Does tensor_parallel support the model inference concurrently or in multi-threads? about tensor_parallel HOT 2 CLOSED

from transformers import AutoModelForCausalLM, AutoTokenizer
import threading
import tensor_parallel as tp
import torch

checkpoint = "bigcode/starcoderbase"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint, torch_dtype=torch.float16,low_cpu_mem_usage=True, trust_remote_code=True)
model = tp.tensor_parallel(model, sharded=False)

def task():
    inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to("cuda")
    outputs = model.generate(inputs)
    print(tokenizer.decode(outputs[0], clean_up_tokenization_spaces=False))

thread1 = threading.Thread(target=task)
thread2 = threading.Thread(target=task)

thread1.start()
thread2.start()

thread1.join()
thread2.join()