本
print("GPU索引号：", torch.cuda.current_device())    # 查看GPU索引号
print("GPU名称：", torch.cuda.get_device_name(1))    # 根据索引号得到GPU名称

tokenizer = AutoTokenizer.from_pretrained("moxing",trust_remote_code=True)

query = "你好"

inputs = tokenizer.apply_chat_template([{"role": "user", "content": query}],
                                       add_generation_prompt=True,
                                       tokenize=True,
                                       return_tensors="pt",
                                       return_dict=True
                                       )

inputs = inputs.to(device)
model = AutoModelForCausalLM.from_pretrained(
    "moxing",
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True,
    device_map='auto'
).eval()

gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1}
with torch.no_grad():
    outputs = model.generate(**inputs, **gen_kwargs)
    outputs = outputs[:, inputs['input_ids'].shape[1]:]
    print(tokenizer.decode(outputs[0], skip_special_tokens=True))

cuda安装解决bug:
pytroch:
SError: [WinError 126] 找不到指定的模块。 Error loading “E:\python310\lib\site-packages\torch\lib\fbgemm.dll
https://blog.csdn.net/qq_43144781/article/details/139354789