ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
1720 commits 1 branch 0 tags 37 MiB
Commit graph

232 commits

Author SHA1 Message Date
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
Song Jiaming
b8b1b6888b [LLM] Performance test (#8796) 2023-08-25 14:31:45 +08:00
SONG Ge
d2926c7672 [LLM] Unify Langchain Native and Transformers LLM API (#8752) 
* deprecate BigDLNativeTransformers and add specific LMEmbedding method

* deprecate and add LM methods for langchain llms

* add native params to native langchain

* new imple for embedding

* move ut from bigdlnative to casual llm

* rename embeddings api and examples update align with usage updating

* docqa example hot-fix

* add more api docs

* add langchain ut for starcoder

* support model_kwargs for transformer methods when calling causalLM and add ut

* ut fix for transformers embedding

* update for langchain causal supporting transformers

* remove model_family in readme doc

* add model_families params to support more models

* update api docs and remove chatglm embeddings for now

* remove chatglm embeddings in examples

* new refactor for ut to add bloom and transformers llama ut

* disable llama transformers embedding ut
 2023-08-25 11:14:21 +08:00
xingyuan li
9537194b4b [LLM] Fix llm test workflow repeatedly download model files 2023-08-25 11:20:46 +09:00
Jin Hanyu
a73a3e5ff9 Fix bugs in manually_build_for_testing.yml. (#8792) 2023-08-23 15:49:23 +08:00
xingyuan li
c94bdd3791 [LLM] Merge windows & linux nightly test (#8756) 
* fix download statement
* add check before build wheel
* use curl to upload files
* windows unittest won't upload converted model
* split llm-cli test into windows & linux versions
* update tempdir create way
* fix nightly converted model name
* windows llm-cli starcoder test temply disabled
* remove taskset dependency
* rename llm_unit_tests_linux to llm_unit_tests
 2023-08-23 12:48:41 +09:00
Shaojun Liu
394304b918 Re organize llm test (#8766) 
* run llm-example-test in llm-nightly-test.yml

* comment out the schedule event
 2023-08-17 09:42:25 +08:00
Shaojie Cui
0a8db3abe0 [PPML]refactor python toolkit (#8740) 
* add dependency and example

* fix stage 3

* downgrade protobuf

* reduce epc memory

* add script

* Readme reduction

* delete unused note
 2023-08-15 10:11:53 +08:00
xingyuan li
1cb8f5abbd [LLM] Revert compile OS for llm build workflow (#8732) 
* use almalinux to build
 2023-08-11 17:47:45 +09:00
xingyuan li
33d9ad234f [LLM] Linux vnni build with ubuntu 18.04 (#8710) 
* move from almalinux
 2023-08-10 19:04:03 +09:00
Song Jiaming
e717e304a6 LLM first example test and template (#8658) 2023-08-10 10:03:11 +08:00
Yishuo Wang
710b9b8982 [LLM] add linux chatglm pybinding binary file (#8698) 2023-08-08 11:16:30 +08:00
xingyuan li
4482ccb329 [LLM] Change build system from centos7 to ubuntu18.04 (#8686) 
* centos7 to ubuntu18
* ubuntu git version 2.17 need to update
* use almalinux8 to build avx2 binaries
 2023-08-07 19:09:58 +09:00
Yishuo Wang
5837cc424a [LLM] add chatglm pybinding binary file release (#8677) 2023-08-04 11:45:27 +08:00
xingyuan li
bc4cdb07c9 Remove conda for llm workflow (#8671) 2023-08-04 12:09:42 +09:00
xingyuan li
110cfb5546 [LLM] Remove old windows nightly test code (#8668) 
Remove old Windows nightly test code triggered by task scheduler
Add new Windows nightly workflow for nightly testing
 2023-08-03 17:12:23 +09:00
Yina Chen
bd177ab612 [LLM] llm binary build linux add avx & avx2 (#8665) 
* llm add linux avx & avx2 release

* fix name

* update check
 2023-08-03 14:38:31 +08:00
xingyuan li
610084e3c0 [LLM] Complete windows unittest (#8611) 
* add windows nightly test workflow
* use github runner to run pr test
* model load should use lowbit
* remove tmp dir after testing
 2023-08-03 14:48:42 +09:00
Xin Qiu
0714888705 build windows avx dll (#8657) 
* windows avx

* add to actions
 2023-08-03 02:06:24 +08:00
Yina Chen
15b3adc7ec [LLM] llm linux binary make -> cmake (#8656) 
* llm linux make -> cmake

* update

* update
 2023-08-02 16:41:54 +08:00
xingyuan li
769209b7f0 Chatglm unittest disable due to missing instruction (#8650) 2023-08-02 10:28:42 +09:00
xingyuan li
cdfbe652ca [LLM] Add chatglm support for llm-cli (#8641) 
* add chatglm build
* add llm-cli support
* update git
* install cmake
* add ut for chatglm
* add files to setup
* fix bug cause permission error when sf lack file
 2023-08-01 14:30:17 +09:00
xingyuan li
3361b66449 [LLM] Revert llm-cli to disable selecting executables on Windows (#8630) 
* revert vnni file select
* revert setup.py
* add model-api.dll
 2023-07-31 11:15:44 +09:00
xingyuan li
919791e406 Add needs to make sure run in order (#8621) 2023-07-26 14:16:57 +09:00
xingyuan li
e3418d7e61 [LLM] Remove concurrency group for binary build workflow (#8619) 
* remove concurrency group for nightly test
 2023-07-26 12:15:53 +09:00
xingyuan li
a98b3fe961 Fix cancel flag causing nightly builds to fail (#8618) 2023-07-26 11:11:08 +09:00
xingyuan li
7d45233825 fix trigger enable flag (#8616) 2023-07-26 10:53:03 +09:00
Guancheng Fu
07d1aee825 [PPML] add fastchat image for tdx (#8610) 2023-07-25 15:23:41 +08:00
Song Jiaming
650b82fa6e [LLM] add CausalLM and Speech UT (#8597) 2023-07-25 11:22:36 +08:00
xingyuan li
9c897ac7db [LLM] Merge redundant code in workflow (#8596) 
* modify workflow concurrency group
* Add build check to avoid repeated compilation
* remove redundant code
 2023-07-25 12:12:00 +09:00
Yuwen Hu
bbde423349 [LLM] Add current Linux UT inference tests to nightly tests (#8578) 
* Add current inference uts to nightly tests

* Change test model from chatglm-6b to chatglm2-6b

* Add thread num env variable for nightly test

* Fix urls

* Small fix
 2023-07-21 13:26:38 +08:00
Yuwen Hu
2266ca7d2b [LLM] Small updates to transformers int4 ut (#8574) 
* Small fix to transformers int4 ut

* Small fix
 2023-07-20 13:20:25 +08:00
xingyuan li
2eeb653c75 fix llm build workflow misspell (#8575) 2023-07-20 12:08:54 +09:00
Song Jiaming
411d896636 LLM first transformers UT (#8514) 
* ut

* transformers api first ut

* name

* dir issue

* use chatglm instead of chatglm2

* omp

* set omp in sh

* source

* taskset

* test

* test omp

* add test
 2023-07-20 10:16:27 +08:00
Yishuo Wang
3bd1420b71 LLM: use MSVC to build avx-vnni binary files (#8570) 2023-07-19 17:38:14 +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
xingyuan li
c87853233b [LLM] Add windows vnni binary build step (#8518) 
* add windows vnni build step
* update build info
* add download command
 2023-07-14 17:24:39 +09:00
xingyuan li
903e9aee7a Fix the problem of workflow cancellation after pr merge (#8530) 
* remove concurrency group for llm binary build workflow
 2023-07-14 16:12:21 +09:00
Yuwen Hu
df97d39e29 Change thread_num in Linux inference actions (#8528) 2023-07-14 10:46:03 +08:00
xingyuan li
60c2c0c3dc Bug fix for merged pr #8503 (#8516) 2023-07-13 17:26:30 +09:00
xingyuan li
4f152b4e3a [LLM] Merge the llm.cpp build and the pypi release (#8503) 
* checkout llm.cpp to build new binary
* use artifact to get latest built binary files
* rename quantize
* modify all release workflow
 2023-07-13 16:34:24 +09:00
xingyuan li
04f2f04410 Add workflow_dispatch for llm unittest workflow (#8485) 2023-07-10 13:16:18 +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
Yuwen Hu
936d21635f [LLM] Extract tests to .github/actions to improve reusability (#8457) 
* Extract tests to .github/actions for better reusing in nightly tests

* Small fix

* Small fix
 2023-07-05 10:09:10 +08:00
Guancheng Fu
e3e95e92ca Add workflow for releasing TDX bigdl-llm image (#8455) 2023-07-04 17:00:29 +08:00
Yuwen Hu
372c775cb4 [LLM] Change default runner for LLM Linux tests to the ones with AVX512 (#8448) 
* Basic change for AVX512 runner

* Remove conda channel and action rename

* Small fix

* Small fix and reduce peak convert disk space

* Define n_threads based on runner status

* Small thread num fix

* Define thread_num for cli

* test

* Add self-hosted label and other small fix
 2023-07-04 14:53:03 +08:00
binbin Deng
146662bc0d LLM: fix langchain windows failure (#8417) 2023-06-30 09:59:10 +08:00
Yina Chen
6251ad8934 [LLM]Windows unittest (#8356) 
* win-unittest

* update

* update

* try llama 7b

* delete llama

* update

* add red-3b

* only test red-3b

* revert

* add langchain

* add dependency

* delete langchain
 2023-06-29 14:03:12 +08:00
Ruonan Wang
4be784a49d LLM: add UT for starcoder (convert, inference) update examples and readme (#8379) 
* first commit to add path

* update example and readme

* update path

* fix

* update based on comment
 2023-06-27 12:12:11 +08:00
Shengsheng Huang
c113ecb929 [LLM] langchain bloom, UT's, default parameters (#8357) 
* update langchain default parameters to align w/ api

* add ut's for llm and embeddings

* update inference test script to install langchain deps

* update tests workflows

---------

Co-authored-by: leonardozcm <changmin.zhao@intel.com>
 2023-06-25 17:38:00 +08:00
Yuwen Hu
066f53232d [LLM] Small nightly tests fix (#8364) 
* Test for install of tnftp

* Improve install of tnftp
 2023-06-20 11:19:13 +08:00
binbin Deng
ab1a833990 LLM: add basic uts related to inference (#8346) 2023-06-19 10:25:51 +08:00
xingyuan li
daae7bd4e4 [LLM] Unittest for llm-cli (#8343) 
* add llm-cli test shell
 2023-06-16 17:42:24 +08:00
Yuwen Hu
1aa33d35d5 [LLM] Refactor LLM Linux tests (#8349) 
* Small name fix

* Add convert nightly tests, and for other llm tests, use stable ckpt

* Small fix and ftp fix

* Small fix

* Small fix
 2023-06-16 15:22:48 +08:00
Yuwen Hu
50dd9dd1c5 [LLM] Small improve for LLM base actions (#8344) 
* Hide ftp url for now

* Small file name fix
 2023-06-15 16:22:41 +08:00
Yuwen Hu
b30aa49c4e [LLM] Add Actions for downloading & converting models (#8320) 
* First push to downloading and converting llm models for testing (Gondolin runner, avx2 for now)

* Change yml file name
 2023-06-15 13:43:47 +08:00
Ruonan Wang
8840dadd86 LLM: binary file version control on source forge (#8329) 
* support version control for llm based on date

* update action
 2023-06-15 09:53:27 +08:00
Pingchuan Ma (Henry)
773255e009 [LLM] Add dev wheel building and basic UT script for LLM package on Linux (#8264) 
* add wheel build for linux

* test fix

* test self-hosted runner

* test fix

* update runner

* update runner

* update fix

* init cicd

* init cicd

* test conda

* update fix

* update no need manual python deps

* test fix bugs

* test fix bugs

* test fix bugs

* fix bugs
 2023-06-08 00:49:57 +08:00
Pingchuan Ma (Henry)
2ed5842448 [LLM] add convert's python deps for LLM (#8260) 
* add python deps for LLM

* update release.sh

* change deps group name

* update all

* fix update

* test fix

* update
 2023-06-06 16:01:17 +08:00
Pingchuan Ma (Henry)
c48d5f7cff [LLM] Enable UT workflow logics for LLM (#8243) 
* check push connection

* enable UT workflow logics for LLM

* test fix

* add licenses

* test fix according to suggestions

* test fix

* update changes
 2023-06-02 17:06:35 +08:00
Pingchuan Ma (Henry)
141febec1f Add dev wheel building script for LLM package on Windows (#8238) 
* Add dev wheel building script for LLM package on Windows

* delete conda

* delete python version check

* minor adjust

* wheel name fixed

* test check

* test fix

* change wheel name
 2023-06-01 11:55:26 +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
Xiangyu Tian
94f08edbb3 [PPML] Refactor BigDL Attestation Service Deployment of Docker and K8s (#8130) 
Refactor BigDL Attestation Service Deployment of Docker image, which split to base image and custom(reference) image.
Update version to 2.4.0-SNAPSHOT.
Refine documents.
 2023-04-26 14:28:00 +08:00
Yao Li
d833a765fe update manually build (#8129) 2023-04-24 16:08:56 +08:00
Yao Li
8719674c92 update manually_build.yml (#8126) 2023-04-24 15:29:24 +08:00
Le-Zheng
8b0876f238 add tdx image in action (#8125) 
* add tdx image in action

* update

* Update manually_build.yml

* update Readme
 2023-04-24 14:37:14 +08:00
Yao Li
f30215a77e delete outdated bigdl kms (#8115) 2023-04-23 15:45:55 +08:00
Yao Li
981bded4b3 fix bigdl-kms-reference (#8110) 2023-04-23 14:08:53 +08:00
Yao Li
c7630f759a [PPML] Add bigdl-kms into manually build (#8105) 
* update readme

* update manually_build.yml

* Update manually_build.yml

* fix format

* udpate

* update
 2023-04-23 11:51:00 +08:00
Wang Jian
96c9343ef2 [PPML] Update occlum production image build dir (#8098) 2023-04-21 11:46:42 +08:00
Heyang Sun
814f5bd915 add no_proxy for bigdl-kms (#7996) 2023-04-06 09:18:53 +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
Heyang Sun
e91cb31575 set no (#7974) 2023-04-03 09:02:43 +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
Guancheng Fu
3a57b97c2b Add dl-serving manually_build workflow (#7719) 2023-03-01 11:05:57 +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