pip install flash_attn 提示

[CloudWise-Lukemiao]

我的demo 代码如下：import torch
from modelscope import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "/root/clark/DeepSeek-V2-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

max_memory = {i: "75GB" for i in range(8)}
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16, max_memory=max_memory)
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id

messages = [
{"role": "user", "content": "Write a piece of quicksort code in C++"}
]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
print(result)

[yunyiyun]

https://gitee.com/ascend/pytorch/issues/I9OVU3?from=project-issue