在modelscope社区，阿里云弹性加速计算EAIS 执行错误，怎么解决？

"在modelscope社区，阿里云弹性加速计算EAIS 执行错误，怎么解决？：

from swift.llm import (
ModelType, get_vllm_engine, get_default_template_type,
get_template, inference_vllm
)
import torch
import os

os.environ['CUDA_VISIBLE_DEVICES'] = '0'

model_type = ModelType.qwen1half_1_8b_chat
llm_engine = get_vllm_engine(model_type)
template_type = get_default_template_type(model_type)
template = get_template(template_type, llm_engine.hf_tokenizer)
llm_engine.generation_config.max_new_tokens = 2048

request_list = [{'query': '蚂蚁'}, {'query': '大象'}]
resp_list = inference_vllm(llm_engine, template, request_list)
for request, resp in zip(request_list, resp_list):
print(f""query: {request['query']}"")
print(f""response: {resp['response']}"")

错误：ValueError: Bfloat16 is only supported on GPUs with compute capability of at least 8.0. Your Tesla P100-PCIE-16GB GPU has compute capability 6.0. You can use float16 instead by explicitly setting thedtype flag in CLI, for example: --dtype=half.

更改：
llm_engine = get_vllm_engine(model_type, torch_dtype=torch.float16)

错误：CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
"