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
Yuwen Hu
86f86a64a2
Small fixes to ipex 2.1 UT support ( #9848 )
2024-01-05 17:36:21 +08:00
Yuwen Hu
f25d23dfbf
[LLM] Add support for PyTorch 2.1 install in UT for GPU ( #9845 )
...
* Add support for ipex 2.1 install in UT and fix perf test
* Small fix
2024-01-05 16:13:18 +08:00
Chen, Zhentao
5de92090b3
try to fix deps installation of bigdl ( #9578 )
2023-12-01 15:25:47 +08:00
Yuwen Hu
d4b248fcd4
Add windows binary build label AVX_VNNI ( #9387 )
2023-11-08 18:13:35 +08:00
Yuwen Hu
dc70fc7b00
Update performance tests for dependency of bigdl-core-xe-esimd ( #9124 )
2023-10-10 19:32:17 +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
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
6a902b892e
[LLM] Add amx build step ( #8822 )
...
* add amx build step
2023-08-28 17:41:18 +09:00
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
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
bc4cdb07c9
Remove conda for llm workflow ( #8671 )
2023-08-04 12:09:42 +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
Xin Qiu
0714888705
build windows avx dll ( #8657 )
...
* windows avx
* add to actions
2023-08-03 02:06:24 +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
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
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
