GitLab

* fix llama2 70b

* fix qwen quantization

* remove pdb

* add faq

* add restful api

* refine

* add simple doc

* lint

* add uvicorn requirement

* more args

* add llama2

* docstring

* update doc

* save

* refine

* lint

* better decode

* add v1/embedding

* add GenerateRequest

* add llama2 chat template

* correct profiling

* update documents

* add length judge

* add faq

* update doc and rename req_que to req_queue

* fix md link, use get_logger, fix sequence_end bug

* use another doc link for go to avoid lint error

* add api_client.py

* update doc

* update doc

* update function interface

* update FAQ

* resolve comments

* pass args like meta_prompt to model

* update chatbot

* update

* rollback

* update llama2 and qwen

* refine

* qwen support

* dynamic ntk & logn attn

* fix ntk & add chat template

* fix ntk scaling & stop words

* fix lint

* add tiktoken to requirements.txt

* fix tokenizer, set model format automatically

* update model.py

* update readme

* fix lint

* import if lib directory exists

* only modify app.py

* rollback

* rollback chatbot.py

* feat(quantization): kv cache use asymmetric

* 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`

* support kv cache offload

* add dataloader docstring

* complete gitignore

* refactor collect mod fn

* add calibration

* fix lint

* add observers and quantizers

* fix lints

* add global available mixin

* fix lints

* split batch inference

* support smoothquant and awq

* update export kv scales

* fix lints

* fix some bugs

* update weight only usage

* update usage

* auto mapping and support smooth internlm

* trust remote code

* fix num head key error

* fix bias error

* align shape and pack order with llm-awq

* modified according to LZHgrla's comments.

* update gitignore

* fix kv qparams export error

* update usage

* decouple calibrate and awq

* update docstrings

* update api name

* update readme

* update readme

* update readme

* update readme

* update kv_qparams and readme

* fix typos

* add some dist utils

* add model utils

* add termio and basicstreamer

* typo

* fix world size

* refactor chat and tested llama1

* add internlm adapter and support stoping criteria

* concat with id for internlm

* update docstring

* update and support llama2

* typo

* move docs to docs

* update docstring of session manager

* update docstring

* update docs

* fix accel none in model

* fix and add test for tensor broadcast

* fix session using typing to check type

* add docstrings and comprehensive condition test

* unit test for dist

* fix session

* split unittests of utils

* typo

* update control flow of accel

* move test model

* remove main in unittest

* remove some log

* remove some comments

* add non-stream inference api for chatbot

* update according to reviewer's comments

* add get_small_sharded_hf.py

* fix pre-commit

* change to incremental decoding

* update

* use local model for webui

* local model for app.py

* lint

* remove print

* add seed

* comments

* fixed seesion_id

* support turbomind batch inference

* update app.py

* lint and docstring

* move webui to serve/gradio

* update doc

* update doc

* update docstring and rmeove print conversition

* log

* Update docs/zh_cn/build.md
Co-authored-by: Chen Xin <xinchen.tju@gmail.com>

* Update docs/en/build.md
Co-authored-by: Chen Xin <xinchen.tju@gmail.com>

* use latest gradio

* fix

* replace partial with InterFace

* use host ip instead of coolie

---------
Co-authored-by: Chen Xin <xinchen.tju@gmail.com>

* 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

* defer symlink

* fix lint

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

* decode only forward pass

* fix lint

* batch embedding

* 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 profile throughput benchmark

* add output only throughput

* update req/min

* update benckmark readme

* fix lint

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

* Fix lmdeploy.serve.turbomind bug
* add __init__.py for turbomind
* add resume function
* fix the assignment for session.response

* Fix code style

* 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

* [Fix] fix issue 127

* 优化防止接口更改

* 如果没有deepspeed用python启动需要手动加载到GPU上

* rollback the changes about max_out_tokens and delelte torch > 2.0 if statement

* support kernel injection with customized deepspeed

* spelling error

* Update chat.py

---------
Co-authored-by: wangruohui <12756472+wangruohui@users.noreply.github.com>

* 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>

* fix get_dataset error

* fix lint

* add datasets to requirements.txt

* update some msci

* 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>

* wip

* profile disable tp

* fix profile

* lint

* fix dlpack

* remove comment

* add tp flag

* add session len check

* add eos

* remove tp and session len inputs

* warp tokenizer

* multithread load weight

* update profile

* refactor tokenizer

* remove pre/post process

* remove mpi4py requirement

* remove

* remove bind

* remove mpi requirement

* check backend_tokenizer