* remove include and language option, select the corresponding dataset based on the model name in Run
* change the nightly test time
* change the nightly test time of harness and ppl
* save the ppl result to json file
* generate csv file and print table result
* generate html
* modify the way to get parent folder
* update html in parent folder
* add llm-ppl-summary and llm-ppl-summary-html
* modify echo single result
* remove download fp16.csv
* change model name of PR
* move ppl nightly related files to llm/test folder
* reformat
* seperate make_table from make_table_and_csv.py
* separate make_csv from make_table_and_csv.py
* update llm-ppl-html
* remove comment
* add Download fp16.results
* add batch_size in stable version test
* add batch_size in excludes
* add excludes for batch_size
* fix ci
* triger regression test
* fix xpu version
* disable ci
* address kai's comment
---------
Co-authored-by: Ariadne <wyn2000330@126.com>
* ensure the result of daily arc perf test
* small fix
* small fix
* small fix
* small fix
* small fix
* small fix
* small fix
* small fix
* small fix
* small fix
* concat more csvs
* small fix
* revert some files
* Add uts for transformers api load_low_bit generation
* Small fixes
* Remove replit-code for CPU tests due to current load_low_bit issue on MPT
* Small change
* Small reorganization to llm unit tests on CPU
* Small fixes
* separate test_optimize_model api with disabled xmx
* delete test_optimize_model in test_transformers_api.py
* set env variable in .sh/ put back test_optimize_model
* unset env variable
* remove env setting in .py
* address errors in action
* remove import ipex
* lower tolerance
* add arc stable version regression test
* empty gpu mem between different models
* triger ci
* comment spr test
* triger ci
* address kai's comments and disable ci
* merge fp8 and int4
* disable ci
* Move 1024 test just after 32-32 test; and enable all model for 1024-128
* Make sure python output encoding in utf-8 so that redirect to txt can always be success
* Upload results to ftp
* Small fix
* Add test for 1024-128 and enable more tests for 512-64
* Fix date in results csv name to the time when the performance is triggered
* Small fix
* Small fix
* further fixes
* LLM: check csv and its corresponding yaml file
* run PR arc perf test
* modify the name of some variables
* execute the check results script in right place
* use cp to replace mv command
* resolve some comments
* resolve more comments
* revert the llm_performance_test.yaml file
* Change igpu win tests for ipex 2.1 and oneapi 2024.0
* Qwen model repo id updates; updates model list for 512-64
* Add .eval for win igpu all-in-one benchmark for best performance
* add exclude option in all-in-one perf test
* update arc-perf-test.yaml
* Exclude in_out_pairs in main function
* fix some bugs
* address Kai's comments
* define excludes at the beginning
* add bloomz:2048 to exclude
* trigger pr temparorily
* Saparate benchmark run for win igpu based in in-out pairs
* Rename fix
* Test workflow
* Small fix
* Skip generation of html for now
* Change back to nightly triggered
* Add supports for loading rwkv models using from_pretrained api
* Temporarily enable pr tests
* Add RWKV in tests and more in-out pairs
* Add rwkv for 512 tests
* Make iterations smaller
* Change back to nightly trigger
* Temp enable PR
* Enable tests for 256-64
* Try again 128-64
* Empty cache after each iteration for igpu benchmark scripts
* Try tests for 512
* change order for 512
* Skip chatglm3 and llama2 for now
* Separate tests for 512-64
* Small fix
* Further fixes
* Change back to nightly again
* Add support for win gpu benchmark with peak gpu memory monitoring
* Add win igpu tests
* Small fix
* Forward outputs
* Small fix
* Test and small fixes
* Small fix
* Small fix and test
* Small fixes
* Add tests for 512-64 and change back to nightly tests
* Small fix
* modify output_path as a directory
* schedule nightly at 21 on Friday
* add tasks and models for nightly
* add accuracy regression
* comment out if to test
* mixed fp4
* for test
* add missing delimiter
* remove comma
* fixed golden results
* add mixed 4 golden result
* add more options
* add mistral results
* get golden result of stable lm
* move nightly scripts and results to test folder
* add license
* add fp8 stable lm golden
* run on all available devices
* trigger only when ready for review
* fix new line
* update golden
* add mistral
* temporary stop other perf test
* Add framework for core performance test with one test model
* Small fix and add platform control
* Comment out lp for now
* Add missing ymal file
* Small fix
* Fix sed contents
* Small fix
* Small path fixes
* Small fix
* Add update to ftp
* Small upload fix
* add chatglm3-6b
* LLM: add model names
* Keep repo id same as ftp and temporary make baichuan2 first priority
* change order
* Remove temp if false and separate pr and nightly results
* Small fix
---------
Co-authored-by: jinbridge <2635480475@qq.com>
* add correctness test on arc for llama model
* modify layer name
* add falcon ut
* refactor and add ut for falcon model
* modify lambda positions and update docs
* replace loading pre input with last decodelayer output
* switch lower bound to single model instead of using the common one
* make the code implementation simple
* fix gpu action allocation memory issue
* add more models and skip runtime error
* upgrade transformers
* temporarily removed Mistral-7B-v0.1
* temporarily disable the upload of arc perf result
* Add test script and workflow for qlora fine-tuning
* Test fix export model
* Download dataset
* Fix export model issue
* Reduce number of training steps
* Rename script
* Correction
* Add gpu workflow and a transformers API inference test
* Set device-specific env variables in script instead of workflow
* Fix status message
---------
Co-authored-by: sgwhat <ge.song@intel.com>
* add ut for mistral model
* update
* fix model path
* upgrade transformers version for mistral model
* refactor correctness ut for mustral model
* refactor mistral correctness ut
* revert test_optimize_model back
* remove mistral from test_optimize_model
* add to revert transformers version back to 4.31.0
* Add test to check correctness of optimized model
* Refactor optimized model test
* Use models in llm-unit-test
* Use AutoTokenizer for bloom
* Print out each passed test
* Remove unused tokenizer from import
* add new API for optimize any pytorch models
* change test util name
* revise API and update UT
* fix python style
* update ut config, change default value
* change defaults, disable ut transcribe
* deprecate BigDLNativeTransformers and add specific LMEmbedding method
* deprecate and add LM methods for langchain llms
* add native params to native langchain
* new imple for embedding
* move ut from bigdlnative to casual llm
* rename embeddings api and examples update align with usage updating
* docqa example hot-fix
* add more api docs
* add langchain ut for starcoder
* support model_kwargs for transformer methods when calling causalLM and add ut
* ut fix for transformers embedding
* update for langchain causal supporting transformers
* remove model_family in readme doc
* add model_families params to support more models
* update api docs and remove chatglm embeddings for now
* remove chatglm embeddings in examples
* new refactor for ut to add bloom and transformers llama ut
* disable llama transformers embedding ut
