ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
2842 commits 1 branch 0 tags 37 MiB
Commit graph

610 commits

Author SHA1 Message Date
SONG Ge
fbd1743b5e
Ollama quickstart update (#10806) 
* add ollama doc for OLLAMA_NUM_GPU

* remove useless params

* revert unexpected changes back

* move env setting to server part

* update
 2024-04-19 15:00:25 +08:00
ZehuaCao
a7c12020b4
Add fastchat quickstart (#10688) 
* add fastchat quickstart

* update

* update

* update
 2024-04-16 14:02:38 +08:00
Ruonan Wang
ea5e46c8cb
Small update of quickstart (#10772) 2024-04-16 10:46:58 +08:00
Yuwen Hu
1abd77507e
Small update for GPU configuration related doc (#10770) 
* Small doc fix for dGPU type name

* Further fixes

* Further fix

* Small fix
 2024-04-15 18:43:29 +08:00
Ruonan Wang
1bd431976d
Update ollama quickstart (#10756) 
* update windows part

* update ollama quickstart

* update ollama

* update

* small fix

* update

* meet review
 2024-04-15 16:37:55 +08:00
Kai Huang
47622c6a92
Fix missing export typo in linux quickstart (#10750) 2024-04-15 14:16:40 +08:00
Yuwen Hu
486df2764a
Update gpu configuration (#10760) 2024-04-15 13:27:15 +08:00
Shengsheng Huang
0ccd7bfca9
revise quickstart (#10721) 2024-04-10 14:24:53 +08:00
yb-peng
a81f9e61a6
Revise open_webui_with_ollama_quickstart.md (#10720) 2024-04-10 14:04:13 +08:00
Shengsheng Huang
6e7da0d92c
small fix in document 2024-04-09 23:04:26 +08:00
Shengsheng Huang
8924dbc3f9
revise open webui quickstart and some indexes (#10715) 
* update readme

* update openwebui readme and update index
 2024-04-09 22:44:03 +08:00
Yuwen Hu
a0244527aa
Small updates to langchain-chatchat quickstart readme (#10714) 2024-04-09 19:37:41 +08:00
Yuwen Hu
fde6ab50d0
Further fix to python 3.11 document (#10712) 2024-04-09 19:13:01 +08:00
yb-peng
447f48499a
Init commit of open-webui quickstart (#10682) 
* init commit of open-webui quickstart

* add links into open-webui quickstart

* Update open_webui_with_ollama_quickstart.md
 2024-04-09 18:21:42 +08:00
Shaojun Liu
f37a1f2a81
Upgrade to python 3.11 (#10711) 
* create conda env with python 3.11

* recommend to use Python 3.11

* update
 2024-04-09 17:41:17 +08:00
Jason Dai
3e4fbee87c
Update readme & quickstart (#10685) 2024-04-09 15:59:17 +08:00
yb-peng
8cf26d8d08
Update ollama_quickstart.md (#10708) 2024-04-09 15:47:41 +08:00
Keyan (Kyrie) Zhang
a11b708135
Modify the .md link in chatchat readthedoc (#10681) 2024-04-07 16:33:32 +08:00
Shengsheng Huang
33f90beda0
fix quickstart docs (#10676) 2024-04-07 14:26:59 +08:00
Jason Dai
29d97e4678
Update readme (#10665) 2024-04-05 18:01:57 +08:00
Yang Wang
ac65ab65c6
Update llama_cpp_quickstart.md (#10663) 2024-04-04 11:00:50 -07:00
Shengsheng Huang
22f09f618a
update the video demo (#10655) 2024-04-03 20:51:01 +08:00
Jason Dai
7c08d83d9e
Update quickstart (#10654) 2024-04-03 20:43:22 +08:00
Shengsheng Huang
f84e72e7af
revise ollama quickstart (#10653) 2024-04-03 20:35:34 +08:00
yb-peng
f789c2eee4
add ollama quickstart (#10649) 
Co-authored-by: arda <arda@arda-arc12.sh.intel.com>
 2024-04-03 19:33:39 +08:00
Shengsheng Huang
1ae519ec69
add langchain-chatchat quickstart (#10652) 2024-04-03 19:23:09 +08:00
Shengsheng Huang
45437ddc9a
update indexes, move some sections in coding quickstart to webui (#10651) 2024-04-03 18:18:49 +08:00
Shengsheng Huang
c26e06d5cf
update coding quickstart and webui quickstart for warmup note (#10650) 2024-04-03 17:18:28 +08:00
Yuwen Hu
5b096c39a6
Change style for video rendering (#10646) 2024-04-03 16:31:02 +08:00
Ovo233
97c626d76f
add continue quickstart (#10610) 
Co-authored-by: Shengsheng Huang <shengsheng.huang@intel.com>
 2024-04-03 14:50:11 +08:00
Jason Dai
e184c480d2
Update WebUI Quickstart (#10630) 2024-04-02 21:49:19 +08:00
Yuwen Hu
89d780f2e9
Small fix to install guide (#10618) 2024-04-02 11:10:55 +08:00
Shaojun Liu
59058bb206
replace 2.5.0-SNAPSHOT with 2.1.0-SNAPSHOT for llm docker images (#10603) 2024-04-01 09:58:51 +08:00
Yuxuan Xia
856f1ace2b
Add linux 6.5 kernel installation (#10573) 
* Add linux 6.5 kernel installation

* Fix linux quick start typo
 2024-03-29 16:02:19 +08:00
Yuwen Hu
e6c5a6a5e6
Small style fix in Install Guide (#10581) 
* Remove strange bold style

* Small fix
 2024-03-28 18:36:17 +08:00
Yuwen Hu
15b8964403
Win install change oneapi to pip installer (#10577) 
* Update windows related guide to use pip installer for oneAPI

* Small style fix

* Add oneAPI version

* Update based on comments

* Small fix
 2024-03-28 18:22:46 +08:00
Keyan (Kyrie) Zhang
0a2e820c9f
Modify install_linux_gpu.md (#10576) 2024-03-28 13:20:42 +08:00
Cheen Hau, 俊豪
1c5eb14128
Update pip install to use --extra-index-url for ipex package (#10557) 
* Change to 'pip install .. --extra-index-url' for readthedocs

* Change to 'pip install .. --extra-index-url' for examples

* Change to 'pip install .. --extra-index-url' for remaining files

* Fix URL for ipex

* Add links for ipex US and CN servers

* Update ipex cpu url

* remove readme

* Update for github actions

* Update for dockerfiles
 2024-03-28 09:56:23 +08:00
Kai Huang
e619142a16
Add SYCL_CACHE_PERSISTENT in doc and explain warmup in benchmark quickstart (#10571) 
* update doc

* update
 2024-03-27 21:03:51 +08:00
Yuwen Hu
1bae5f40d2
Hide pip installer for windows install (#10568) 
* Hide oneAPI install with pip installer for now

* Small fix
 2024-03-27 18:41:41 +08:00
Cheen Hau, 俊豪
f239bc329b
Specify oneAPI minor version in documentation (#10561) 2024-03-27 17:58:57 +08:00
Yuwen Hu
c182acef3f
[Doc] Update IPEX-LLM Index Page (#10534) 
* Update readthedocs readme before Latest Update

* Update before quick start section in index page

* Update quickstart section

* Further updates for Code Example

* Small fix

* Small fix

* Fix migration guide style
 2024-03-25 18:43:32 +08:00
Yuwen Hu
e0ea7b8244
[Doc] IPEX-LLM Doc Layout Update (#10532) 
* Fix navigation bar to 1

* Remove unnecessary python api

* Fixed failed langchain native api doc

* Change index page layout

* Update quicklink for IPEX-LLM

* Simplify toc and add bigdl-llm migration guide

* Update readthedocs readme

* Add missing index link for bigdl-llm migration guide

* Update logo image and repo link

* Update copyright

* Small fix

* Update copyright

* Update top nav bar

* Small fix
 2024-03-25 16:23:56 +08:00
Shengsheng Huang
de5bbf83de
update linux quickstart and formats of migration (#10530) 
* update linux quickstart and formats of migration

* update quickstart

* update format
 2024-03-25 15:38:02 +08:00
Jason Dai
5b76f88a8f
Update README.md (#10518) 2024-03-25 13:37:01 +08:00
Shengsheng Huang
d7d0e66b18
move migration guide to quickstart (#10521) 2024-03-25 11:50:49 +08:00
Wang, Jian4
16b2ef49c6
Update_document by heyang (#30) 2024-03-25 10:06:02 +08:00
Wang, Jian4
9df70d95eb
Refactor bigdl.llm to ipex_llm (#24) 
* Rename bigdl/llm to ipex_llm

* rm python/llm/src/bigdl

* from bigdl.llm to from ipex_llm
 2024-03-22 15:41:21 +08:00
Ruonan Wang
a7da61925f LLM: add windows related info in llama-cpp quickstart (#10505) 
* first commit

* update

* add image, update Prerequisites

* small fix
 2024-03-22 13:51:14 +08:00
Cheen Hau, 俊豪
a7d38bee94 WebUI quickstart: add instruct chat mode and tested models (#10436) 
* Add instruct chat mode and tested models

* Fix table

* Remove falcon from 'tested models'

* Fixes

* Open image in new window
 2024-03-21 20:15:32 +08:00
Kai Huang
92ee2077b3 Update Linux Quickstart (#10499) 
* fix quick start

* update toc

* expose docker
 2024-03-21 20:13:21 +08:00
Ruonan Wang
8d0ea1b9b3 LLM: add initial QuickStart for linux cpp usage (#10418) 
* add first version

* update content and add link

* --amend

* update based on new usage

* update usage based on new pr

* temp save

* basic stable version

* change to backend
 2024-03-21 17:35:58 +08:00
Yuxuan Xia
3d59c74a0b Linux quick start (#10391) 
* Fix Baichuan2 prompt format

* Add linux quick start guide

* Modify the linux installation quick start

* Adjust Linux quick start

* Adjust Linux quick start

* Add linux quick start screenshots

* Revert Baichuan2 changes

* Fix linux quick start typo

* Fix linux quick start typos

* Remove linux quick start downgrade kernel

* Change linux quick start bigdl install

* Modify linux quick start
 2024-03-21 16:02:29 +08:00
hxsz1997
158a49986a Add quickstart for install bigdl-llm in docker on windows with Intel GPU (#10421) 
* add quickstart for install bigdl in docker on window with Intel GPU

* modify the inference command

* add note of required disk space

* add the issue of iGPU
 2024-03-21 15:57:27 +08:00
Shengsheng Huang
e25d7413de add prerequisite section in quickstart (#10460) 
* add prerequisite section

* fix typo
 2024-03-19 14:24:51 +08:00
Cheen Hau, 俊豪
9880ddfc17 Update WebUI quickstart (#10316) 
* Enlarge images and make them clickable to open in new window

* Update text to match image

* Remove image for 'AttributeError' since it does not show the error

* Add note on slower first response

* 'gpu models' -> 'gpu types'
 2024-03-13 17:59:55 +08:00
Lilac09
aec83a8be6 Fix user guide indent (#10393) 2024-03-13 09:49:07 +08:00
Jin Qiao
c2fb17bd43 LLM: update quickstart Windows gpu install guide & other quickstart doc style (#10365) 
* init

* fix doc style, add modelscope and tutorial

* fix web ui doc style

* add exit way

* fix

* fix modelscope note

* fix according to comment

* fix according to comment

* fix

* fix according to comments

* fix

* fix

* fix

* fix style

* try fix

* fix

* fix

* Small updates

---------

Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
 2024-03-12 18:38:35 +08:00
Lilac09
5809a3f5fe Add run-hbm.sh & add user guide for spr and hbm (#10357) 
* add run-hbm.sh

* add spr and hbm guide

* only support quad mode

* only support quad mode

* update special cases

* update special cases
 2024-03-12 16:15:27 +08:00
WeiguangHan
cac96b00be LLM: Small fix for benchmark userguide (#10373) 
* small fix for benchmark userguide

* resolve some comments
 2024-03-12 12:26:26 +08:00
WeiguangHan
f4cef95690 LLM: some slight modification to benchmark user guide (#10347) 2024-03-08 19:43:12 +08:00
Cheen Hau, 俊豪
6829efd350 Change quickstart documentation to use oneapi offline installer (#10350) 
* Change to oneapi offline installer

* Fixes

* Add "call"

* Fixes
 2024-03-08 19:24:00 +08:00
WeiguangHan
db00e79cdf LLM: add user guide for benchmarking (#10284) 
* add user guide for benchmarking

* change the name and place of the benchmark user guide

* resolve some comments

* resolve new comments

* modify some typo

* resolve some new comments

* modify some descriptions
 2024-03-07 18:50:29 +08:00
Yuwen Hu
fa69fed58f Small fixes to oneAPI link (#10339) 2024-03-07 09:56:04 +08:00
Yuwen Hu
566e9bbb36 [LLM Doc] Restructure (#10322) 
* Add quick link guide to sidebar

* Add QuickStart to TOC

* Update quick links in main page

* Hide some section in More for top nav bar

* Resturct FAQ sections

* Small fix
 2024-03-05 14:35:55 +08:00
Xin Qiu
58208a5883 Update FAQ document. (#10300) 
* Update install_gpu.md

* Update resolve_error.md

* Update README.md

* Update resolve_error.md

* Update README.md

* Update resolve_error.md
 2024-03-04 08:35:11 +08:00
Jason Dai
4cb4db618d Update WebUI quickstart (#10305) 2024-03-03 22:18:26 +08:00
Shengsheng Huang
1db20dd1d0 add warmup advice in quickstart (#10293) 2024-03-01 17:15:45 +08:00
Xin Qiu
509e206de0 update doc about gemma random and unreadable output. (#10297) 
* Update install_gpu.md

* Update README.md

* Update README.md
 2024-03-01 15:41:16 +08:00
Shengsheng Huang
90f2f82638 revise webui quickstart (#10287) 2024-03-01 10:04:21 +08:00
Cheen Hau, 俊豪
653cb500ed Add webUI quickstart (#10266) 
* Add webUI quickstart

* Add GPU driver install

* Move images to readthedocs assets
 2024-02-29 10:08:06 +08:00
Shengsheng Huang
b88f447974 fix typo and change wording (#10254) 2024-02-27 13:40:51 +08:00
Shengsheng Huang
04a6b0040c Windows GPU Install Quickstart update (#10240) 
* Update install_windows_gpu.md

* Update install_windows_gpu.md

* Update install_windows_gpu.md

* fix numbering

* Update install_windows_gpu.md

* Update install_windows_gpu.md
 2024-02-27 13:14:39 +08:00
Zhicun
7c236e4c6d quick start for windows with gpu (#10221) 
* quick start for windows igpu

* Update install_windows_gpu.md

* Update install_windows_gpu.md

* Update install_windows_gpu.md

* Update install_windows_gpu.md

* Update install_windows_gpu.md

* Update install_windows_gpu.md

* update the demo.py

* Update install_windows_gpu.md

* Update install_windows_gpu.md

* fix image position typo

* Update install_windows_gpu.md

* update pip install command

---------

Co-authored-by: Shengsheng Huang <shannie.huang@gmail.com>
 2024-02-26 12:19:36 +08:00
Jason Dai
40584dec6d Update readme (#10214) 2024-02-23 11:42:16 +08:00
Yuwen Hu
94cb16fe40 [LLM] Small updates to Win GPU Install Doc (#10199) 
* Make Offline installer as default for win gpu doc for oneAPI

* Small other fixes
 2024-02-21 17:58:40 +08:00
hxsz1997
6e10d98a8d Fix some typos (#10175) 
* add llm-ppl workflow

* update the DATASET_DIR

* test multiple precisions

* modify nightly test

* match the updated ppl code

* add matrix.include

* fix the include error

* update the include

* add more model

* update the precision of include

* update nightly time and add more models

* fix the workflow_dispatch description, change default model of pr and modify the env

* modify workflow_dispatch language options

* modify options

* modify language options

* modeify workflow_dispatch type

* modify type

* modify the type of language

* change seq_len type

* fix some typos

* revert changes to stress_test.txt
 2024-02-20 14:14:53 +08:00
Cheen Hau, 俊豪
6952847f68 GPU install doc - add pip install oneAPI for windows (#10157) 
* Add instructions for pip install oneAPI for windows

* Improve clarity

* Format fix

* Fix

* Fix in runtime configuration
 2024-02-19 14:46:08 +08:00
Kai Huang
7400401706 Update gpu pip install oneapi doc (#10137) 
* fix link

* fix

* fix

* minor
 2024-02-09 11:27:40 +08:00
Cheen Hau, 俊豪
a7f9a13f6e Enhance gpu doc with PIP install oneAPI (#10109) 
* Add pip install oneapi instructions

* Fixes

* Add instruction for oneapi2023

* Runtime config

* Fixes

* Remove "Currently, oneAPI installed with .. "

* Add pip package version for oneAPI 2024

* Reviewer comments

* Fix errors
 2024-02-07 21:14:15 +08:00
binbin Deng
c1ec3d8921 LLM: update FAQ about too many open files (#10119) 2024-02-07 15:02:24 +08:00
Jason Dai
e2233dddef Update README (#10111) 2024-02-06 19:29:07 +08:00
Jason Dai
f440cb4fba Update Self-Speculative Decoding Readme (#10102) 2024-02-06 12:59:17 +08:00
binbin Deng
91cf9d41d0 LLM: add solutions of some frequently asked questions (#10068) 2024-02-04 09:28:20 +08:00
binbin Deng
4b92235bdb LLM: add initial FAQ page (#10055) 2024-02-01 09:43:39 +08:00
Shaojun Liu
2a0d65a009 Bump aiohttp from 3.9.0 to 3.9.2 to resolve security issues (#10030) 
* Bump aiohttp from 3.9.0 to 3.9.2 to resolve security issues

* update url

* remove aiohttp version from requirements.txt

* revert aiohttp to 3.9.0

* trigger tests

* revert
 2024-01-30 19:36:02 +08:00
Yuwen Hu
175027c90f Small clarification for windows installation guide (#10002) 2024-01-25 18:39:11 +08:00
Mingyu Wei
bc9cff51a8 LLM GPU Example Update for Windows Support (#9902) 
* Update README in LLM GPU Examples

* Update reference of Intel GPU

* add cpu_embedding=True in comment

* small fixes

* update GPU/README.md and add explanation for cpu_embedding=True

* address comments

* fix small typos

* add backtick for cpu_embedding=True

* remove extra backtick in the doc

* add period mark

* update readme
 2024-01-24 13:42:27 +08:00
Cheen Hau, 俊豪
e403e4a8b7 Add APT install instructions for oneAPI (#9875) 
* Add APT installer

* Include reviewer suggestions

* Add note - ensure matching version of oneAPI and pytorch/ipex

* Fix 'command line installer'

* Fix formatting. Address review comments

* Append ':' to '..by running the following commands'

* Fix formatting

* achieve -> archive
 2024-01-17 17:30:30 +08:00
Yuwen Hu
0aef35a965 [LLM] Improve LLM doc regarding windows gpu related info (#9880) 
* Improve runtime configuration for windows

* Add python 310/311 supports for wheel downloading

* Add troubleshooting for windows gpu

* Remove manually import ipex due to auto importer

* Add info regarding cpu_embedding=True on iGPU

* More info for Windows users

* Small updates to API docs

* Python style fix

* Remove tip for loading from saved optimize_model for now

* Updated based on comments

* Update win info for multi-intel gpus selection

* Small fix

* Small fix
 2024-01-11 14:37:16 +08:00
Cheen Hau, 俊豪
b2aa267f50 Enhance LLM GPU installation document (#9828) 
* Improve gpu install doc

* Add troubleshooting - setvars.sh not done properly.

* Further improvements

* 2024.x.x -> 2024.0

* Fixes

* Fix Install BigDL-LLM From Wheel : bigdl-llm[xpu_2.0]

* Remove "export USE_XETLA=OFF" for Max GPU
 2024-01-09 16:30:50 +08:00
Yuwen Hu
5ba1dc38d4 [LLM] Change default Linux GPU install option to PyTorch 2.1 (#9858) 
* Update default xpu to ipex 2.1

* Update related install ut support correspondingly

* Add arc ut tests for both ipex 2.0 and 2.1

* Small fix

* Diable ipex 2.1 test for now as oneapi 2024.0 has not beed installed on the test machine

* Update document for default PyTorch 2.1

* Small fix

* Small fix

* Small doc fixes

* Small fixes
 2024-01-08 17:16:17 +08:00
Kai Huang
62a3c0fc16 Fix quick build doc (#9853) 2024-01-08 14:26:34 +08:00
Yishuo Wang
5c6543e070 Reorganize LLM GPU installation document (#9777) 2024-01-03 13:53:05 +08:00
Xin Qiu
95c03765cb Update install_gpu.md, remove kernel 5.19 requirement. (#9757) 
* Update install_gpu.md

* Update install_gpu.md

* Update install_gpu.md

* Update install_gpu.md

* Update install_gpu.md

* Update install_gpu.md

* Update install_gpu.md

* Update install_gpu.md

* Update install_gpu.md

* Small fixes

---------

Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
 2023-12-22 16:17:56 +08:00
Yuwen Hu
c00a9144c4 [LLM] Small fixes to llm gpu installation guide (#9700) 2023-12-15 23:13:33 +08:00
Yuwen Hu
68d0c255fc [LLM] Update GPU installation doc (#9693) 
* Temp

* Add win 2.1 doc supports

* Reorg layout

* Fix based on comments

* Small fix
 2023-12-14 18:32:51 +08:00
Yining Wang
a04a027b4c Edit gpu doc (#9583) 
* harness: run llama2-7b

* harness: run llama2-7b

* harness: run llama2-7b

* harness: run llama2-7b

* edit-gpu-doc

* fix some format problem

* fix spelling problems

* fix evaluation yml

* delete redundant space

* fix some problems

* address comments

* change link
 2023-12-11 14:59:07 +08:00
Kai Huang
f7e596d85a Update doc (#9580) 
* update aiohttp in docs

* update doc
 2023-12-01 15:40:37 +08:00
Xin Qiu
32b37f3af7 Update gpu install.md (#9541) 
* Update install_gpu.md

* Update install_gpu.md
 2023-11-28 11:15:03 +08:00