Yuwen Hu
6d03d06ebb
Change runtime configurations for perf test on Windows ( #12705 )
...
* Change runtime configurations for perf test on Windows
* Small fix
2025-01-14 17:54:57 +08:00
Yuwen Hu
4bf93c66e8
Support install from source for PyTorch 2.6 RC in UT ( #12697 )
...
* Support install from source for PyTorch 2.6 RC in UT
* Remove expecttest
2025-01-10 16:44:18 +08:00
Yuwen Hu
c24741584d
Support PyTorch 2.6 RC perf test on Windows ( #12683 )
2025-01-09 18:17:23 +08:00
Yishuo Wang
a596f1ae5f
remove bigdl-llm test to fix langchain UT ( #12613 )
2024-12-26 10:17:25 +08:00
Yuwen Hu
6278cafc25
Add setuptools as a basic dependency ( #12563 )
...
* Add setuptools as a basic dependency
* Remove unnecessary requirements of setuptools in example/unit/nightly tests
2024-12-17 16:56:41 +08:00
Chu,Youcheng
acd77d9e87
Remove env variable BIGDL_LLM_XMX_DISABLED in documentation ( #12445 )
...
* fix: remove BIGDL_LLM_XMX_DISABLED in mddocs
* fix: remove set SYCL_CACHE_PERSISTENT=1 in example
* fix: remove BIGDL_LLM_XMX_DISABLED in workflows
* fix: merge igpu and A-series Graphics
* fix: remove set BIGDL_LLM_XMX_DISABLED=1 in example
* fix: remove BIGDL_LLM_XMX_DISABLED in workflows
* fix: merge igpu and A-series Graphics
* fix: textual adjustment
* fix: textual adjustment
* fix: textual adjustment
2024-11-27 11:16:36 +08:00
Ruonan Wang
6c5e8fc70c
fix again ( #12407 )
2024-11-15 11:57:58 +08:00
Ruonan Wang
fcc0fa7316
fix workflow again ( #12406 )
...
* fix again
* fix name
2024-11-15 11:01:35 +08:00
Ruonan Wang
548dec5185
fix npu pipeline workflow ( #12404 )
2024-11-15 10:01:33 +08:00
Yuwen Hu
923d696854
Small fix to LNL performance tests ( #12333 )
2024-11-05 13:24:58 +08:00
Yuwen Hu
e2adc974fd
Small fix to LNL performance tests ( #12331 )
2024-11-04 19:22:41 +08:00
Yuwen Hu
522cdf8e9d
Add initial support for LNL nightly performance tests ( #12326 )
...
* Add initial support for LNL nightly performance tests
* Small fix
2024-11-04 18:53:51 +08:00
Yuwen Hu
4644cb640c
Perf test further fix regarding trl version ( #12321 )
2024-11-04 11:01:25 +08:00
Ruonan Wang
8fe01c9e4d
[NPU pipeline] update cmake usage of pipeline ( #12320 )
2024-11-04 10:30:03 +08:00
Yuwen Hu
94ce447794
Fix performance tests regarding trl version ( #12319 )
...
* Fix performance tests regarding trl version
* Small fix
2024-11-04 09:42:18 +08:00
Yuwen Hu
d8c1287335
Further update for Windows dGPU performance tests ( #12244 )
2024-10-22 15:07:21 +08:00
Yuwen Hu
ac2dac857c
Disable 4k input test for now for Windows dGPU performance test ( #12239 )
2024-10-21 15:03:26 +08:00
Yuwen Hu
ea5154d85e
Further update to Windows dGPU perf test ( #12237 )
2024-10-21 10:27:16 +08:00
Yuwen Hu
da9270be2d
Further update to Windows dGPU perf test ( #12233 )
2024-10-18 23:20:17 +08:00
Yuwen Hu
5935b25622
Further update windows gpu perf test regarding results integrity check ( #12232 )
2024-10-18 18:15:13 +08:00
Yuwen Hu
ef659629f3
Small update to Windows dGPU perf test ( #12230 )
...
* Small update to Windows dGPU perf test
* Small fix
* Small fixes
* Remove unnecessary file
2024-10-18 16:39:59 +08:00
Yuwen Hu
9d7f42fd0f
Support manually trigger of dGPU perf test on Windows ( #12229 )
...
* Support manually trigger of dgpu perf test on Windows
* Small fix
* Small fix
* Small update
2024-10-18 15:38:21 +08:00
Yuwen Hu
b88c1df324
Add Llama 3.1 & 3.2 to Arc Performance test ( #12225 )
...
* Add llama3.1 and llama3.2 in arc perf (#12202 )
* Add llama3.1 and llama3.2 in arc perf
* Uninstall trl after arc test on transformers>=4.40
* Fix arc llama3 perf (#12212 )
* Fix pip uninstall
* Uninstall trl after test on transformers==4.43.1
* Fix llama3 arc perf (#12218 )
---------
Co-authored-by: Jin, Qiao <89779290+JinBridger@users.noreply.github.com>
2024-10-17 21:12:45 +08:00
Yuwen Hu
c9ac39fc1e
Add Llama 3.2 to iGPU performance test (transformers 4.45) ( #12209 )
...
* Add Llama 3.2 to iGPU Perf (#12200 )
* Add Llama 3.2 to iGPU Perf
* Downgrade accelerate after step
* Temporarily disable model for test
* Temporarily change ERRORLEVEL check (#12201 )
* Restore llama3.2 perf (#12206 )
* Revert "Temporarily change ERRORLEVEL check"
This reverts commit 909dbbc930ab4283737161a55bb32006e6ca1991.
* Revert "Temporarily disable model for test"
This reverts commit 95322dc3c6429aa836f21bda0b5ba8d9b48592f8.
---------
Co-authored-by: Jin, Qiao <89779290+JinBridger@users.noreply.github.com>
2024-10-15 17:44:46 +08:00
Shaojun Liu
724b2ae66d
add npu-level0 pipeline.dll to ipex-llm ( #12181 )
...
* add npu-level0 pipeline.dll to ipex-llm
* test
* update runner label
* fix
* update
* fix
* fix
2024-10-11 16:05:20 +08:00
Shaojun Liu
9b4fee8b5b
disable nightly release for finetune images ( #12070 )
2024-09-12 15:10:50 +08:00
Yuwen Hu
c94032f97e
Try to fix llamaindex ut again ( #12061 )
2024-09-11 12:11:04 +08:00
Yuwen Hu
94dade9aca
Fix UT of ipex_llm.llamaindex ( #12055 )
2024-09-11 09:58:43 +08:00
Shaojun Liu
75b19f8522
revert actions/download-artifact version to 3 ( #12017 )
2024-09-04 22:39:07 +08:00
Shaojun Liu
c6348a4666
Update action.yml ( #12016 )
2024-09-04 22:12:24 +08:00
Shaojun Liu
77cb348220
fix dependabot alerts ( #12006 )
...
* fix dependabot alerts
* update
2024-09-04 17:13:45 +08:00
Shaojun Liu
e5dc4e9123
disable outdated scheduled workflow ( #11915 )
2024-08-24 07:17:42 +08:00
Shaojun Liu
4cf640c548
update docker image tag to 2.2.0-SNAPSHOT ( #11904 )
2024-08-23 13:57:41 +08:00
Shaojun Liu
c5b51d41fb
Update pypi tag to 2.2.0.dev0 ( #11895 )
2024-08-22 16:48:09 +08:00
Yuwen Hu
bac98baab9
Make performance test install specific ipex-llm version from pypi ( #11892 )
2024-08-22 11:10:12 +08:00
Yuwen Hu
37106a877c
igpu performance test smal fix ( #11872 )
2024-08-21 03:09:14 +08:00
Yuwen Hu
0d58c2fdf9
Update performance test regarding updated default transformers==4.37.0 ( #11869 )
...
* Update igpu performance from transformers 4.36.2 to 4.37.0 (#11841 )
* upgrade arc perf test to transformers 4.37 (#11842 )
* fix load low bit com dtype (#11832 )
* feat: add mixed_precision argument on ppl longbench evaluation
* fix: delete extra code
* feat: upgrade arc perf test to transformers 4.37
* fix: add missing codes
* fix: keep perf test for qwen-vl-chat in transformers 4.36
* fix: remove extra space
* fix: resolve pr comment
* fix: add empty line
* fix: add pip install for spr and core test
* fix: delete extra comments
* fix: remove python -m for pip
* Revert "fix load low bit com dtype (#11832 )"
This reverts commit 6841a9ac8f#11846 )
* add transformers==4.36.2 for qwen-vl
* Small update
---------
Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
* fix: remove qwen-7b on core test (#11851 )
* fix: remove qwen-7b on core test
* fix: change delete to comment
---------
Co-authored-by: Jinhe Tang <jin.tang1337@gmail.com>
* replce filename (#11854 )
* fix: remove qwen-7b on core test
* fix: change delete to comment
* fix: replace filename
---------
Co-authored-by: Jinhe Tang <jin.tang1337@gmail.com>
* fix: delete extra comments (#11863 )
* Remove transformers installation for temp test purposes
* Small fix
* Small update
---------
Co-authored-by: Chu,Youcheng <70999398+cranechu0131@users.noreply.github.com>
Co-authored-by: Zhao Changmin <changmin.zhao@intel.com>
Co-authored-by: Jinhe Tang <jin.tang1337@gmail.com>
Co-authored-by: Zijie Li <michael20001122@gmail.com>
Co-authored-by: Chu,Youcheng <1340390339@qq.com>
2024-08-20 17:59:28 +08:00
Yuwen Hu
016e840eed
Fix performance tests ( #11802 )
...
* Fix performance tests
* Small fix
2024-08-15 01:37:01 +08:00
Shaojun Liu
e3c1dae619
Fix Windows Unit Test ( #11801 )
...
* Update llm_unit_tests.yml
* remove debug information
* Delete .github/actions/llm/cli-test-windows directory
2024-08-14 19:16:48 +08:00
Ruonan Wang
43cca3be27
fix gemma2 runtime error caused by sliding window ( #11788 )
...
* fix runtime error
* revert workflow
2024-08-14 10:43:33 +08:00
Yuwen Hu
ec184af243
Add gemma-2-2b-it and gemma-2-9b-it to igpu nightly performance test ( #11778 )
...
* add yaml and modify `concat_csv.py` for `transformers` 4.43.1 (#11758 )
* add yaml and modify `concat_csv.py` for `transformers` 4.43.1
* remove 4.43 for arc; fix;
* remove 4096-512 for 4.43
* comment some models
* Small fix
* uncomment models (#11777 )
---------
Co-authored-by: Ch1y0q <qiyue2001@gmail.com>
2024-08-13 15:39:56 +08:00
hxsz1997
8ef4caaf5d
add 3k and 4k input of nightly perf test on iGPU ( #11701 )
...
* Add 3k&4k input in workflow for iGPU (#11685 )
* add 3k&4k input in workflow
* comment for test
* comment models for accelarate test
* remove OOM models
* modify typo
* change test model (#11696 )
* reverse test models (#11700 )
2024-08-01 14:17:46 +08:00
Shaojun Liu
4d56ef5646
Fix openssf issue ( #11632 )
2024-07-22 14:14:28 +08:00
Yuwen Hu
2478e2c14b
Add check in iGPU perf workflow for results integrity ( #11616 )
...
* Add csv check for igpu benchmark workflow (#11610 )
* add csv check for igpu benchmark workflow
* ready to test
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
* Restore the temporarily removed models in iGPU-perf (#11615 )
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
---------
Co-authored-by: Xu, Shuo <100334393+ATMxsp01@users.noreply.github.com>
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-18 14:13:16 +08:00
Shaojun Liu
2b17536424
Fix python style check: update python version to 3.11 ( #11601 )
...
* Update python version to 3.11
2024-07-17 15:39:46 +08:00
Xu, Shuo
13a72dc51d
Test MiniCPM performance on iGPU in a more stable way ( #11573 )
...
* Test MiniCPM performance on iGPU in a more stable way
* small fix
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-12 17:07:41 +08:00
Xu, Shuo
1355b2ce06
Add model Qwen-VL-Chat to iGPU-perf ( #11558 )
...
* Add model Qwen-VL-Chat to iGPU-perf
* small fix
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-11 15:39:02 +08:00
Wang, Jian4
51f2effb05
Add xpu-tgi manually_build ( #11556 )
2024-07-11 10:35:40 +08:00
Yuwen Hu
8982ab73d5
Add Yi-6B and StableLM to iGPU perf test ( #11546 )
...
* Add transformer4.38.2 test to igpu benchmark (#11529 )
* add transformer4.38.1 test to igpu benchmark
* use transformers4.38.2 & fix csv name error in 4.38 workflow
* add model Yi-6B-Chat & remove temporarily most models
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
* filter some errorlevel (#11541 )
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
* Restore the temporarily removed models in iGPU-perf (#11544 )
* filter some errorlevel
* restore the temporarily removed models in iGPU-perf
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
---------
Co-authored-by: Xu, Shuo <100334393+ATMxsp01@users.noreply.github.com>
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-09 18:51:23 +08:00
Xu, Shuo
64cfed602d
Add new models to benchmark ( #11505 )
...
* Add new models to benchmark
* remove Qwen/Qwen-VL-Chat to pass the validation
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-08 10:35:55 +08:00
