ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
2915 commits 1 branch 0 tags 37 MiB
Commit graph

67 commits

Author SHA1 Message Date
Wang, Jian4
86cec80b51
LLM: Add llm inference_cpp_xpu_docker (#10933) 
* test_cpp_docker

* update

* update

* update

* update

* add sudo

* update nodejs version

* no need npm

* remove blinker

* new cpp docker

* restore

* add line

* add manually_build

* update and add mtl

* update for workdir llm

* add benchmark part

* update readme

* update 1024-128

* update readme

* update

* fix

* update

* update

* update readme too

* update readme

* no change

* update dir_name

* update readme
 2024-05-15 11:10:22 +08:00
Qiyuan Gong
1e00bd7bbe
Re-org XPU finetune images (#10971) 
* Rename xpu finetune image from `ipex-llm-finetune-qlora-xpu` to `ipex-llm-finetune-xpu`.
* Add axolotl to xpu finetune image.
* Upgrade peft to 0.10.0, transformers to 4.36.0.
* Add accelerate default config to home.
 2024-05-15 09:42:43 +08:00
Wang, Jian4
459b764406
Remove munually_build_for_test push outside (#10968) 2024-05-09 10:40:34 +08:00
Wang, Jian4
33b8f524c2
Add cpp docker manually_test (#10946) 
* add cpp docker

* update
 2024-05-07 11:23:28 +08:00
Shaojun Liu
bb9be70105
replace bigdl-llm with ipex-llm (#10545) 2024-03-26 15:12:38 +08:00
Shaojun Liu
7a3a20cf5b Fix: GitHub-owned GitHubAction not pinned by hash (#10152) 2024-02-18 16:49:28 +08:00
Shaojun Liu
9f5a86f9db fix OpenSSF Token-Permissions issues (#10121) 
Co-authored-by: Your Name <Your Email>
 2024-02-07 16:51:10 +08:00
Wang, Jian4
40ec9f7ead Add qlora cpu docker manually build (#9501) 2023-11-21 14:39:16 +08:00
Ziteng Zhang
916ccc0779 Update manually_build_for_testing.yml 2023-10-26 16:26:14 +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
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
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
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
Wang Jian
7563b26ca9 Occlum fastchat build Use nocache and update order (#8972) 2023-09-14 14:05:15 +08:00
Wang Jian
954ef954b6 [PPML] Add occlum llm image munually build (#8849) 2023-08-30 11:31:47 +08:00
Jin Hanyu
a73a3e5ff9 Fix bugs in manually_build_for_testing.yml. (#8792) 2023-08-23 15:49:23 +08:00
Guancheng Fu
07d1aee825 [PPML] add fastchat image for tdx (#8610) 2023-07-25 15:23:41 +08:00
Guancheng Fu
4f287df664 Fix manullay_build_for_testing (#8556) 2023-07-18 16:21:39 +08:00
Guancheng Fu
3e0e370898 [PPML] Add bigdl-llm-demo dependencies to TDX image (#8551) 
* add bigdl-llm-demo dependencies to tdx image

* use only one RUN command

* Add bigdl-ppml

* done
 2023-07-18 14:23:07 +08:00
Guancheng Fu
a4ae132ef4 Add bigdl llm sgx image (#8480) 
* Add dockerfile for bigdl-llm-ppml

* fix llm-cli multi-process

* add workflow
 2023-07-10 10:10:38 +08:00
Wang Jian
16c795158d [PPML] Pull new deep-learning base image before build (#8469) 
* pull new base image before build

* update
 2023-07-06 14:29:09 +08:00
Shaojie Cui
768b15881d [PPML]CICD: build 32g bigdata image (#8205) 
* [PPML]CICD: build 32g bigdata image

* fix
 2023-05-17 11:30:10 +08:00
Wang Jian
96c9343ef2 [PPML] Update occlum production image build dir (#8098) 2023-04-21 11:46:42 +08:00
Shaojie Cui
f885466475 [CICD]fix: typo in build (#7990) 2023-04-04 14:30:44 +08:00
Shaojie Cui
8a24ae76a8 [CICD]fix image name in bigdata toolkit (#7978) 2023-04-03 15:57:27 +08:00
Shaojie Cui
13717ee5c8 [CICD]add noattest bigdata toolkit image (#7968) 2023-03-31 14:02:08 +08:00
Shaojie Cui
522e5ae35b [CICD]add no_proxy arg when building bigdata (#7868) 
* [CICD]add no_proxy arg when building bigdata

* fix
 2023-03-14 16:34:52 +08:00
Shaojie Cui
57125dfcd4 [PPML]tag 8g epc bigdata as default image (#7789) 
* build 4g and tag 8g as latest

* reduce script memory

* doc
 2023-03-08 10:49:40 +08:00
Shaojie Cui
f0fa26a8a8 [PPML]Reduce the epc usage of bigdata (#7606) 
* build bigdata with smaller epc

* reduce epc in script

* fix action

* install pyarrow

* delete unused part

* reduce epc

* fix

* malloc_arena_max

* set 16g to default and delete 4g

* unused example

* spark simplequery

* pyspark simplequery

* fix

* fix

* fix

* code style fix
 2023-03-01 14:59:27 +08:00
Shaojie Cui
feacade38c [CICD]fix: delete latest tag bigdata image built for testing (#7701) 2023-02-27 17:01:22 +08:00
Shaojie Cui
b12f2e1902 [CICD]delete bigdata image with debug log level (#7657) 2023-02-23 09:53:06 +08:00
Shaojie Cui
e5fb0a3315 [CICD]build bigdata toolkit with no cache (#7652) 2023-02-22 16:32:28 +08:00
Guancheng Fu
3adcb84e24 Update dl-serving-gramine-ref workflow 2023-02-17 13:48:45 +08:00
Guancheng Fu
de1ec0d19b Update workflow for dl-serving gramine-ref 2023-02-17 13:43:31 +08:00
Guancheng Fu
842e676ad7 adding new workflow for dl-serving image (#7595) 2023-02-17 10:29:20 +08:00
Shaojie Cui
ec2b9c13ee [CICD]add bigdata toolkit with debug log level (#7564) 2023-02-15 20:16:17 +08:00
Shaojie Cui
3e040d7b28 [PPML]refactor bigdata build (#7088) 2022-12-26 13:49:59 +08:00
Wang Jian
b82975a8d1 [PPML] Update customer image readme (#6859) 
* push no build production image

* init build.sh

* update

* update path

* update rm order

* update path

* update readme

* update
 2022-12-02 16:45:30 +08:00
Xiangyu Tian
cd8d21dded Fix docker rmi in manually_build (#6716) 2022-11-23 13:44:48 +08:00
Wang Jian
229302b758 Update occlum register path (#6709) 2022-11-22 10:47:52 +08:00
Guancheng Fu
1b72f1b38f [PPML] Upgrade PyTorch version to 1.13.0 (#6638) 
* Make gramine to generate patched OpenMP

* cp libgomp to /usr/local/lib/

* Move gopenmp to a different place

* add patch to use gramine version openmp

* Change base Dockerfile

* Applying optimization recommended by PyTorch tutorial

* Ready for test pert_ipex.py

* remove extra space

* Fix dockerfile to use PyTorch 1.13.0

* Pin markupsafe to 2.0.1 after installing bigdl-nano, may need changes?

* Change test workflow
 2022-11-21 20:02:30 +08:00
Wang Jian
8f18a235fd Occlum customer image build action no cache (#6674) 2022-11-18 11:27:27 +08:00
Shaojie Cui
aff0f55b7f fix: add var base_image in bigdata build (#6616) 2022-11-15 16:31:33 +08:00
Shaojie Cui
f1d4fb4d37 cicd:add option bigdl-ppml-trusted-bigdata-gramine (#6615) 2022-11-15 16:19:43 +08:00