Merge branch 'dev_triton' of https://huggingface.co/Qwen/Qwen-7B-Chat-Int4 into pr/11

Update README of branch dev_triton.

Pull updates from branch 'main' of https://huggingface.co/Qwen/Qwen-7B-Chat-Int4.

update wechat

update wechat

update modeling_qwen.py

update modeling_qwen.py

Merge branch 'dev_triton' of https://huggingface.co/Qwen/Qwen-7B-Chat-Int4 into pr/8

update modeling_qwen.py

Add ApplyRoPE and RMSNorm kernels written in OpenAI Triton.

update modeling_qwen.py

update

remove fix-sized causal mask

update wechat.png

add kernel file check in modeling_qwen.py

update modeling.py

update int8 quantization info

update modeling_qwen.py

update batch inference

update default generate hyperparams

format

update tokenization.py

update tokenization.py

Update README.md

Update README.md (#5)

Update README.md

Update README.md

softmax_in_fp32

update modeling_qwen.py

update kernels

update modeling_qwen.py

update modeling_qwen.py

Upload 2 files

Upload code_interpreter_showcase_001.jpg

update kvcache

update readme

update model