Fix bug caused by 'groupsize' vs 'group_size' and change all code to use 'group_size' consistently

[TheBloke]

Today I found a bug in the quantisation code caused by #43 . in auto_gptq/modeling/_utils.py it uses groupsize but code calling it passes group_size.

I fixed that, and then thought I should update the whole repo to be consistent. I think it would be great if one name was used consistently throughout the repo. This will help avoid bugs and confusion. And 'group_size' seems to be the best name to use, as that's what's used in quantize_config.json.

With this PR merged into faster-llama, all *.py files use 'group_size' . There are no longer any references to 'groupsize'.

Before:

tomj@Eddie ~/src/AutoGPTQ (faster-llama)$ find . -name "*.py" -exec grep -o "group_size" {} + | wc -l
      38
tomj@Eddie ~/src/AutoGPTQ (faster-llama)$ find . -name "*.py" -exec grep -o "groupsize" {} + | wc -l
      54

After:

tomj@Eddie ~/src/TheBloke_AutoGPTQ (TheBloke_faster-llama_groupsize_fix)$ find . -name "*.py" -exec grep -o "group_size" {} + | wc -l
      92
tomj@Eddie ~/src/TheBloke_AutoGPTQ (TheBloke_faster-llama_groupsize_fix)$ find . -name "*.py" -exec grep -o "groupsize" {} + | wc -l
       0

Note: I only changed .py files, not any CUDA kernels. I don't know CUDA code and don't want to risk touching anything which I don't understand, in case there any implications I don't know about.

I have done tests of Triton and CUDA inference, and Triton and CUDA quantisation, and all seems OK.

Hope this change is OK with you guys, @PanQiWei @qwopqwop200 ?

[PanQiWei]

Thank you very much for standardize the spell of 'groupsize' to 'group_size'! ❤️