Support autoround v0.7

[Kaihui-intel]

Type of Change

feature or bug fix or documentation or validation or others
API changed or not

Description

        fp32_model = copy.deepcopy(self.gptj)
        quant_config = AutoRoundConfig(nsamples=32, seqlen=10, iters=10, amp=False ,scale_dtype="fp16", 
                                       scheme=scheme, export_format="llm_compressor")
        logger.info(f"Test AutoRound with config {quant_config}")

        # quantizer execute
        model = prepare(model=fp32_model, quant_config=quant_config)
        run_fn(model, self.dataloader)
        q_model = convert(model)

Expected Behavior & Potential Risk

the expected behavior that triggered by this PR

How has this PR been tested?

how to reproduce the test (including hardware information)

Dependency Change?

any library dependency introduced or removed