GitLab

* add

* import fire in main

* wrap to speed up fire cli

* update

* update docs

* update docs

* fix

* resolve commennts

* resolve confict and add test for cli

* tmp

* update

* update

* update

* update

* update

* remove

* update

* update

* add w4a16

* fix `deploy.py`

* add doc

* add w4a16 kernels

* fuse w1/w3 & bugfixes

* fix typo

* python

* guard sm75/80 features

* add missing header

* refactor

* qkvo bias

* update cost model

* fix lint

* update `deploy.py`

* refactor model.py and support baichuan-7b

* remove model_name

* remove hard session_len

* export tokenizer.py to target dir

* remove model_name from client

* remove model_name

* update

* correct throughput equation

* fix session.response

* update serving.md

* update readme

* update according to review comments

* update

* update

* update

* update

* [bugfix] Fix some docs' bug in 'serving'

* [bugfix] Fix some docs' bug in 'serving'

* docs(serving.md): typo

* docs(README): quantization

* update contrib

* update links

* add performance

* use png

* update

* update

* update

* update

* update