GitLab

* works on interlm and vicuna

* support GQA

* remove comment

* update readme, add logger, default tp=1

* remove log

* bump version to v0.0.2

* fix command

* update installation and inference section

* Doc: add Twitter link

* Doc: add a space

* translate quantization doc

* revise

* Update README_zh-CN.md

* Update README.md

* Update README_zh-CN.md

* Update README.md

* Update README_zh-CN.md

* checkin benchmark on real conversation data

* change resolution

* update

* 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

* add GQA for llama2

* fix model conversion

* fix lint & remove dev log

* update news

* minor

* fix allocation size

* fix split_dim for w_qkv.bias

* add llama2 template

* update readme and fix lint

* update readme

* add bos

* add bos

* remove bos

* Update model.py

---------
Co-authored-by: grimoire <yaoqian@pjlab.org.cn>

* remove copy

* repetition_penalty=1

* add repetition_penalty to chat args

* update readme

* update readme

* update requirements

* update transformers version

* lint

* comments

* lint

* update requirements

* remove setup_requires

---------
Co-authored-by: dongchunyu <dongchunyu@pjlab.org.cn>

* docs: fix doc

* fix: fix lint

* [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

* draft torch client

* deal with space of tokenizer

* support tensor parallel

* fix

* fix

* move folder

* move instruction to readme

* move to torch/

* rename client to chat

* very bad response

* stash

* rename streamer

* support internlm

* change default args

* remove test

* improve instructions

* remove module docstring

* decrease header level of torch model

* 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