ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
1063 commits 1 branch 0 tags 37 MiB
Commit graph

1063 commits

This branch
This branch
All branches
Author SHA1 Message Date
Jun Wang
2bc0e7abbb [llm] Add convert_model api (#8244) 
* add convert_model api

* change the model_path to input_path

* map int4 to q4_0

* fix blank line

* change bloomz to bloom

* remove default model_family

* change dtype to lower first
 2023-06-03 10:18:29 +08:00
Yuwen Hu
e290660b20 [LLM] Add so shared library for Bloom family models (#8258) 
* Add so file downloading for bloom family models

* Supports selecting of avx2/avx512 so for bloom
 2023-06-02 17:39:40 +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
Yina Chen
657ea0ee50 [LLM] Fix linux load libs for NeoX and llama (#8257) 
* init

* add lisence

* fix style
 2023-06-02 17:03:17 +08:00
Yuwen Hu
286b010bf1 [LLM] First push for Bloomz pybinding (#8252) 
* Initial commit to move bloom pybinding to bigdl-llm

* Revise path for shared library

* Small fix
 2023-06-02 14:41:04 +08:00
Yina Chen
91a1528fce [LLM]Support for linux package (llama, NeoX) & quantize (llama) (#8246) 
* temp

* update

* update

* remove cmake

* runtime get platform  ->  change platform name using sed

* update

* update

* add platform flags(default: current platform) & delete legacy libs & add neox quantize
 2023-06-02 13:51:35 +08:00
Junwei Deng
350d31a472 LLM: first push gptneox pybinding (#8234) 
* first push gptneox pybinding

* fix

* fix code style and add license

---------

Co-authored-by: binbin <binbin1.deng@intel.com>
 2023-06-02 09:28:00 +08:00
binbin Deng
3a9aa23835 LLM: fix and update related license in llama pybinding (#8250) 2023-06-01 17:09:15 +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
binbin Deng
e56f24b424 LLM: first push llama pybinding (#8241) 
* first push llama binding

* update dll
 2023-06-01 10:59:15 +08:00
Ruonan Wang
3fd716d422 LLM: update setup.py to add a missing data(#8240) 2023-06-01 10:25:43 +08:00
binbin Deng
8421af51ae LLM: support converting to ggml format (#8235) 
* add convert

* fix

* fix

* fix

* try

* test

* update check

* fix

* fix
 2023-05-31 15:20:06 +08:00
Ruonan Wang
c890609d1e LLM: Support package/quantize for llama.cpp/redpajama.cpp on Windows (#8236) 
* support windows of llama.cpp

* update quantize

* update version of llama.cp submodule

* add gptneox.dll

* add quantize-gptneox.exe
 2023-05-31 14:47:12 +08:00
Yishuo Wang
fa0b0a4555 [nano] fix optuna version (#8237) 2023-05-31 13:44:04 +08:00
Pingchuan Ma (Henry)
1f913a6941 [LLM] Add LLM pep8 coding style checking (#8233) 
* add LLM pep8 coding checking

* resolve bugs in testing scripts and code style revision
 2023-05-30 15:58:14 +08:00
Ruonan Wang
4638b85f3e [llm] Initial support of package and quantize (#8228) 
* first commit of CMakeFiles.txt to include llama & gptneox

* initial support of quantize

* update cmake for only consider linux now

* support quantize interface

* update based on comment
 2023-05-26 16:36:46 +08:00
Junwei Deng
ea22416525 LLM: add first round files (#8225) 2023-05-25 11:29:18 +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
binbin Deng
21d5108f95 Chronos: improve prvd and nb tests with more python versions (#8048) 2023-05-10 13:52:54 +08:00
Ruonan Wang
c0967bc143 [Nano] Fix link of win.md (#8174) 2023-05-09 10:13:19 +08:00
Pingchuan Ma (Henry)
30367f5eb1 [Nano] Add how-to-guide for pytorch async pipeline (#8146) 
* add how-to-guide for pytorch async pipeline

* revise introduction

* resolve image issues
 2023-05-06 22:15:42 +08:00
Ruonan Wang
e178692c2c [Nano] Support python 3.10 in nightly test (#8163) 
* support 3.10

* fix version of onnxruntime-extensions

* upgrade ray

* fix from collections.abc import Iterable

* upgrade onnxruntime-extensions to 0.7.0
 2023-05-06 15:56:40 +08:00
Ruonan Wang
203753270d [Nano] Upgrade python to 3.8 (#8137) 
* upgrade python to 3.8

* fix version of protobuf

* upgrade python in nightly and regression
 2023-05-05 13:11:32 +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
Le-Zheng
9fdbede632 update 2.4.0-snapshot readthedoc (#8127) 2023-04-24 15:47:41 +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
binbin Deng
5ed3ac52c0 Chronos: update information about python version in installation document (#8081) 2023-04-24 11:17:35 +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
Cengguang Zhang
5ebfaa9a77 Doc: Add known issues for Orca. (#8096) 
* Doc: add known issues for orca.

* fix: fix style.

* fix: style.
 2023-04-21 14:48:33 +08:00
Wang Jian
96c9343ef2 [PPML] Update occlum production image build dir (#8098) 2023-04-21 11:46:42 +08:00
Yuwen Hu
9ffd1f6dda Mock prophet as doc building failed (#8083) 2023-04-19 17:24:58 +08:00
Kai Huang
a3848611e8 Add Orca workflow image (#8049) 2023-04-14 15:38:32 +08:00
Pingchuan Ma (Henry)
c6eccbfcc2 [Nano] add pt dgpu inference how-to-guide (#8026) 
* docs for arc dgpu how-to-guide

* minor adjustment + system info

* minor adjustment for appearance

* fix bugs

* add system info

* fix syntax errors

* adjust docs according to comments

* final adjustment

* delete gpu workflow testing
 2023-04-12 19:18:16 +08:00
Junwei Deng
2daaa6f7de Nano: TF multi process how-to for customized training loop (#8006) 
* add how-to guide

* add overview

* fix doc

* fix pep8

* update the notebook
 2023-04-07 17:19:47 +08:00
joan726
9695ef2978 Updated Powered By and Blogs (#7909) 
* Update blogs.md

* Update powered-by.md

* Update powered-by.md

Corrected Yahoo! to Yahoo! JAPAN
 2023-04-07 15:02:03 +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
Junwei Deng
a6f96521af Chronos: AIOps User Guide (#7960) 
* add aiops doc

* add image

* fix typo
 2023-03-31 10:15:00 +08:00
Jiao Wang
a02402e410 update (#7904) 2023-03-20 01:38:53 -07:00
Jason Dai
eac9b088e2 [Document] Update Nano description (#7872) 2023-03-15 08:36:19 +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
Xiangyu Tian
144efd0748 Add MAA part to azure_ppml readthedocs document (#7857) 
Docs modification to add how to enable MAA in azure_ppml.
 2023-03-14 14:45:58 +08:00
Xin Qiu
633668c882 Update nnframes.md (#7808) 2023-03-08 15:29:00 +08:00