ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
2218 commits 1 branch 0 tags 37 MiB
Commit graph

315 commits

Author SHA1 Message Date
Yuwen Hu
dfe28c58bb Small upload fix for igpu-perf test (#9792) 2023-12-27 15:50:58 +08:00
Shaojun Liu
6c75c689ea bigdl-llm stress test for stable version (#9781) 
* 1k-512 2k-512 baseline

* add cpu stress test

* update yaml name

* update

* update

* clean up

* test

* update

* update

* update

* test

* update
 2023-12-27 15:40:53 +08:00
dingbaorong
5cfb4c4f5b Arc stable version performance regression test (#9785) 
* add arc stable version regression test

* empty gpu mem between different models

* triger ci

* comment spr test

* triger ci

* address kai's comments and disable ci

* merge fp8 and int4

* disable ci
 2023-12-27 11:01:56 +08:00
Yuwen Hu
c38e18f2ff [LLM] Migrate iGPU perf tests to new machine (#9784) 
* Move 1024 test just after 32-32 test; and enable all model for 1024-128

* Make sure python output encoding in utf-8 so that redirect to txt can always be success

* Upload results to ftp

* Small fix
 2023-12-26 19:15:57 +08:00
Shaojun Liu
b6222404b8 bigdl-llm stable version: let the perf test fail if the difference between perf and baseline is greater than 5% (#9750) 
* test

* test

* test

* update

* revert
 2023-12-25 13:47:11 +08:00
Chen, Zhentao
4a98bfa5ae fix harness manual run env typo (#9763) 2023-12-22 18:42:35 +08:00
Yuwen Hu
02436c6cce [LLM] Enable more long context in-out pairs for iGPU perf tests (#9765) 
* Add test for 1024-128 and enable more tests for 512-64

* Fix date in results csv name to the time when the performance is triggered

* Small fix

* Small fix

* further fixes
 2023-12-22 18:18:23 +08:00
Yuwen Hu
1c8c104bb8 [LLM] Small fixes for igpu win perf tests (#9756) 2023-12-22 15:51:03 +08:00
Chen, Zhentao
86a69e289c fix harness runner label of manual trigger (#9754) 
* fix runner

* update golden
 2023-12-22 15:09:22 +08:00
WeiguangHan
2d1bf20309 LLM: small fix llm_performance_tests.html (#9753) 
* LLM: small fix llm_performance_tests.html

* reslove some comments

* revert the llm_performance_test.yaml
 2023-12-22 13:55:01 +08:00
Shaojun Liu
bb52239e0a bigdl-llm stable version release & test (#9732) 
* stable version test

* trigger spr test

* update

* trigger

* test

* test

* test

* test

* test

* refine

* release linux first
 2023-12-21 22:55:33 +08:00
WeiguangHan
34bb804189 LLM: check csv and its corresponding yaml file (#9702) 
* LLM: check csv and its corresponding yaml file

* run PR arc perf test

* modify the name of some variables

* execute the check results script in right place

* use cp to replace mv command

* resolve some comments

* resolve more comments

* revert the llm_performance_test.yaml file
 2023-12-21 09:54:33 +08:00
WeiguangHan
3aa8b66bc3 LLM: remove starcoder-15.5b model temporarily (#9720) 2023-12-19 20:14:46 +08:00
Chen, Zhentao
b3647507c0 Fix harness workflow (#9704) 
* error when larger than 0.001

* fix env setup

* fix typo

* fix typo
 2023-12-18 15:42:10 +08:00
WeiguangHan
1f0245039d LLM: check the final csv results for arc perf test (#9684) 
* LLM: check the final csv results for arc perf test

* delete useless python script

* change threshold

* revert the llm_performance_tests.yml
 2023-12-14 19:46:08 +08:00
Yuwen Hu
82ac2dbf55 [LLM] Small fixes for win igpu test for ipex 2.1 (#9686) 
* Fixes to install for igpu performance tests

* Small update for core performance tests model lists
 2023-12-14 15:39:51 +08:00
Yuwen Hu
cbdd49f229 [LLM] win igpu performance for ipex 2.1 and oneapi 2024.0 (#9679) 
* Change igpu win tests for ipex 2.1 and oneapi 2024.0

* Qwen model repo id updates; updates model list for 512-64

* Add .eval for win igpu all-in-one benchmark for best performance
 2023-12-13 18:52:29 +08:00
Yuwen Hu
017932a7fb Small fix for html generation (#9656) 2023-12-12 14:06:18 +08:00
WeiguangHan
1e25499de0 LLM: test new oneapi (#9654) 
* test new oneapi

* revert llm_performance_tests.yml
 2023-12-12 11:12:14 +08:00
Yuwen Hu
d272b6dc47 [LLM] Enable generation of html again for win igpu tests (#9652) 
* Enable generation of html again and comment out rwkv for 32-512 as it is not very stable

* Small fix
 2023-12-11 19:15:17 +08:00
Yuwen Hu
894d0aaf5e [LLM] iGPU win perf test reorg based on in-out pairs (#9645) 
* trigger pr temparorily

* Saparate benchmark run for win igpu based in in-out pairs

* Rename fix

* Test workflow

* Small fix

* Skip generation of html for now

* Change back to nightly triggered
 2023-12-08 20:46:40 +08:00
Chen, Zhentao
972cdb9992 gsm8k OOM workaround (#9597) 
* update bigdl_llm.py

* update the installation of harness

* fix partial function

* import ipex

* force seq len in decrease order

* put func outside class

* move comments

* default 'trust_remote_code' as True

* Update llm-harness-evaluation.yml
 2023-12-08 18:47:25 +08:00
WeiguangHan
1ff4bc43a6 degrade pandas version (#9643) 2023-12-08 17:44:51 +08:00
Yuwen Hu
c998f5f2ba [LLM] iGPU long context tests (#9598) 
* Temp enable PR

* Enable tests for 256-64

* Try again 128-64

* Empty cache after each iteration for igpu benchmark scripts

* Try tests for 512

* change order for 512

* Skip chatglm3 and llama2 for now

* Separate tests for 512-64

* Small fix

* Further fixes

* Change back to nightly again
 2023-12-06 10:19:20 +08:00
Chen, Zhentao
8c8a27ded7 Add harness summary job (#9457) 
* format yml

* add make_table_results

* add summary job

* add a job to print single result

* upload full directory
 2023-12-05 10:04:10 +08:00
Yuwen Hu
3f4ad97929 [LLM] Add performance tests for windows iGPU (#9584) 
* Add support for win gpu benchmark with peak gpu memory monitoring

* Add win igpu tests

* Small fix

* Forward outputs

* Small fix

* Test and small fixes

* Small fix

* Small fix and test

* Small fixes

* Add tests for 512-64 and change back to nightly tests

* Small fix
 2023-12-04 20:50:02 +08:00
Chen, Zhentao
29d5bb8df4 Harness workflow dispatch (#9591) 
* add set-matrix job

* add workflow_dispatch

* fix context

* fix manual run

* rename step

* add quotes

* add runner option

* not required labels

* add runner label to output

* use double quote
 2023-12-04 15:53:29 +08:00
Chen, Zhentao
9557aa9c21 Fix harness nightly (#9586) 
* update golden

* loose the restriction of diff

* only compare results when scheduled
 2023-12-04 11:45:00 +08:00
Chen, Zhentao
5de92090b3 try to fix deps installation of bigdl (#9578) 2023-12-01 15:25:47 +08:00
Chen, Zhentao
cb228c70ea Add harness nightly (#9552) 
* modify output_path as a directory

* schedule nightly at 21 on Friday

* add tasks and models for nightly

* add accuracy regression

* comment out if to test

* mixed fp4

* for test

* add  missing delimiter

* remove comma

* fixed golden results

* add mixed 4 golden result

* add more options

* add mistral results

* get golden result of stable lm

* move nightly scripts and results to test folder

* add license

* add fp8 stable lm golden

* run on all available devices

* trigger only when ready for review

* fix new line

* update golden

* add mistral
 2023-12-01 14:16:35 +08:00
Chen, Zhentao
4d7d5d4c59 Add 3 leaderboard tasks (#9566) 
* update leaderboard map

* download model and dataset without overwritten

* fix task drop

* run on all available devices
 2023-12-01 14:01:14 +08:00
Chen, Zhentao
c8e0c2ed48 Fixed dumped logs in harness (#9549) 
* install transformers==4.34.0

* modify output_path as a directory

* add device and task to output dir parents
 2023-11-30 12:47:56 +08:00
WeiguangHan
5098bc3544 LLM: enable previous models (#9505) 
* enable previous models

* test mistral model

* for test

* run models separately

* test all models

* for test

* revert the llm_performance_test.yaml
 2023-11-28 10:21:07 +08:00
Wang, Jian4
40ec9f7ead Add qlora cpu docker manually build (#9501) 2023-11-21 14:39:16 +08:00
WeiguangHan
c487b53f21 LLM: only run arc perf test nightly (#9448) 
* LLM: only run arc perf test nightly

* deleted unused python scripts

* rebase main
 2023-11-15 19:38:14 +08:00
Chen, Zhentao
d19ca21957 patch bigdl-llm model to harness by binding instead of patch file (#9420) 
* add run_llb.py

* fix args interpret

* modify outputs

* update workflow

* add license

* test mixed 4 bit

* update readme

* use autotokenizer

* add timeout

* refactor workflow file

* fix working directory

* fix env

* throw exception if some jobs failed

* improve terminal outputs

* Disable var which cause the run stuck

* fix unknown precision

* fix key error

* directly output config instead

* rm harness submodule
 2023-11-14 12:51:39 +08:00
Chen, Zhentao
f36d7b2d59 Fix harness stuck (#9435) 
* remove env to avoid being stuck

* use small model for test
 2023-11-13 15:29:53 +08:00
Yuwen Hu
4faf5af8f1 [LLM] Add perf test for core on Windows (#9397) 
* temporary stop other perf test

* Add framework for core performance test with one test model

* Small fix and add platform control

* Comment out lp for now

* Add missing ymal file

* Small fix

* Fix sed contents

* Small fix

* Small path fixes

* Small fix

* Add update to ftp

* Small upload fix

* add chatglm3-6b

* LLM: add model names

* Keep repo id same as ftp and temporary make baichuan2 first priority

* change order

* Remove temp if false and separate pr and nightly results

* Small fix

---------

Co-authored-by: jinbridge <2635480475@qq.com>
 2023-11-13 13:58:40 +08:00
WeiguangHan
2cfef5ef1e LLM: store the nightly test and pr results separately (#9404) 
* LLM: store the csv results separately

* modify the trigger files of LLM Performance Test
 2023-11-11 06:35:27 +08:00
Yuwen Hu
3d107f6d25 [LLM] Separate windows build UT and build runner (#9403) 
* Separate windows build UT and build runner

* Small fix
 2023-11-09 18:47:38 +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
Yuwen Hu
d4b248fcd4 Add windows binary build label AVX_VNNI (#9387) 2023-11-08 18:13:35 +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
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
Shaojun Liu
833e4dbc8d fix llm-performance-test-on-arc bug (#9357) 2023-11-06 10:00:25 +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
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
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
Jasonzzt
d1bdc0ef72 spr & arc ut with python 3.9 & 3.10 & 3.11 2023-11-01 22:57:48 +08:00
Jasonzzt
687da21467 test 3.11 2023-11-01 19:14:53 +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
Jasonzzt
3c3329010d add conda update -n base conda 2023-11-01 16:36:35 +08:00
Jasonzzt
2fff0e8c21 use runner avx2 with linux 2023-11-01 16:28:29 +08:00
Jasonzzt
964a8e6dc1 update conda 2023-11-01 16:20:19 +08:00
Jasonzzt
cb7ef38e86 rerun 2023-11-01 15:30:34 +08:00
Jasonzzt
8f6e979fad test again 2023-11-01 15:10:11 +08:00
Jasonzzt
b66584f23b test 2023-11-01 14:51:23 +08:00
Jasonzzt
ba148ff3ff test py311 2023-11-01 14:08:49 +08:00
Jasonzzt
6f1cee90a4 test 2023-11-01 13:58:03 +08:00
Jasonzzt
d51821e264 test 2023-11-01 13:49:32 +08:00
Jasonzzt
7c7a7f2ec1 spr & arc ut with python3,9&3.10&3.11 2023-11-01 13:17:13 +08:00
Jasonzzt
4f9fd0dffd arc-ut with 3.10 & 3.11 2023-11-01 10:51:57 +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
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
Yuwen Hu
21631209a9 [LLM] Skip CPU performance test for now (#9291) 
* Skip llm cpu performance test for now

* Add install for wheel package
 2023-10-27 12:55:04 +08:00
Ziteng Zhang
46ab0419b8 Merge pull request #9279 from Jasonzzt/main 
Add bigdl-llm-finetune-cpu to manually_build to upload image on hub
 2023-10-27 09:55:08 +08:00
Yuwen Hu
733df28a2b [LLM] Migrate Arc UT to another runner (#9286) 
* Separate arc llm ut to another runner

* Add dependency for einops
 2023-10-26 19:08:57 +08:00
Ziteng Zhang
916ccc0779 Update manually_build_for_testing.yml 2023-10-26 16:26:14 +08:00
Ziteng Zhang
14a23015f8 Update manually_build.yml 2023-10-26 16:24:03 +08:00
Jasonzzt
37b1708d16 Add bigdl-llm-finetune-cpu to manually_build 2023-10-26 15:53:44 +08:00
Lilac09
4ed7f066d3 add bigdl-llm-finetune-xpu to manually_build (#9278) 2023-10-26 15:30:05 +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
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
Guancheng Fu
f37547249d Refine README/CICD (#9253) 2023-10-24 12:56:03 +08:00
Guancheng Fu
9faa2f1eef Fix bigdl-llm-serving-tdx image (#9251) 2023-10-24 10:49:35 +08:00
Guancheng Fu
6cb884d82d Fix missing manually_build_for_testing entry (#9245) 2023-10-23 16:35:09 +08:00
Guancheng Fu
2ead3f7d54 add manually build (#9244) 2023-10-23 15:53:30 +08:00
WeiguangHan
f87f67ee1c LLM: arc perf test for some popular models (#9188) 2023-10-19 15:56:15 +08:00
ZehuaCao
65dd73b62e Update manually_build.yml (#9138) 
* Update manually_build.yml

fix llm-serving-tdx image build dir

* Update manually_build.yml
 2023-10-11 15:07:09 +08:00
Yuwen Hu
dc70fc7b00 Update performance tests for dependency of bigdl-core-xe-esimd (#9124) 2023-10-10 19:32:17 +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
Zhengjin Wang
0dbb3a283e amend manually_build 2023-10-10 10:03:23 +08:00
Zhengjin Wang
bb3bb46400 add llm-serving-xpu on github action 2023-10-10 09:48:58 +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
ZehuaCao
aad68100ae Add trusted-bigdl-llm-serving-tdx image. (#9093) 
* add entrypoint in cpu serving

* kubernetes support for fastchat cpu serving

* Update Readme

* add image to manually_build action

* update manually_build.yml

* update README.md

* update manually_build.yaml

* update attestation_cli.py

* update manually_build.yml

* update Dockerfile

* rename

* update trusted-bigdl-llm-serving-tdx Dockerfile
 2023-10-08 10:13:51 +08:00
ZehuaCao
b773d67dd4 Add Kubernetes support for BigDL-LLM-serving CPU. (#9071) 2023-10-07 09:37:48 +08:00
Lilac09
c91b2bd574 fix:modify indentation (#9070) 
* modify Dockerfile

* add README.md

* add README.md

* Modify Dockerfile

* Add bigdl inference cpu image build

* Add bigdl llm cpu image build

* Add bigdl llm cpu image build

* Add bigdl llm cpu image build

* Modify Dockerfile

* Add bigdl inference cpu image build

* Add bigdl inference cpu image build

* Add bigdl llm xpu image build

* manually build

* recover file

* manually build

* recover file

* modify indentation
 2023-09-27 14:53:52 +08:00
Lilac09
ecee02b34d Add bigdl llm xpu image build (#9062) 
* modify Dockerfile

* add README.md

* add README.md

* Modify Dockerfile

* Add bigdl inference cpu image build

* Add bigdl llm cpu image build

* Add bigdl llm cpu image build

* Add bigdl llm cpu image build

* Modify Dockerfile

* Add bigdl inference cpu image build

* Add bigdl inference cpu image build

* Add bigdl llm xpu image build
 2023-09-26 14:29:03 +08:00
Lilac09
9ac950fa52 Add bigdl llm cpu image build (#9047) 
* modify Dockerfile

* add README.md

* add README.md

* Modify Dockerfile

* Add bigdl inference cpu image build

* Add bigdl llm cpu image build

* Add bigdl llm cpu image build

* Add bigdl llm cpu image build
 2023-09-26 13:22:11 +08:00
Yuwen Hu
c389e1323d fix xpu performance tests by making sure that latest bigdl-core-xe is installed (#9001) 2023-09-19 17:33:30 +08:00
Wang Jian
7563b26ca9 Occlum fastchat build Use nocache and update order (#8972) 2023-09-14 14:05:15 +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
xingyuan li
704a896e90 [LLM] Add perf test on xpu for bigdl-llm (#8866) 
* add xpu latency job
* update install way
* remove duplicated workflow
* add perf upload
 2023-09-05 17:36:24 +09:00
xingyuan li
de6c6bb17f [LLM] Downgrade amx build gcc version and remove avx flag display (#8856) 
* downgrade to gcc 11
* remove avx display
 2023-08-31 14:08:13 +09:00
Shengsheng Huang
7b566bf686 [LLM] add new API for optimize any pytorch models (#8827) 
* add new API for optimize any pytorch models

* change test util name

* revise API and update UT

* fix python style

* update ut config, change default value

* change defaults, disable ut transcribe
 2023-08-30 19:41:53 +08:00
Wang Jian
954ef954b6 [PPML] Add occlum llm image munually build (#8849) 2023-08-30 11:31:47 +08:00
xingyuan li
67052198eb [LLM] Build with multiprocess (#8797) 
* build with multiprocess
 2023-08-29 10:49:52 +09:00
xingyuan li
6a902b892e [LLM] Add amx build step (#8822) 
* add amx build step
 2023-08-28 17:41:18 +09:00