* 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
* 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
* 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
* 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
* 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
