xingyuan li
bc4cdb07c9
Remove conda for llm workflow ( #8671 )
2023-08-04 12:09:42 +09:00
xingyuan li
610084e3c0
[LLM] Complete windows unittest ( #8611 )
...
* add windows nightly test workflow
* use github runner to run pr test
* model load should use lowbit
* remove tmp dir after testing
2023-08-03 14:48:42 +09:00
xingyuan li
769209b7f0
Chatglm unittest disable due to missing instruction ( #8650 )
2023-08-02 10:28:42 +09:00
xingyuan li
cdfbe652ca
[LLM] Add chatglm support for llm-cli ( #8641 )
...
* add chatglm build
* add llm-cli support
* update git
* install cmake
* add ut for chatglm
* add files to setup
* fix bug cause permission error when sf lack file
2023-08-01 14:30:17 +09:00
xingyuan li
7d45233825
fix trigger enable flag ( #8616 )
2023-07-26 10:53:03 +09:00
Song Jiaming
650b82fa6e
[LLM] add CausalLM and Speech UT ( #8597 )
2023-07-25 11:22:36 +08:00
xingyuan li
9c897ac7db
[LLM] Merge redundant code in workflow ( #8596 )
...
* modify workflow concurrency group
* Add build check to avoid repeated compilation
* remove redundant code
2023-07-25 12:12:00 +09:00
Yuwen Hu
bbde423349
[LLM] Add current Linux UT inference tests to nightly tests ( #8578 )
...
* Add current inference uts to nightly tests
* Change test model from chatglm-6b to chatglm2-6b
* Add thread num env variable for nightly test
* Fix urls
* Small fix
2023-07-21 13:26:38 +08:00
Yuwen Hu
2266ca7d2b
[LLM] Small updates to transformers int4 ut ( #8574 )
...
* Small fix to transformers int4 ut
* Small fix
2023-07-20 13:20:25 +08:00
Song Jiaming
411d896636
LLM first transformers UT ( #8514 )
...
* ut
* transformers api first ut
* name
* dir issue
* use chatglm instead of chatglm2
* omp
* set omp in sh
* source
* taskset
* test
* test omp
* add test
2023-07-20 10:16:27 +08:00
Yuwen Hu
df97d39e29
Change thread_num in Linux inference actions ( #8528 )
2023-07-14 10:46:03 +08:00
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
xingyuan li
04f2f04410
Add workflow_dispatch for llm unittest workflow ( #8485 )
2023-07-10 13:16:18 +08:00
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
Yuwen Hu
372c775cb4
[LLM] Change default runner for LLM Linux tests to the ones with AVX512 ( #8448 )
...
* Basic change for AVX512 runner
* Remove conda channel and action rename
* Small fix
* Small fix and reduce peak convert disk space
* Define n_threads based on runner status
* Small thread num fix
* Define thread_num for cli
* test
* Add self-hosted label and other small fix
2023-07-04 14:53:03 +08:00
Ruonan Wang
4be784a49d
LLM: add UT for starcoder (convert, inference) update examples and readme ( #8379 )
...
* first commit to add path
* update example and readme
* update path
* fix
* update based on comment
2023-06-27 12:12:11 +08:00
Shengsheng Huang
c113ecb929
[LLM] langchain bloom, UT's, default parameters ( #8357 )
...
* update langchain default parameters to align w/ api
* add ut's for llm and embeddings
* update inference test script to install langchain deps
* update tests workflows
---------
Co-authored-by: leonardozcm <changmin.zhao@intel.com>
2023-06-25 17:38:00 +08:00
binbin Deng
ab1a833990
LLM: add basic uts related to inference ( #8346 )
2023-06-19 10:25:51 +08:00
xingyuan li
daae7bd4e4
[LLM] Unittest for llm-cli ( #8343 )
...
* add llm-cli test shell
2023-06-16 17:42:24 +08:00
Yuwen Hu
1aa33d35d5
[LLM] Refactor LLM Linux tests ( #8349 )
...
* Small name fix
* Add convert nightly tests, and for other llm tests, use stable ckpt
* Small fix and ftp fix
* Small fix
* Small fix
2023-06-16 15:22:48 +08:00
Yuwen Hu
50dd9dd1c5
[LLM] Small improve for LLM base actions ( #8344 )
...
* Hide ftp url for now
* Small file name fix
2023-06-15 16:22:41 +08:00
