[WIP] Support Hqq and Eetq quantization

[hjh0119]

PR type

• [x] Bug Fix
• [x] New Feature
• [x] Document Updates
• [ ] More Models or Datasets Support

PR information

New quantization algorithms:

• HQQ
• EETQ

Uniform quantization bit parameter as quantization_bit.

• The quant_bits parameter is deprecated; for compatibility purposes, it has been synchronized to quantization_bit.

To resolve the garbled output issue during inference with internvl-chat-v1.5-int8 on V100 machines, fix the dtype to bf16.

• https://github.com/modelscope/swift/issues/890