from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3.6-35B-A3B",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model = PeftModel.from_pretrained(base, "ying2022/qwen3-6-35b-xlam-tools-lora")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3.6-35B-A3B")

messages = [{"role": "user", "content": "<your prompt here>"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
outputs = model.generate(inputs, max_new_tokens=500, temperature=0.3)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Serving with vLLM

bash

vllm serve Qwen/Qwen3.6-35B-A3B \
  --enable-lora \
  --lora-modules adapter=ying2022/qwen3-6-35b-xlam-tools-lora \
  --max-loras 1 --max-lora-rank 64 \
  --tensor-parallel-size 2 \
  --gpu-memory-utilization 0.90 \
  --max-model-len 4096