ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
1729 commits 1 branch 0 tags 37 MiB
Commit graph

515 commits

Author SHA1 Message Date
Wang, Jian4
ac7fbe77e2 Update qlora readme (#9416) 2023-11-12 19:29:29 +08:00
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