ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
1843 commits 1 branch 0 tags 37 MiB
Commit graph

614 commits

Author SHA1 Message Date
Yining Wang
d7334513e1 codeshell: fix wrong links (#9417) 2023-11-12 19:22:33 +08:00
Zheng, Yi
0674146cfb Add cpu and gpu examples of distil-whisper (#9374) 
* Add distil-whisper examples

* Fixes based on comments

* Minor fixes

---------

Co-authored-by: Ariadne330 <wyn2000330@126.com>
 2023-11-10 16:09:55 +08:00
Ziteng Zhang
ad81b5d838 Update qlora README.md (#9422) 2023-11-10 15:19:25 +08:00
Heyang Sun
b23b91407c fix llm-init on deepspeed missing lib (#9419) 2023-11-10 13:51:24 +08:00
SONG Ge
dfb00e37e9 [LLM] Add model correctness test on ARC for llama and falcon (#9347) 
* add correctness test on arc for llama model

* modify layer name

* add falcon ut

* refactor and add ut for falcon model

* modify lambda positions and update docs

* replace loading pre input with last decodelayer output

* switch lower bound to single model instead of using the common one

* make the code implementation simple

* fix gpu action allocation memory issue
 2023-11-10 13:48:57 +08:00
dingbaorong
36fbe2144d Add CPU examples of fuyu (#9393) 
* add fuyu cpu examples

* add gpu example

* add comments

* add license

* remove gpu example

* fix inference time
 2023-11-09 15:29:19 +08:00
Heyang Sun
df8e4d7889 [LLM] apply allreduce and bias to training in LowBitLinear (#9395) 2023-11-09 14:35:54 +08:00
Wang, Jian4
40cead6b5b LLM: Fix CPU qlora dtype convert issue (#9394) 2023-11-09 14:34:01 +08:00
WeiguangHan
34449cb4bb LLM: add remaining models to the arc perf test (#9384) 
* add remaining models

* modify the filepath which stores the test result on ftp server

* resolve some comments
 2023-11-09 14:28:42 +08:00
Ruonan Wang
bfca76dfa7 LLM: optimize QLoRA by updating lora convert logic (#9372) 
* update convert logic of qlora

* update

* refactor and further improve performance

* fix style

* meet code review
 2023-11-08 17:46:49 +08:00
binbin Deng
54d95e4907 LLM: add alpaca qlora finetuning example (#9276) 2023-11-08 16:25:17 +08:00
binbin Deng
97316bbb66 LLM: highlight transformers version requirement in mistral examples (#9380) 2023-11-08 16:05:03 +08:00
Ruonan Wang
7e8fb29b7c LLM: optimize QLoRA by reducing convert time (#9370) 2023-11-08 13:14:34 +08:00
Chen, Zhentao
298b64217e add auto triggered acc test (#9364) 
* add auto triggered acc test

* use llama 7b instead

* fix env

* debug download

* fix download prefix

* add cut dirs

* fix env of model path

* fix dataset download

* full job

* source xpu env vars

* use matrix to trigger model run

* reset batch=1

* remove redirect

* remove some trigger

* add task matrix

* add precision list

* test llama-7b-chat

* use /mnt/disk1 to store model and datasets

* remove installation test

* correct downloading path

* fix HF vars

* add bigdl-llm env vars

* rename file

* fix hf_home

* fix script path

* rename as harness evalution

* rerun
 2023-11-08 10:22:27 +08:00
Yishuo Wang
bfd9f88f0d [LLM] Use fp32 as dtype when batch_size <=8 and qtype is q4_0/q8_0/fp8 (#9365) 2023-11-08 09:54:53 +08:00
WeiguangHan
84ab614aab LLM: add more models and skip runtime error (#9349) 
* add more models and skip runtime error

* upgrade transformers

* temporarily removed Mistral-7B-v0.1

* temporarily disable the upload of arc perf result
 2023-11-08 09:45:53 +08:00
Heyang Sun
fae6db3ddc [LLM] refactor cpu low-bit forward logic (#9366) 
* [LLM] refactor cpu low-bit forward logic

* fix style

* Update low_bit_linear.py

* Update low_bit_linear.py

* refine
 2023-11-07 15:09:16 +08:00
Heyang Sun
af94058203 [LLM] Support CPU deepspeed distributed inference (#9259) 
* [LLM] Support CPU Deepspeed distributed inference

* Update run_deepspeed.py

* Rename

* fix style

* add new codes

* refine

* remove annotated codes

* refine

* Update README.md

* refine doc and example code
 2023-11-06 17:56:42 +08:00
Jin Qiao
f9bf5382ff Fix: add aquila2 in README (#9362) 2023-11-06 16:37:57 +08:00
Jin Qiao
e6b6afa316 LLM: add aquila2 model example (#9356) 2023-11-06 15:47:39 +08:00
Xin Qiu
1420e45cc0 Chatglm2 rope optimization on xpu (#9350) 2023-11-06 13:56:34 +08:00
Yining Wang
9377b9c5d7 add CodeShell CPU example (#9345) 
* add CodeShell CPU example

* fix some problems
 2023-11-03 13:15:54 +08:00
ZehuaCao
ef83c3302e Use to test llm-performance on spr-perf (#9316) 
* Update llm_performance_tests.yml

* Update llm_performance_tests.yml

* Update action.yml

* Create cpu-perf-test.yaml

* Update action.yml

* Update action.yml

* Update llm_performance_tests.yml

* Update llm_performance_tests.yml

* Update llm_performance_tests.yml

* Update llm_performance_tests.yml

* Update llm_performance_tests.yml

* Update llm_performance_tests.yml

* Update llm_performance_tests.yml

* Update llm_performance_tests.yml

* Update llm_performance_tests.yml

* Update llm_performance_tests.yml

* Update llm_performance_tests.yml
 2023-11-03 11:17:16 +08:00
Yuwen Hu
a0150bb205 [LLM] Move embedding layer to CPU for iGPU inference (#9343) 
* Move embedding layer to CPU for iGPU llm inference

* Empty cache after to cpu

* Remove empty cache as it seems to have some negative effect to first token
 2023-11-03 11:13:45 +08:00
Cheen Hau, 俊豪
8f23fb04dc Add inference test for Whisper model on Arc (#9330) 
* Add inference test for Whisper model

* Remove unnecessary inference time measurement
 2023-11-03 10:15:52 +08:00
Zheng, Yi
63411dff75 Add cpu examples of WizardCoder (#9344) 
* Add wizardcoder example

* Minor fixes
 2023-11-02 20:22:43 +08:00
dingbaorong
2e3bfbfe1f Add internlm_xcomposer cpu examples (#9337) 
* add internlm-xcomposer cpu examples

* use chat

* some fixes

* add license

* address shengsheng's comments

* use demo.jpg
 2023-11-02 15:50:02 +08:00
Jin Qiao
97a38958bd LLM: add CodeLlama CPU and GPU examples (#9338) 
* LLM: add codellama CPU pytorch examples

* LLM: add codellama CPU transformers examples

* LLM: add codellama GPU transformers examples

* LLM: add codellama GPU pytorch examples

* LLM: add codellama in readme

* LLM: add LLaVA link
 2023-11-02 15:34:25 +08:00
Chen, Zhentao
d4dffbdb62 Merge harness (#9319) 
* add harness patch and llb script

* add readme

* add license

* use patch instead

* update readme

* rename tests to evaluation

* fix typo

* remove nano dependency

* add original harness link

* rename title of usage

* rename BigDLGPULM as BigDLLM

* empty commit to rerun job
 2023-11-02 15:14:19 +08:00
Zheng, Yi
63b2556ce2 Add cpu examples of skywork (#9340) 2023-11-02 15:10:45 +08:00
dingbaorong
f855a864ef add llava gpu example (#9324) 
* add llava gpu example

* use 7b model

* fix typo

* add in README
 2023-11-02 14:48:29 +08:00
Ziteng Zhang
dd3cf2f153 LLM: Add python 3.10 & 3.11 UT 
LLM: Add python 3.10 & 3.11 UT
 2023-11-02 14:09:29 +08:00
Wang, Jian4
149146004f LLM: Add qlora finetunning CPU example (#9275) 
* add qlora finetunning example

* update readme

* update example

* remove merge.py and update readme
 2023-11-02 09:45:42 +08:00
WeiguangHan
9722e811be LLM: add more models to the arc perf test (#9297) 
* LLM: add more models to the arc perf test

* remove some old models

* install some dependencies
 2023-11-01 16:56:32 +08:00
Jin Qiao
6a128aee32 LLM: add ui for portable-zip (#9262) 2023-11-01 15:36:59 +08:00
Jasonzzt
cb7ef38e86 rerun 2023-11-01 15:30:34 +08:00
Jasonzzt
ba148ff3ff test py311 2023-11-01 14:08:49 +08:00
Yishuo Wang
726203d778 [LLM] Replace Embedding layer to fix it on CPU (#9254) 2023-11-01 13:58:10 +08:00
Jasonzzt
7c7a7f2ec1 spr & arc ut with python3,9&3.10&3.11 2023-11-01 13:17:13 +08:00
Yang Wang
e1bc18f8eb fix import ipex problem (#9323) 
* fix import ipex problem

* fix style
 2023-10-31 20:31:34 -07:00
Cengguang Zhang
9f3d4676c6 LLM: Add qwen-vl gpu example (#9290) 
* create qwen-vl gpu example.

* add readme.

* fix.

* change input figure and update outputs.

* add qwen-vl pytorch model gpu example.

* fix.

* add readme.
 2023-11-01 11:01:39 +08:00
Ruonan Wang
7e73c354a6 LLM: decoupling bigdl-llm and bigdl-nano (#9306) 2023-11-01 11:00:54 +08:00
Yina Chen
2262ae4d13 Support MoFQ4 on arc (#9301) 
* init

* update

* fix style

* fix style

* fix style

* meet comments
 2023-11-01 10:59:46 +08:00
binbin Deng
8ef8e25178 LLM: improve response speed in multi-turn chat (#9299) 
* update

* fix stop word and add chatglm2 support

* remove system prompt
 2023-11-01 10:30:44 +08:00
Cengguang Zhang
d4ab5904ef LLM: Add python 3.10 llm UT (#9302) 
* add py310 test for llm-unit-test.

* add py310 llm-unit-tests

* add llm-cpp-build-py310

* test

* test

* test.

* test

* test

* fix deactivate.

* fix

* fix.

* fix

* test

* test

* test

* add build chatglm for win.

* test.

* fix
 2023-11-01 10:15:32 +08:00
WeiguangHan
03aa368776 LLM: add the comparison between latest arc perf test and last one (#9296) 
* add the comparison between latest test and last one to html

* resolve some comments

* modify some code logics
 2023-11-01 09:53:02 +08:00
Jin Qiao
96f8158fe2 LLM: adjust dolly v2 GPU example README (#9318) 2023-11-01 09:50:22 +08:00
Jin Qiao
c44c6dc43a LLM: add chatglm3 examples (#9305) 2023-11-01 09:50:05 +08:00
Xin Qiu
06447a3ef6 add malloc and intel openmp to llm deps (#9322) 2023-11-01 09:47:45 +08:00
Cheen Hau, 俊豪
d638b93dfe Add test script and workflow for qlora fine-tuning (#9295) 
* Add test script and workflow for qlora fine-tuning

* Test fix export model

* Download dataset

* Fix export model issue

* Reduce number of training steps

* Rename script

* Correction
 2023-11-01 09:39:53 +08:00
Ruonan Wang
d383ee8efb LLM: update QLoRA example about accelerate version(#9314) 2023-10-31 13:54:38 +08:00
Cheen Hau, 俊豪
cee9eaf542 [LLM] Fix llm arc ut oom (#9300) 
* Move model to cpu after testing so that gpu memory is deallocated

* Add code comment

---------

Co-authored-by: sgwhat <ge.song@intel.com>
 2023-10-30 14:38:34 +08:00
dingbaorong
ee5becdd61 use coco image in Qwen-VL (#9298) 
* use coco image

* add output

* address yuwen's comments
 2023-10-30 14:32:35 +08:00
Yang Wang
163d033616 Support qlora in CPU (#9233) 
* support qlora in CPU

* revert example

* fix style
 2023-10-27 14:01:15 -07:00
Yang Wang
8838707009 Add deepspeed autotp example readme (#9289) 
* Add deepspeed autotp example readme

* change word
 2023-10-27 13:04:38 -07:00
dingbaorong
f053688cad add cpu example of LLaVA (#9269) 
* add LLaVA cpu example

* Small text updates

* update link

---------

Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
 2023-10-27 18:59:20 +08:00
Zheng, Yi
7f2ad182fd Minor Fixes of README (#9294) 2023-10-27 18:25:46 +08:00
Zheng, Yi
1bff54a378 Display demo.jpg n the README.md of HuggingFace Transformers Agent (#9293) 
* Display demo.jpg

* remove demo.jpg
 2023-10-27 18:00:03 +08:00
Zheng, Yi
a4a1dec064 Add a cpu example of HuggingFace Transformers Agent (use vicuna-7b-v1.5) (#9284) 
* Add examples of HF Agent

* Modify folder structure and add link of demo.jpg

* Fixes of readme

* Merge applications and Applications
 2023-10-27 17:14:12 +08:00
Guoqiong Song
aa319de5e8 Add streaming-llm using llama2 on CPU (#9265) 
Enable streaming-llm to let model take infinite inputs, tested on desktop and SPR10
 2023-10-27 01:30:39 -07:00
Cheen Hau, 俊豪
6c9ae420a5 Add regression test for optimize_model on gpu (#9268) 
* Add MPT model to transformer API test

* Add regression test for optimize_model on gpu.

---------

Co-authored-by: sgwhat <ge.song@intel.com>
 2023-10-27 09:23:19 +08:00
Cengguang Zhang
44b5fcc190 LLM: fix pretraining_tp argument issue. (#9281) 2023-10-26 18:43:58 +08:00
WeiguangHan
6b2a32eba2 LLM: add missing function for PyTorch InternLM model (#9285) 2023-10-26 18:05:23 +08:00
Yina Chen
f879c48f98 fp8 convert use ggml code (#9277) 2023-10-26 17:03:29 +08:00
Yina Chen
e2264e8845 Support arc fp4 (#9266) 
* support arc fp4

* fix style

* fix style
 2023-10-25 15:42:48 +08:00
Cheen Hau, 俊豪
ab40607b87 Enable unit test workflow on Arc (#9213) 
* Add gpu workflow and a transformers API inference test

* Set device-specific env variables in script instead of workflow

* Fix status message

---------

Co-authored-by: sgwhat <ge.song@intel.com>
 2023-10-25 15:17:18 +08:00
SONG Ge
160a1e5ee7 [WIP] Add UT for Mistral Optimized Model (#9248) 
* add ut for mistral model

* update

* fix model path

* upgrade transformers version for mistral model

* refactor correctness ut for mustral model

* refactor mistral correctness ut

* revert test_optimize_model back

* remove mistral from test_optimize_model

* add to revert transformers version back to 4.31.0
 2023-10-25 15:14:17 +08:00
Yang Wang
067c7e8098 Support deepspeed AutoTP (#9230) 
* Support deepspeed

* add test script

* refactor convert

* refine example

* refine

* refine example

* fix style

* refine example and adapte latest ipex

* fix style
 2023-10-24 23:46:28 -07:00
Yining Wang
a6a8afc47e Add qwen vl CPU example (#9221) 
* eee

* add examples on CPU and GPU

* fix

* fix

* optimize model examples

* add Qwen-VL-Chat CPU example

* Add Qwen-VL CPU example

* fix optimize problem

* fix error

* Have updated, benchmark fix removed from this PR

* add generate API example

* Change formats in qwen-vl example

* Add CPU transformer int4 example for qwen-vl

* fix repo-id problem and add Readme

* change picture url

* Remove unnecessary file

---------

Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
 2023-10-25 13:22:12 +08:00
binbin Deng
f597a9d4f5 LLM: update perf test configuration (#9264) 2023-10-25 12:35:48 +08:00
binbin Deng
770ac70b00 LLM: add low_bit option in benchmark scripts (#9257) 2023-10-25 10:27:48 +08:00
WeiguangHan
ec9195da42 LLM: using html to visualize the perf result for Arc (#9228) 
* LLM: using html to visualize the perf result for Arc

* deploy the html file

* add python license

* reslove some comments
 2023-10-24 18:05:25 +08:00
Jin Qiao
90162264a3 LLM: replace torch.float32 with auto type (#9261) 2023-10-24 17:12:13 +08:00
SONG Ge
bd5215d75b [LLM] Reimplement chatglm fuse rms optimization (#9260) 
* re-implement chatglm rope rms

* update
 2023-10-24 16:35:12 +08:00
dingbaorong
5a2ce421af add cpu and gpu examples of flan-t5 (#9171) 
* add cpu and gpu examples of flan-t5

* address yuwen's comments
* Add explanation  why we add modules to not convert
* Refine prompt and add a translation example
* Add a empty line at the end of files

* add examples of flan-t5 using optimize_mdoel api

* address bin's comments

* address binbin's comments

* add flan-t5 in readme
 2023-10-24 15:24:01 +08:00
Yining Wang
4a19f50d16 phi-1_5 CPU and GPU examples (#9173) 
* eee

* add examples on CPU and GPU

* fix

* fix

* optimize model examples

* have updated

* Warmup and configs added

* Update two tables
 2023-10-24 15:08:04 +08:00
SONG Ge
bfc1e2d733 add fused rms optimization for chatglm model (#9256) 2023-10-24 14:40:58 +08:00
Ruonan Wang
b15656229e LLM: fix benchmark issue (#9255) 2023-10-24 14:15:05 +08:00
Guancheng Fu
f37547249d Refine README/CICD (#9253) 2023-10-24 12:56:03 +08:00
binbin Deng
db37edae8a LLM: update langchain api document page (#9222) 2023-10-24 10:13:41 +08:00
Xin Qiu
0c5055d38c add position_ids and fuse embedding for falcon (#9242) 
* add position_ids for falcon

* add cpu

* add cpu

* add license
 2023-10-24 09:58:20 +08:00
Wang, Jian4
c14a61681b Add load low-bit in model-serving for reduce EPC (#9239) 
* init load low-bit

* fix

* fix
 2023-10-23 11:28:20 +08:00
Yina Chen
0383306688 Add arc fp8 support (#9232) 
* add fp8 support

* add log

* fix style
 2023-10-20 17:15:07 +08:00
Yang Wang
118249b011 support transformers 4.34+ for llama (#9229) 2023-10-19 22:36:30 -07:00
Chen, Zhentao
5850241423 correct Readme GPU example and API docstring (#9225) 
* update readme to correct GPU usage

* update from_pretrained supported low bit options

* fix stype check
 2023-10-19 16:08:47 +08:00
WeiguangHan
f87f67ee1c LLM: arc perf test for some popular models (#9188) 2023-10-19 15:56:15 +08:00
Yang Wang
b0ddde0410 Fix removing convert dtype bug (#9216) 
* Fix removing convert dtype bug

* fix style
 2023-10-18 11:24:22 -07:00
Ruonan Wang
942d6418e7 LLM: fix chatglm kv cache (#9215) 2023-10-18 19:09:53 +08:00
SONG Ge
0765f94770 [LLM] Optimize kv_cache for mistral model family (#9189) 
* add kv_cache optimization for mistral model

* kv_cache optimize for mistral

* update stylr

* update
 2023-10-18 15:13:37 +08:00
Ruonan Wang
3555ebc148 LLM: fix wrong length in gptj kv_cache optimization (#9210) 
* fix wrong length in gptj kv cache

* update
 2023-10-18 14:59:02 +08:00
Shengsheng Huang
6dad8d16df optimize NormHead for Baichuan2 (#9205) 
* optimize NormHead for Baichuan2

* fix ut and change name

* rename functions
 2023-10-18 14:05:07 +08:00
Jin Qiao
a3b664ed03 LLM: add GPU More-Data-Types and Save/Load example (#9199) 2023-10-18 13:13:45 +08:00
WeiguangHan
b9194c5786 LLM: skip some model tests using certain api (#9163) 
* LLM: Skip some model tests using certain api

* initialize variable named result
 2023-10-18 09:39:27 +08:00
Ruonan Wang
09815f7064 LLM: fix RMSNorm optimization of Baichuan2-13B/Baichuan-13B (#9204) 
* fix rmsnorm of baichuan2-13B

* update baichuan1-13B too

* fix style
 2023-10-17 18:40:34 +08:00
Jin Qiao
d7ce78edf0 LLM: fix portable zip README image link (#9201) 
* LLM: fix portable zip readme img link

* LLM: make README first image center align
 2023-10-17 16:38:22 +08:00
Cheen Hau, 俊豪
66c2e45634 Add unit tests for optimized model correctness (#9151) 
* Add test to check correctness of optimized model

* Refactor optimized model test

* Use models in llm-unit-test

* Use AutoTokenizer for bloom

* Print out each passed test

* Remove unused tokenizer from import
 2023-10-17 14:46:41 +08:00
Jin Qiao
d946bd7c55 LLM: add CPU More-Data-Types and Save-Load examples (#9179) 2023-10-17 14:38:52 +08:00
Ruonan Wang
c0497ab41b LLM: support kv_cache optimization for Qwen-VL-Chat (#9193) 
* dupport qwen_vl_chat

* fix style
 2023-10-17 13:33:56 +08:00
binbin Deng
1cd9ab15b8 LLM: fix ChatGLMConfig check (#9191) 2023-10-17 11:52:56 +08:00
Yang Wang
7160afd4d1 Support XPU DDP training and autocast for LowBitMatmul (#9167) 
* support autocast in low bit matmul

* Support XPU DDP training

* fix  amp
 2023-10-16 20:47:19 -07:00
Ruonan Wang
77afb8796b LLM: fix convert of chatglm (#9190) 2023-10-17 10:48:13 +08:00
dingbaorong
af3b575c7e expose modules_to_not_convert in optimize_model (#9180) 
* expose modules_to_not_convert in optimize_model

* some fixes
 2023-10-17 09:50:26 +08:00
Cengguang Zhang
5ca8a851e9 LLM: add fuse optimization for Mistral. (#9184) 
* add fuse optimization for mistral.

* fix.

* fix

* fix style.

* fix.

* fix error.

* fix style.

* fix style.
 2023-10-16 16:50:31 +08:00
Jiao Wang
49e1381c7f update rope (#9155) 2023-10-15 21:51:45 -07:00
Jason Dai
b192a8032c Update llm-readme (#9176) 2023-10-16 10:54:52 +08:00
binbin Deng
a164c24746 LLM: add kv_cache optimization for chatglm2-6b-32k (#9165) 2023-10-16 10:43:15 +08:00
Yang Wang
7a2de00b48 Fixes for xpu Bf16 training (#9156) 
* Support bf16 training

* Use a stable transformer version

* remove env

* fix style
 2023-10-14 21:28:59 -07:00
Cengguang Zhang
51a133de56 LLM: add fuse rope and norm optimization for Baichuan. (#9166) 
* add fuse rope optimization.

* add rms norm optimization.
 2023-10-13 17:36:52 +08:00
Jin Qiao
db7f938fdc LLM: add replit and starcoder to gpu pytorch model example (#9154) 2023-10-13 15:44:17 +08:00
Jin Qiao
797b156a0d LLM: add dolly-v1 and dolly-v2 to gpu pytorch model example (#9153) 2023-10-13 15:43:35 +08:00
Yishuo Wang
259cbb4126 [LLM] add initial bigdl-llm-init (#9150) 2023-10-13 15:31:45 +08:00
Cengguang Zhang
433f408081 LLM: Add fuse rope and norm optimization for Aquila. (#9161) 
* add fuse norm optimization.

* add fuse rope optimization
 2023-10-13 14:18:37 +08:00
SONG Ge
e7aa67e141 [LLM] Add rope optimization for internlm (#9159) 
* add rope and norm optimization for internlm and gptneox

* revert gptneox back and split with pr#9155 #

* add norm_forward

* style fix

* update

* update
 2023-10-13 14:18:28 +08:00
Jin Qiao
f754ab3e60 LLM: add baichuan and baichuan2 to gpu pytorch model example (#9152) 2023-10-13 13:44:31 +08:00
Ruonan Wang
b8aee7bb1b LLM: Fix Qwen kv_cache optimization (#9148) 
* first commit

* ut pass

* accelerate rotate half by using common util function

* fix style
 2023-10-12 15:49:42 +08:00
binbin Deng
69942d3826 LLM: fix model check before attention optimization (#9149) 2023-10-12 15:21:51 +08:00
JIN Qiao
1a1ddc4144 LLM: Add Replit CPU and GPU example (#9028) 2023-10-12 13:42:14 +08:00
JIN Qiao
d74834ff4c LLM: add gpu pytorch-models example llama2 and chatglm2 (#9142) 2023-10-12 13:41:48 +08:00
Ruonan Wang
4f34557224 LLM: support num_beams in all-in-one benchmark (#9141) 
* support num_beams

* fix
 2023-10-12 13:35:12 +08:00
Ruonan Wang
62ac7ae444 LLM: fix inaccurate input / output tokens of current all-in-one benchmark (#9137) 
* first fix

* fix all apis

* fix
 2023-10-11 17:13:34 +08:00
binbin Deng
eb3fb18eb4 LLM: improve PyTorch API doc (#9128) 2023-10-11 15:03:39 +08:00
binbin Deng
995b0f119f LLM: update some gpu examples (#9136) 2023-10-11 14:23:56 +08:00
Ruonan Wang
1c8d5da362 LLM: fix llama tokenizer for all-in-one benchmark (#9129) 
* fix tokenizer for gpu benchmark

* fix ipex fp16

* meet code review

* fix
 2023-10-11 13:39:39 +08:00
binbin Deng
2ad67a18b1 LLM: add mistral examples (#9121) 2023-10-11 13:38:15 +08:00
Ruonan Wang
1363e666fc LLM: update benchmark_util.py for beam search (#9126) 
* update reorder_cache

* fix
 2023-10-11 09:41:53 +08:00
Guoqiong Song
e8c5645067 add LLM example of aquila on GPU (#9056) 
* aquila, dolly-v1, dolly-v2, vacuna
 2023-10-10 17:01:35 -07:00
Ruonan Wang
388f688ef3 LLM: update setup.py to add bigdl-core-xe package (#9122) 2023-10-10 15:02:48 +08:00
Zhao Changmin
1709beba5b LLM: Explicitly close pickle file pointer before removing temporary directory (#9120) 
* fp close
 2023-10-10 14:57:23 +08:00
Yuwen Hu
0e09dd926b [LLM] Fix example test (#9118) 
* Update llm example test link due to example layout change

* Add better change detect
 2023-10-10 13:24:18 +08:00
Ruonan Wang
ad7d9231f5 LLM: add benchmark script for Max gpu and ipex fp16 gpu (#9112) 
* add pvc bash

* meet code review

* rename to run-max-gpu.sh
 2023-10-10 10:18:41 +08:00
binbin Deng
e4d1457a70 LLM: improve transformers style API doc (#9113) 2023-10-10 09:31:00 +08:00
Yuwen Hu
65212451cc [LLM] Small update to performance tests (#9106) 
* small updates to llm performance tests regarding model handling

* Small fix
 2023-10-09 16:55:25 +08:00
Zhao Changmin
edccfb2ed3 LLM: Check model device type (#9092) 
* check model device
 2023-10-09 15:49:15 +08:00
binbin Deng
5e9962b60e LLM: update example layout (#9046) 2023-10-09 15:36:39 +08:00
Yina Chen
4c4f8d1663 [LLM]Fix Arc falcon abnormal output issue (#9096) 
* update

* update

* fix error & style

* fix style

* update train

* to input_seq_size
 2023-10-09 15:09:37 +08:00
Zhao Changmin
548e4dd5fe LLM: Adapt transformers models for optimize model SL (#9022) 
* LLM: Adapt transformers model for SL
 2023-10-09 11:13:44 +08:00
Ruonan Wang
f64257a093 LLM: basic api support for esimd fp16 (#9067) 
* basic api support for fp16

* fix style

* fix

* fix error and style

* fix style

* meet code review

* update based on comments
 2023-10-09 11:05:17 +08:00
JIN Qiao
65373d2a8b LLM: adjust portable zip content (#9054) 
* LLM: adjust portable zip content

* LLM: adjust portable zip README
 2023-10-09 10:51:19 +08:00
Xin Qiu
b3e94a32d4 change log4error import (#9098) 2023-10-08 09:23:28 +08:00
Kai Huang
78ea7ddb1c Combine apply_rotary_pos_emb for gpt-neox (#9074) 2023-10-07 16:27:46 +08:00
Yang Wang
36dd4afd61 Fix llama when rope scaling is not None (#9086) 
* Fix llama when rope scaling is not None

* fix style

* fix style
 2023-10-06 13:27:37 -07:00
Yang Wang
fcb1c618a0 using bigdl-llm fused rope for llama (#9066) 
* optimize llama xpu rope

* fix bug

* fix style

* refine append cache

* remove check

* do not cache cos sin

* remove unnecessary changes

* clean up

* fix style

* check for training
 2023-10-06 09:57:29 -07:00
Jiao Wang
aefa5a5bfe Qwen kv cache (#9079) 
* qwen and aquila

* update

* update

* style
 2023-10-05 11:59:17 -07:00
Jiao Wang
d5ca1f32b6 Aquila KV cache optimization (#9080) 
* update

* update

* style
 2023-10-05 11:10:57 -07:00
Yang Wang
88565c76f6 add export merged model example (#9018) 
* add export merged model example

* add sources

* add script

* fix style
 2023-10-04 21:18:52 -07:00
Yang Wang
0cd8f1c79c Use ipex fused rms norm for llama (#9081) 
* also apply rmsnorm

* fix cpu
 2023-10-04 21:04:55 -07:00
Cengguang Zhang
fb883100e7 LLM: support chatglm-18b convert attention forward in benchmark scripts. (#9072) 
* add chatglm-18b convert.

* fix if statement.

* fix
 2023-09-28 14:04:52 +08:00
Yishuo Wang
6de2189e90 [LLM] fix chatglm main choice (#9073) 2023-09-28 11:23:37 +08:00
Cengguang Zhang
ad62c58b33 LLM: Enable jemalloc in benchmark scripts. (#9058) 
* enable jemalloc.

* fix readme.
 2023-09-26 15:37:49 +08:00
Cengguang Zhang
b4a1266ef0 [WIP] LLM: add kv cache support for internlm. (#9036) 
* LLM: add kv cache support for internlm

* add internlm apply_rotary_pos_emb

* fix.

* fix style.
 2023-09-25 14:16:59 +08:00
Ruonan Wang
975da86e00 LLM: fix gptneox kv cache (#9044) 2023-09-25 13:03:57 +08:00
Cengguang Zhang
26213a5829 LLM: Change benchmark bf16 load format. (#9035) 
* LLM: Change benchmark bf16 load format.

* comment on bf16 chatglm.

* fix.
 2023-09-22 17:38:38 +08:00
JinBridge
023555fb1f LLM: Add one-click installer for Windows (#8999) 
* LLM: init one-click installer for windows

* LLM: fix typo in one-click installer readme

* LLM: one-click installer try except logic

* LLM: one-click installer add dependency

* LLM: one-click installer adjust README.md

* LLM: one-click installer split README and add zip compress in setup.bat

* LLM: one-click installer verified internlm and llama2 and replace gif

* LLM: remove one-click installer images

* LLM: finetune the one-click installer README.md

* LLM: fix typo in one-click installer README.md

* LLM: rename one-click installer to protable executable

* LLM: rename other places to protable executable

* LLM: rename the zip filename to executable

* LLM: update .gitignore

* LLM: add colorama to setup.bat
 2023-09-22 14:46:30 +08:00
Jiao Wang
028a6d9383 MPT model optimize for long sequence (#9020) 
* mpt_long_seq

* update

* update

* update

* style

* style2

* update
 2023-09-21 21:27:23 -07:00
Ruonan Wang
b943d73844 LLM: refactor kv cache (#9030) 
* refactor utils

* meet code review; update all models

* small fix
 2023-09-21 21:28:03 +08:00
Cengguang Zhang
868511cf02 LLM: fix kv cache issue of bloom and falcon. (#9029) 2023-09-21 18:12:20 +08:00
Ruonan Wang
bf51ec40b2 LLM: Fix empty cache (#9024) 
* fix

* fix

* update example
 2023-09-21 17:16:07 +08:00
Yina Chen
714884414e fix error (#9025) 2023-09-21 16:42:11 +08:00
binbin Deng
edb225530b add bark (#9016) 2023-09-21 12:24:58 +08:00
SONG Ge
fa47967583 [LLM] Optimize kv_cache for gptj model family (#9010) 
* optimize gptj model family attention

* add license and comment for dolly-model

* remove xpu mentioned

* remove useless info

* code sytle

* style fix

* code style in gptj fix

* remove gptj arch

* move apply_rotary_pos_emb into utils

* kv_seq_length update

* use hidden_states instead of query layer to reach batch size
 2023-09-21 10:42:08 +08:00
Cengguang Zhang
b3cad7de57 LLM: add bloom kv cache support (#9012) 
* LLM: add bloom kv cache support

* fix style.
 2023-09-20 21:10:53 +08:00
Kai Huang
156af15d1e Add NF3 (#9008) 
* add nf3

* grammar
 2023-09-20 20:03:07 +08:00
Kai Huang
6981745fe4 Optimize kv_cache for gpt-neox model family (#9015) 
* override gptneox

* style

* move to utils

* revert
 2023-09-20 19:59:19 +08:00
JinBridge
48b503c630 LLM: add example of aquila (#9006) 
* LLM: add example of aquila

* LLM: replace AquilaChat with Aquila

* LLM: shorten prompt of aquila example
 2023-09-20 15:52:56 +08:00
Cengguang Zhang
735a17f7b4 LLM: add kv cache to falcon family. (#8995) 
* add kv cache to falcon family.

* fix: import error.

* refactor

* update comments.

* add two version falcon attention forward.

* fix

* fix.

* fix.

* fix.

* fix style.

* fix style.
 2023-09-20 15:36:30 +08:00
Ruonan Wang
94a7f8917b LLM: fix optimized kv cache for baichuan-13b (#9009) 
* fix baichuan 13b

* fix style

* fix

* fix style
 2023-09-20 15:30:14 +08:00
Yang Wang
c88f6ec457 Experiment XPU QLora Finetuning (#8937) 
* Support xpu finetuning

* support xpu finetuning

* fix style

* fix style

* fix style

* refine example

* add readme

* refine readme

* refine api

* fix fp16

* fix example

* refactor

* fix style

* fix compute type

* add qlora

* refine training args

* fix example

* fix style

* fast path forinference

* address comments

* refine readme

* revert lint
 2023-09-19 10:15:44 -07:00
Jason Dai
51518e029d Update llm readme (#9005) 2023-09-19 20:01:33 +08:00
Ruonan Wang
249386261c LLM: add Baichuan2 cpu example (#9002) 
* add baichuan2 cpu examples

* add link

* update prompt
 2023-09-19 18:08:30 +08:00
Ruonan Wang
004c45c2be LLM: Support optimized kv_cache for baichuan family (#8997) 
* add initial support for baichuan attantion

* support baichuan1

* update based on comment

* update based on comment

* support baichuan2

* update link, change how to jusge baichuan2

* fix style

* add model parameter for pob emb

* update based on comment
 2023-09-19 15:38:54 +08:00
Xin Qiu
37bb0cbf8f Speed up gpt-j in gpubenchmark (#9000) 
* Speedup gpt-j in gpubenchmark

* meet code review
 2023-09-19 14:22:28 +08:00
Zhao Changmin
2a05581da7 LLM: Apply low_cpu_mem_usage algorithm on optimize_model API (#8987) 
* low_cpu_mem_usage
 2023-09-18 21:41:42 +08:00
Cengguang Zhang
8299b68fea update readme. (#8996) 2023-09-18 17:06:15 +08:00
binbin Deng
c1d25a51a8 LLM: add optimize_model example for bert (#8975) 2023-09-18 16:18:35 +08:00
Cengguang Zhang
74338fd291 LLM: add auto torch dtype in benchmark. (#8981) 2023-09-18 15:48:25 +08:00
Ruonan Wang
cabe7c0358 LLM: add baichuan2 example for arc (#8994) 
* add baichuan2 examples

* add link

* small fix
 2023-09-18 14:32:27 +08:00
binbin Deng
0a552d5bdc LLM: fix installation on windows (#8989) 2023-09-18 11:14:54 +08:00
Ruonan Wang
32716106e0 update use_cahce=True (#8986) 2023-09-18 07:59:33 +08:00
Xin Qiu
64ee1d7689 update run_transformer_int4_gpu (#8983) 
* xpuperf

* update run.py

* clean upo

* uodate

* update

* meet code review
 2023-09-15 15:10:04 +08:00
Zhao Changmin
16b9412e80 tie_word_embeddings (#8977) 
tie_word_embeddings
 2023-09-15 10:17:09 +08:00
JinBridge
c12b8f24b6 LLM: add use_cache=True for all gpu examples (#8971) 2023-09-15 09:54:38 +08:00
Guancheng Fu
d1b62ef2f2 [bigdl-llm] Remove serving-dep from all_requires (#8980) 
* Remove serving-dep from all_requires

* pin fastchat version
 2023-09-14 16:59:24 +08:00
Yishuo Wang
bcf456070c fix bloom-176b int overflow (#8973) 2023-09-14 14:37:57 +08:00
Ruonan Wang
dd57623650 LLM: reduce GPU memory for optimize_model=True (#8965) 
* reduce gpu memory for llama & chatglm

* change to device type
 2023-09-13 17:27:09 +08:00
binbin Deng
be29c75c18 LLM: refactor gpu examples (#8963) 
* restructure

* change to hf-transformers-models/
 2023-09-13 14:47:47 +08:00
Cengguang Zhang
cca84b0a64 LLM: update llm benchmark scripts. (#8943) 
* update llm benchmark scripts.

* change tranformer_bf16 to pytorch_autocast_bf16.

* add autocast in transformer int4.

* revert autocast.

* add "pytorch_autocast_bf16" to doc

* fix comments.
 2023-09-13 12:23:28 +08:00
SONG Ge
7132ef6081 [LLM Doc] Add optimize_model doc in transformers api (#8957) 
* add optimize in from_pretrained

* add api doc for load_low_bit

* update api docs following comments

* update api docs

* update

* reord comments
 2023-09-13 10:42:33 +08:00
Zhao Changmin
c32c260ce2 LLM: Add save/load API in optimize_model to support general pytorch model (#8956) 
* support hf format SL
 2023-09-13 10:22:00 +08:00
Ruonan Wang
4de73f592e LLM: add gpu example of chinese-llama-2-7b (#8960) 
* add gpu example of chinese -llama2

* update model name and link

* update name
 2023-09-13 10:16:51 +08:00
Guancheng Fu
0bf5857908 [LLM] Integrate FastChat as a serving framework for BigDL-LLM (#8821) 
* Finish changing

* format

* add licence

* Add licence

* fix

* fix

* Add xpu support for fschat

* Fix patch

* Also install webui dependencies

* change setup.py dependency installs

* fiox

* format

* final test
 2023-09-13 09:28:05 +08:00
Yuwen Hu
cb534ed5c4 [LLM] Add Arc demo gif to readme and readthedocs (#8958) 
* Add arc demo in main readme

* Small style fix

* Realize using table

* Update based on comments

* Small update

* Try to solve with height problem

* Small fix

* Update demo for inner llm readme

* Update demo video for readthedocs

* Small fix

* Update based on comments
 2023-09-13 09:23:52 +08:00
Zhao Changmin
dcaa4dc130 LLM: Support GQA on llama kvcache (#8938) 
* support GQA
 2023-09-12 12:18:40 +08:00
binbin Deng
2d81521019 LLM: add optimize_model examples for llama2 and chatglm (#8894) 
* add llama2 and chatglm optimize_model examples

* update default usage

* update command and some descriptions

* move folder and remove general_int4 descriptions

* change folder name
 2023-09-12 10:36:29 +08:00
Zhao Changmin
f00c442d40 fix accelerate (#8946) 
Co-authored-by: leonardozcm <leonardozcm@gmail.com>
 2023-09-12 09:27:58 +08:00
Yang Wang
16761c58be Make llama attention stateless (#8928) 
* Make llama attention stateless

* fix style

* fix chatglm

* fix chatglm xpu
 2023-09-11 18:21:50 -07:00
Zhao Changmin
e62eda74b8 refine (#8912) 
Co-authored-by: leonardozcm <leonardozcm@gmail.com>
 2023-09-11 16:40:33 +08:00
Yina Chen
df165ad165 init (#8933) 2023-09-11 14:30:55 +08:00
Ruonan Wang
b3f5dd5b5d LLM: update q8 convert xpu&cpu (#8930) 2023-09-08 16:01:17 +08:00
Yina Chen
33d75adadf [LLM]Support q5_0 on arc (#8926) 
* support q5_0

* delete

* fix style
 2023-09-08 15:52:36 +08:00
Yuwen Hu
ca35c93825 [LLM] Fix langchain UT (#8929) 
* Change dependency version for langchain uts

* Downgrade pandas version instead; and update example readme accordingly
 2023-09-08 13:51:04 +08:00