[vLLM] Support vLLM CPU backend and provide QBits acceleration (#1551)

Co-authored-by: VincyZhang <[email protected]>
Co-authored-by: Wang, Chang <[email protected]>

Update modeling_auto.py (#1499)

Signed-off-by: Wang, Chang <[email protected]>

[Transformers] Support load mode from HF Hub when use Neural Speed (#…

…1449)

Co-authored-by: Wenxin Zhang <[email protected]>
Co-authored-by: changwangss <[email protected]>

[NeuralChat] Fix tgi endpoint in test (#1388)

fix ut (#1307)

Support weight-only kernel with IPEX for intel GPU (#1153)

[LLM Runtime] Fix convert mistral script missing parameter issue (#1100)

[LLM Runtime] dynamic link the layer to compress binary size (#1059)

Co-authored-by: Ding, Yi <[email protected]>

Merge branch 'lvl/fix_config_parameters' into llmaas1.3.0

fix checkmarx issue (#842)

Signed-off-by: Wenxin Zhang <[email protected]>