GitLab

* feat(build): enable ninja and lld

* fix(.github): add ninja installation

* fix(CI): remove dimsize=256

* fix(CI): add option for generate.sh

* fix(docs): update

* fix

* fix lint

* turbomind support export model params

* fix overflow

* support turbomind.from_pretrained

* fix tp

* support AutoModel

* support load kv qparams

* update auto_awq

* udpate docstring

* export lmdeploy version

* update doc

* remove download_hf_repo

* LmdeployForCausalLM -> LmdeployForCausalLM

* refactor turbomind.py

* update comment

* add bfloat16 convert back

* support gradio run_locl load hf

* support resuful api server load hf

* add docs

* support loading previous quantized model

* adapt pr 690

* udpate docs

* not export turbomind config when quantize a model

* check model_name when can not get it from config.json

* update readme

* remove model_name in auto_awq

* update

* update

* udpate

* fix build

* absolute import

* tmp

* update

* update

* optimize for throughput

* update

* fix eos

* clean up

* fix serving

* fix indexed copy

* minor

* minor

---------
Co-authored-by: lvhan028 <lvhan_028@163.com>

* fix init of finished buf

* fix `finished_count`

* refresh decoder attention kernel

* block-level kv cache

* `BlockManager` & `SequenceManager`

* update

* update

* update

* update

* rename

* GQA support

* fix context length

* GQA dispatch

* kv8

* tune

* async stream cb

* nvtx

* config parsing

* debug

* optimize output cost

* split-k decoding

* minor

* truncate `session_len` by available blocks

* minor

* license

* fix

* dispatch `cp.async`

* fix linking

* fix

* fix deadlock

* guard input length

* correct start offset

* fix prefill chunking

* fix `cache_block_seq_len` param passing

* fix `block_size` fmtstr

* fix output tokens

* fix batch resizing

* fix masking of finished sequences

* add debug util

* free unused block early

* add ntk scaling and logn scaling

* cmake flags

* fix typo

* w4a16 for sm75

* fix msvc build

* fix msvc build

* fix block verification

* fix msvc build

* use `std::shuffle`

* fix lint

* fix lint

* fix lint

* clear incoming buffer

* clear finished requests

* fix batch initialization

* fix typo

* fix typo

* fix comparison

* Fix memory leak

* modern c++

* cuda allocator fix

* graceful termination

* lint and compilation fix

* support actual seqlen

* fix lint

* update variable types

* lint

* update type

* fix lint

---------

* reduce gil switching

* ffi lock func

* remove unused

* remove unused

* remove unused

* 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

* pack llama_gemm

* update CMakeLists.txt

* remove candidate

* update MANIFEST.in

* 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>

* Pad tok_embedding and output weights to make their shape divisible by TP

* update

* update

* update

* update

* update llamaBatch

* disable cache hint for CUDA < 11.4

* fix lint

* fix lint

* fix cuda-11.3 build

* 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

* __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

* 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`

* works on interlm and vicuna

* support GQA

* remove comment

* update readme, add logger, default tp=1

* remove log

* clean-up

* fix lint

* fix lint

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

* decode only forward pass

* fix lint

* batch embedding

* 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

* format-11.1

* md-link-config

* change target tritonfastertransformerbackend to tritonturbomindbackend

* install targets to backends/turbomind

* changge model_dir

* build turbomind

* change namespace fastertransformer to turbomind

* change logger name