…ech#4396)

* improve stablility of zero

* fix wrong index

* add record stream

* style: apply formatter

* fix: add outdated warnings

* docs: add dataset format and polish

* docs: polish README

* fix: fix json format

* fix: fix typos

* revert: revert 7b example

…ech#4430)

Co-authored-by: Siyuan Tian <siyuant@vmware.com>

* [cluster] add process group mesh

* [test] add process group mesh test

* force sync

* [pipeline] add stage manager

* [test] add pipeline stage manager test

* [pipeline] add docstring for stage manager

* [pipeline] add p2p communication

* [test] add p2p communication test

* [test] add rerun decorator

* [test] rename to avoid conflict

* [api] update optimizer wrapper to fit pipeline

* [pipeline] add base schedule

* [pipeline] add 1f1b schedule

* [test] add pipeline schedule utils test

* [pipeline] fix import

* add pipeline policy and bert forward to be done

* add bertmodel pipeline forward and make tests

* add Bert_Policy and test for policy

* update formatting

* update formatting

* update the code

* fix bugs

* fix name confilt

* [pipeline] add stage manager

* [test] add pipeline stage manager test

* [pipeline] add docstring for stage manager

* add pipeline policy and bert forward to be done

* add bertmodel pipeline forward and make tests

* add Bert_Policy and test for policy

* update formatting

* update formatting

* update the code

* fix bugs

* fix name confilt

…licy (hpcaitech#4161)

* add pipeline policy and bert forward to be done

* add bertmodel pipeline forward and make tests

* add Bert_Policy and test for policy

* update formatting

* update formatting

* update the code

* fix bugs

* fix name confilt

* add bloom model and policy ,revise the base class of policy

* revise

* revision

* add bert_for_pretraining

…pcaitech#4172)

* add pipeline policy and bert forward to be done

* add bertmodel pipeline forward and make tests

* add Bert_Policy and test for policy

* update formatting

* update formatting

* update the code

* fix bugs

* fix name confilt

* add bloom model and policy ,revise the base class of policy

* revise

* revision

* add bert_for_pretraining

* add bert_for_pretraining forward and policy

* fix typos

* cancel warning

* change the imediate output to default dict

* change the default output of get_shared_params

…itech#4187)

* move bert related pipeline components to shardformer

* fix bugs

* revision

* fix bert model tests

* fix bert_lm_head model tests

* fix tests

* fix tests

* done checks

* skip bloom

* [shardformer] support lazy init

* [shardformer] linear support lazy init

* [shardformer] embedding support lazy init

* [shardformer] norm support lazy init

* [shardformer] fused linear support lazy init

* [test] update shardformer test layer

* [test] shardformer with lazy init fit ddp

* [lazy] hotfix deepcopy of param

* [shardformer] fix bert policy and update test

* [shardformer] fix bloom policy and update test

* [shardformer] fix opt policy and update test

* [shardformer] fix t5 policy and update test

* [shardformer] fix gpt2 policy and update test

* [shardformer] fix llama policy and update test

* add pipeline forward

* complete pipeline forward check

* fix bert forward without pipeline

* fix comments

* discard useless line

* add todo

* clean prints

* fix distribute layers

* bloom policy

* llama pipeline forward and tests

* fix the output and attention_mask

* fix name

* bind argument to policy

* Revert "bloom policy"

This reverts commit 8dee68a.

This policy should be revert and copied to feature/bloom

* revert the bloom changes

* cancel unneeded inputs

* gpt

…line (hpcaitech#4208)

* bloom policy

* llama pipeline forward and tests

* fix the output and attention_mask

* fix name

* bind argument to policy

* Revert "bloom policy"

This reverts commit 8dee68a.

This policy should be revert and copied to feature/bloom

* revert the bloom changes

* cancel unneeded inputs

* gpt

* finish llama

* causal lm and sequence classification

* revision

* bloom policy

* llama pipeline forward and tests

* fix the output and attention_mask

* fix name

* bind argument to policy

* finish bloom model

* test shard gpt2

* clear cache

…4224)

* * fix typehint & docstring in sharder.py

* * update pipeline forward for GPT2Model

* * add test for pipeline forward of GPT2Model

* * add cache cleaning in gpt2 test

* * change assert to raise command

* add forward for GPTLMHeadModel

* add test for gpt_lm

* arranging get_held_layers method

* arrange forward replacement

* add forward for GPT2ForTokenClassification

* add forward for GPT2ForSequenceClassification

* fix test_shard_gpt2.py

* add GPT2DoubleHeadsmodel & fix bugs

* add id checking in get_shared_params

* bloom policy

* llama pipeline forward and tests

* fix the output and attention_mask

* fix name

* bind argument to policy

* Revert "bloom policy"

This reverts commit 8dee68a.

This policy should be revert and copied to feature/bloom

* revert the bloom changes

* cancel unneeded inputs

* gpt

* finish llama

* causal lm and sequence classification

* revision

* add pure pipeline test

* finish some bert models

* finish all bert models

* finish bert tests

* fix bugs

* fix bugs

* fix test pipeline

* fix data gen for qa

* update the set pipeline forward

* shared params

* fix bugs

* bloom policy

* llama pipeline forward and tests

* fix the output and attention_mask

* fix name

* bind argument to policy

* finish bloom model

* test shard gpt2

* clear cache

* support all bloom models

* add bloom models policies

* finish bloom pipeline and tests

* add set pipeline

* finish bloom

…HybridParallelPlugin (hpcaitech#4624)

* Enable policy assignment in HybridPlugin and enable llama policy for llamav2

* Remove Policy from Plugin

* revert changes of plugin

HybridParallelModule

* revert changes in plugin

* upgrade transformers

* revert transformers version

---------

Co-authored-by: flybird11111 <1829166702@qq.com>

)

* set optimizer to optional in execute_pipeline

* arrange device and mixed precision in booster init

* fix execute_pipeline in booster.py

* update vit example for hybrid plugin

* reset tp/pp size

* fix dataloader iteration bug

* update optimizer passing in evaluation/add grad_accum

* change criterion

* wrap tqdm

* change grad_accum to grad_checkpoint

* fix pbar

* [devops] fix concurrency group

* [devops] fix compatibility test

* [devops] fix tensornvme install

* [devops] fix tensornvme install

* [devops] fix colossalai install

hpcaitech#4645)

* [shardformer] update shardformer readme

[shardformer] update shardformer readme

[shardformer] update shardformer readme

* [shardformer] update llama2/opt finetune example and shardformer update to llama2

* [shardformer] update llama2/opt finetune example and shardformer update to llama2

* [shardformer] update llama2/opt finetune example and shardformer update to llama2

* [shardformer] change dataset

* [shardformer] change dataset

* [shardformer] fix CI

* [shardformer] fix

* [shardformer] fix

* [shardformer] fix

* [shardformer] fix

* [shardformer] fix

[example] update opt example

[example] resolve comments

fix

fix

…aitech#4671)

* [legacy] move communication to legacy (hpcaitech#4640)

* [legacy] refactor logger and clean up legacy codes (hpcaitech#4654)

* [legacy] make logger independent to gpc

* [legacy] make optim independent to registry

* [legacy] move test engine to legacy

* [legacy] move nn to legacy (hpcaitech#4656)

* [legacy] move nn to legacy

* [checkpointio] fix save hf config

* [test] remove useledd rpc pp test

* [legacy] fix nn init

* [example] skip tutorial hybriad parallel example

* [devops] test doc check

* [devops] test doc check

* [shardformer]fix gpt2 test

[shardformer]fix gpt2 test

[shardformer]fix gpt2 test

* fix

* [shardformer] add todo

* [shardformer] add todo

…nd related kernels for our inference system (hpcaitech#4577)

* [infer] Infer/llama demo (hpcaitech#4503)

* add

* add infer example

* finish

* finish

* stash

* fix

* [Kernels]  add inference token attention kernel (hpcaitech#4505)

* add token forward

* fix tests

* fix comments

* add try import triton

* add adapted license

* add tests check

* [Kernels] add necessary kernels (llama & bloom) for attention forward and kv-cache manager  (hpcaitech#4485)

* added _vllm_rms_norm

* change place

* added tests

* added tests

* modify

* adding kernels

* added tests:

* adding kernels

* modify

* added

* updating kernels

* adding tests

* added tests

* kernel change

* submit

* modify

* added

* edit comments

* change name

* change commnets and fix import

* add

* added

* combine codes (hpcaitech#4509)

* [feature] add KV cache manager for llama & bloom inference (hpcaitech#4495)

* add kv cache memory manager

* add stateinfo during inference

* format

* format

* rename file

* add kv cache test

* revise on BatchInferState

* file dir change

* [Bug FIx] import llama context ops fix (hpcaitech#4524)

* added _vllm_rms_norm

* change place

* added tests

* added tests

* modify

* adding kernels

* added tests:

* adding kernels

* modify

* added

* updating kernels

* adding tests

* added tests

* kernel change

* submit

* modify

* added

* edit comments

* change name

* change commnets and fix import

* add

* added

* fix

* add ops into init.py

* add

* [Infer] Add TPInferEngine and fix file path (hpcaitech#4532)

* add engine for TP inference

* move file path

* update path

* fix TPInferEngine

* remove unused file

* add engine test demo

* revise TPInferEngine

* fix TPInferEngine, add test

* fix

* Add Inference test for llama (hpcaitech#4508)

* add kv cache memory manager

* add stateinfo during inference

* add

* add infer example

* finish

* finish

* format

* format

* rename file

* add kv cache test

* revise on BatchInferState

* add inference test for llama

* fix conflict

* feature: add some new features for llama engine

* adapt colossalai triton interface

* Change the parent class of llama  policy

* add nvtx

* move llama inference code to tensor_parallel

* fix __init__.py

* rm tensor_parallel

* fix: fix bugs in auto_policy.py

* fix:rm some unused codes

* mv colossalai/tpinference to colossalai/inference/tensor_parallel

* change __init__.py

* save change

* fix engine

* Bug fix: Fix hang

* remove llama_infer_engine.py

---------

Co-authored-by: yuanheng-zhao <jonathan.zhaoyh@gmail.com>
Co-authored-by: CjhHa1 <cjh18671720497@outlook.com>

* [infer] Add Bloom inference policy and replaced methods (hpcaitech#4512)

* add bloom inference methods and policy

* enable pass BatchInferState from model forward

* revise bloom infer layers/policies

* add engine for inference (draft)

* add test for bloom infer

* fix bloom infer policy and flow

* revise bloom test

* fix bloom file path

* remove unused codes

* fix bloom modeling

* fix dir typo

* fix trivial

* fix policy

* clean pr

* trivial fix

* Revert "[infer] Add Bloom inference policy and replaced methods (hpcaitech#4512)" (hpcaitech#4552)

This reverts commit 17cfa57.

* [Doc] Add colossal inference doc (hpcaitech#4549)

* create readme

* add readme.md

* fix typos

* [infer] Add Bloom inference policy and replaced methods (hpcaitech#4553)

* add bloom inference methods and policy

* enable pass BatchInferState from model forward

* revise bloom infer layers/policies

* add engine for inference (draft)

* add test for bloom infer

* fix bloom infer policy and flow

* revise bloom test

* fix bloom file path

* remove unused codes

* fix bloom modeling

* fix dir typo

* fix trivial

* fix policy

* clean pr

* trivial fix

* trivial

* Fix Bugs In Llama Model Forward (hpcaitech#4550)

* add kv cache memory manager

* add stateinfo during inference

* add

* add infer example

* finish

* finish

* format

* format

* rename file

* add kv cache test

* revise on BatchInferState

* add inference test for llama

* fix conflict

* feature: add some new features for llama engine

* adapt colossalai triton interface

* Change the parent class of llama  policy

* add nvtx

* move llama inference code to tensor_parallel

* fix __init__.py

* rm tensor_parallel

* fix: fix bugs in auto_policy.py

* fix:rm some unused codes

* mv colossalai/tpinference to colossalai/inference/tensor_parallel

* change __init__.py

* save change

* fix engine

* Bug fix: Fix hang

* remove llama_infer_engine.py

* bug fix: fix bugs about infer_state.is_context_stage

* remove pollcies

* fix: delete unused code

* fix: delete unused code

* remove unused coda

* fix conflict

---------

Co-authored-by: yuanheng-zhao <jonathan.zhaoyh@gmail.com>
Co-authored-by: CjhHa1 <cjh18671720497@outlook.com>

* [doc] add colossal inference fig (hpcaitech#4554)

* create readme

* add readme.md

* fix typos

* upload fig

* [NFC] fix docstring for colossal inference (hpcaitech#4555)

Fix docstring and comments in kv cache manager and bloom modeling

* fix docstring in llama modeling (hpcaitech#4557)

* [Infer] check import vllm (hpcaitech#4559)

* change import vllm

* import apply_rotary_pos_emb

* change import location

* [DOC] add installation req (hpcaitech#4561)

* add installation req

* fix

* slight change

* remove empty

* [Feature] rms-norm transfer into inference llama.py  (hpcaitech#4563)

* add installation req

* fix

* slight change

* remove empty

* add rmsnorm polciy

* add

* clean codes

* [infer] Fix tp inference engine (hpcaitech#4564)

* fix engine prepare data

* add engine test

* use bloom for testing

* revise on test

* revise on test

* reset shardformer llama (hpcaitech#4569)

* [infer] Fix engine - tensors on different devices (hpcaitech#4570)


* fix diff device in engine

* [codefactor] Feature/colossal inference (hpcaitech#4579)

* code factors

* remove

* change coding (hpcaitech#4581)

* [doc] complete README of colossal inference (hpcaitech#4585)

* complete fig

* Update README.md

* [doc]update readme (hpcaitech#4586)

* update readme

* Update README.md

* bug fix: fix bus in llama and bloom (hpcaitech#4588)

* [BUG FIX]Fix test engine in CI and non-vllm kernels llama forward  (hpcaitech#4592)

* fix tests

* clean

* clean

* fix bugs

* add

* fix llama non-vllm kernels bug

* modify

* clean codes

* [Kernel]Rmsnorm fix (hpcaitech#4598)

* fix tests

* clean

* clean

* fix bugs

* add

* fix llama non-vllm kernels bug

* modify

* clean codes

* add triton rmsnorm

* delete vllm kernel flag

* [Bug Fix]Fix bugs in llama (hpcaitech#4601)

* fix tests

* clean

* clean

* fix bugs

* add

* fix llama non-vllm kernels bug

* modify

* clean codes

* bug fix: remove rotary_positions_ids

---------

Co-authored-by: cuiqing.li <lixx3527@gmail.com>

* [kernel] Add triton layer norm & replace norm for bloom (hpcaitech#4609)

* add layernorm for inference

* add test for layernorm kernel

* add bloom layernorm replacement policy

* trivial: path

* [Infer] Bug fix rotary embedding in llama (hpcaitech#4608)

* fix rotary embedding

* delete print

* fix init seq len bug

* rename pytest

* add benchmark for llama

* refactor codes

* delete useless code

* [bench] Add bloom inference benchmark (hpcaitech#4621)

* add bloom benchmark

* readme - update benchmark res

* trivial - uncomment for testing (hpcaitech#4622)

* [Infer] add check triton and cuda version for tests (hpcaitech#4627)

* fix rotary embedding

* delete print

* fix init seq len bug

* rename pytest

* add benchmark for llama

* refactor codes

* delete useless code

* add check triton and cuda

* Update sharder.py (hpcaitech#4629)

* [Inference] Hot fix some bugs and typos (hpcaitech#4632)

* fix

* fix test

* fix conflicts

* [typo]Comments fix (hpcaitech#4633)

* fallback

* fix commnets

* bug fix: fix some bugs in test_llama and test_bloom (hpcaitech#4635)

* [Infer] delete benchmark in tests and fix bug for llama and bloom (hpcaitech#4636)

* fix rotary embedding

* delete print

* fix init seq len bug

* rename pytest

* add benchmark for llama

* refactor codes

* delete useless code

* add check triton and cuda

* delete benchmark and fix infer bugs

* delete benchmark for tests

* delete useless code

* delete bechmark function in utils

* [Fix] Revise TPInferEngine, inference tests and benchmarks (hpcaitech#4642)

* [Fix] revise TPInferEngine methods and inference tests

* fix llama/bloom infer benchmarks

* fix infer tests

* trivial fix: benchmakrs

* trivial

* trivial: rm print

* modify utils filename for infer ops test (hpcaitech#4657)

* [Infer] Fix TPInferEngine init & inference tests, benchmarks (hpcaitech#4670)

* fix engine funcs

* TPInferEngine: receive shard config in init

* benchmarks: revise TPInferEngine init

* benchmarks: remove pytest decorator

* trivial fix

* use small model for tests

* [NFC] use args for infer benchmarks (hpcaitech#4674)

* revise infer default (hpcaitech#4683)

* [Fix] optimize/shard model in TPInferEngine init (hpcaitech#4684)

* remove using orig model in engine

* revise inference tests

* trivial: rename

---------

Co-authored-by: Jianghai <72591262+CjhHa1@users.noreply.github.com>
Co-authored-by: Xu Kai <xukai16@foxmail.com>
Co-authored-by: Yuanheng Zhao <54058983+yuanheng-zhao@users.noreply.github.com>
Co-authored-by: yuehuayingxueluo <867460659@qq.com>
Co-authored-by: yuanheng-zhao <jonathan.zhaoyh@gmail.com>
Co-authored-by: CjhHa1 <cjh18671720497@outlook.com>

* update booster_api.md

* update booster_checkpoint.md

* update booster_plugins.md

* move transformers importing inside function

* fix Dict typing

* fix autodoc bug

* small fix

* [shardformer] update shardformer readme

* [shardformer] update shardformer readme

* [shardformer] update shardformer readme

* [shardformer] update shardformer readme

* [shardformer] update shardformer readme

* add gptq

* refactor code

* fix tests

* replace auto-gptq

* rname inferance/quant

* refactor test

* add auto-gptq as an option

* reset requirements

* change assert and check auto-gptq

* add import warnings

* change test flash attn version

* remove example

* change requirements of flash_attn

* modify tests

* [skip ci] change requirements-test

* [skip ci] add cuda kernels

* add license

* [skip ci] fix max_input_len

* format files & change test size

* [skip ci]