Cheng, Penghui

> @PenghuiCheng Awesome. Does Qbits support any x86_64 including amd and non-validated intel? Also is this limited to only some recent gen chips? I only see that two classes of...

@Qubitium , Hi, we are not sure if we have done everything appropriately, but we expect your review. Please let us know if there's anything we can do to improve...

@kranipa , This issue is caused by mismatch the version of ITREX and neural-compressor. You can use neural-compressor version 2.5.1 and try it again. ITREX 1.4 is released now, Please...

@PhzCode , could you post your code and let me try to reproduce it. thanks very much.

Could we add a document introducing what h2o is?

Hi，@YangShuaiTHU, Could you tell us what model you used? I test loading/saving in UT:tests/CI/test_weight_only_gpu.py, it is OK. BTW, we used Transformers version is 4.34.1

now the issue has been fixed.

Hi, @benjamin-marie , what version do you use? I try to reproduce your issue on intel-extension-for-transformers version 1.3.1 and transformers version 4.36.2. It is OK in my side. thanks! Cheng,...

hi, @songhan, This PR is based on [RFC](https://github.com/casper-hansen/AutoAWQ/issues/390), could you help review it or assign it to suitable personnel?

@casper-hansen We are delighted to see your suggestions for this PR, which can help us better understand your requirements. Looking forward to your review.