RichardWooSJTU

support v100 csrc

4

### PR types Bug fixes ### PR changes Others ### Description Support csrc building on sm70

Restruct 52 open

4

### PR types New features ### PR changes Others ### Description 5.2

[Inference GPT] Fix 345M load path and use auto_model to export quant model

1

1. Add auto export shell script and config file for GPT quant model 2. Fix GPT fp16 model exporting error

[LLM] Fix v100 csrc building

5

### PR types Bug fixes ### PR changes Others ### Description csrc building enable bfloat16 default, which is not supported when cuda arch < sm80. This PR add `CUDA_ENBALE_BF16` macro...