GitLab

* add api.py

* update serve function

* add model_name arg and provide examples

* docstring

* remove service_available

* type hint

* 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

* robust incremental decode for leading space

* speed up lookup as prefix_space_tokens is shorter than no_prefix_space_tokens

* add UT and fix qwen stuff

* move tokenizer

* remove Tokenizer in init

* update deploy.py

* expose stop words

* support string

* fix

* remove eoa from chatbot

* remove eoa of turbomind

* fix ut

* suffix wheel and fix InternLM no system bug

* better profiler

* wait for releasing mem

* remove fire

* remove support for multiple model benchmark

* comments

* support actual seqlen

* change chat template

* update

* fix ut

* int->size_t

* output more details

* correct tp

* rollback

* update

* update readme

* add 'internlm-chat' as the default tag for internlm chat models

* rollback tokenizer

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

* support actual seqlen

* fix lint

* update variable types

* lint

* update type

* fix lint

---------

* tmp

* add demo for codellama inference

* update

* update

* update

* update codellama.md

* export rope_theta

* update

* update doc

* fix client.py

* define SamplingParam

* rollback 'end'

* rotary_emb_base to rotary_embedding_base

* change to baichuan2-7b

* first

* fix causal mask

* disable flash attention2 on sm70

* fix 2

* update readme

* clang-format

* disable ft2 on windows

* fix lint

* fix build

* fix build

* fix long kv seq

* fix lint

* sync copy output

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

* support decode

* unit test and benckmark and improve

* remove some drafts

* enable numerical test

* minor

* add some benchmark data

* add more output

* update interface

* remove debugs

* format

* update docstring

* remove print and add benchmark results

* use logits & add main

* fix rb

* dump large

* update test

* update test decode

* add decimal

* __PRETTY_FUNCTION__

* CASE_K

* uint

* remove not

* HALF_FLT_MAX

* struct init

* port utils

* better build pthread-win32

* port kernels

* port utils/gemm_test

* hide windows header

* port models

* port examples && triton_backend && unittests

* update build readme

* fix lint

* fix lint

* fix lint

* fix lint

* fix lint

* fix build

* fix build

* cmake version

* fix typos

* update ci

* port kernels/gemm_s_f16

* update ci

* fix ci

* use cudaStreamSynchronize instead of volatile check

* remove gettimeofday

* remove pthread-win32

* remove dirent.h

* update pre-commit

* update

* remove todo

* fix include

* fix build

* fix build

* fix build ci

* fix github action trigger

* update README

* fix linux-build ci

* remove windows folder

* fix lint

* update readme

* 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

* fix build tests failure

* move src test cases to tests/csrc

* 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

* update log info

* format cuda utils

* 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

* wip

* wip

* example finish

* fix include and namespace

* wtf

* install lib

* batchize

* update cmake install

* multithread

* fix comment

* fix

* add mmengine

* bind llamamodel

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

* build turbomind

* change namespace fastertransformer to turbomind

* change logger name

* temp

* fix lint

* csrc->src

* remove clang-format

* skip .rst

* skip doc

* clang-format

version

version

* mat_B

* add ft code

* gitignore

* fix lint

* revert fmha