GitLab

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

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

* Update README.md: use internlm-chat-7b

* Update README_zh-CN.md: use intern-chat-7b

* Doc: update discord and wechat link

* Doc: update discord and wechat link

* [Doc] add discord and wechat link

* [Doc] add discord and wechat link

* [Doc] add discord and wechat link

* [Doc] add discord and wechat link

* docs(serving.md): typo

* docs(README): quantization

* previous merged

* add chinese

* support torch<2

* add a docstring

* fix typo

* rename torch submodule

* rename to pytorch

* rename in readme

* update benchmark image

* update image url

* docs(README): fix script

* add performance

* use png

* update

* update

* update

* update

* update

* add demo gif

* add demo gif

* add cal qparams

* support offload inference

* add collect funtions (mod,weight)

* stats kv scales

* update init

* add user guide

* fix hints

* fix comments & support turbomind format

* update user guide

* fix slice kv cache error & support pileval dataset (used in llm-awq)

* fix wrong num heads slice

* update default dataset

* fix conflict

* fix hints

* fix hints

* add gitignore

* docs(README): update description

* docs(project): add quantization test results

* docs(README): reorder

* docs(quantization): add more description

* docs(README): remove openmmlab badge

* docs(README): scale up image

* docs(dir): add zh_cn subdir

* [Doc] add persistent batch inference

* update

* update

* Update README.md

* Update README_zh-CN.md

* change target tritonfastertransformerbackend to tritonturbomindbackend

* install targets to backends/turbomind

* changge model_dir

* build turbomind

* change namespace fastertransformer to turbomind

* change logger name

* change llmdeploy to lmdeploy

* update logo

* update readme

* add webui

* update readme

* resolve comments

* readme

* feat(src): add int8 and compile passed

* feat(kernels): fix

* feat(llama): update kernel

* feat(src): add debug

* fix(kernel): k_cache use int8_t pointer

* style(llama): clean code

* feat(deploy.py): revert to enable fmha

* style(LlamaV2): clean code

* feat(deploy.py): add default quant policy

* check-in dockerfile

* check-in dockerfile

* add logo

* update readme