Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge public Intel Neural Compressor to fork (#93)
* modify 3.x ipex example structure (#1858) * modify 3.x ipex example structure Signed-off-by: Cheng, Zixuan <[email protected]> * add json path Signed-off-by: Cheng, Zixuan <[email protected]> * fix for sq Signed-off-by: Cheng, Zixuan <[email protected]> * minor fix Signed-off-by: Cheng, Zixuan <[email protected]> * Update run_clm_no_trainer.py * Update run_clm_no_trainer.py * Update run_clm_no_trainer.py * minor fix Signed-off-by: Cheng, Zixuan <[email protected]> * remove old files Signed-off-by: Cheng, Zixuan <[email protected]> * fix act_algo Signed-off-by: Cheng, Zixuan <[email protected]> --------- Signed-off-by: Cheng, Zixuan <[email protected]> Co-authored-by: xinhe <[email protected]> * Improve UT Branch Coverage for TF 3x (#1867) Signed-off-by: zehao-intel <[email protected]> * [3x] add recommendation examples (#1844) Signed-off-by: xin3he <[email protected]> * Add PT2E cv&llm example (#1853) Signed-off-by: Kaihui-intel <[email protected]> * Update SQ/WOQ status (#1869) Signed-off-by: Sun, Xuehao <[email protected]> Co-authored-by: chen, suyue <[email protected]> * Modify WOQ examples structure (#1866) Signed-off-by: Kaihui-intel <[email protected]> Signed-off-by: chensuyue <[email protected]> * update v2.6 release readme (#1871) Signed-off-by: chensuyue <[email protected]> * Limit numpy versions (#1874) Signed-off-by: Sun, Xuehao <[email protected]> * fix layer match (#1873) Signed-off-by: Kaihui-intel <[email protected]> Co-authored-by: Sun, Xuehao <[email protected]> * Enhance autotune to return the best `q_model` directly (#1875) Signed-off-by: yiliu30 <[email protected]> * Add op statistics dump for woq (#1876) Signed-off-by: Kaihui-intel <[email protected]> * rm cov (#1878) Signed-off-by: yiliu30 <[email protected]> * Add `set_local` support for static quant with pt2e (#1870) Signed-off-by: yiliu30 <[email protected]> * Update the Gaudi container example in the README (#1885) * support quant_lm_head arg in all WOQ configs (#1881) Signed-off-by: xin3he <[email protected]> * Fix sql injection for Neural Solution gRPC (#1879) Signed-off-by: Kaihui-intel <[email protected]> * Remove Gelu Fusion for TF Newapi (#1886) Signed-off-by: zehao-intel <[email protected]> * Refine HQQ UTs (#1888) Signed-off-by: yiliu30 <[email protected]> * tmp fix nas deps issue (#1896) Signed-off-by: chensuyue <[email protected]> * support auto_host2device on RTN and GPTQ(#1894) Signed-off-by: He, Xin3 <[email protected]> * remove import pdb (#1897) Signed-off-by: changwangss <[email protected]> * Port auto-detect absorb layers for TEQ (#1895) Signed-off-by: yiliu30 <[email protected]> * Remove 1x API (#1865) Signed-off-by: yiliu30 <[email protected]> Co-authored-by: chen, suyue <[email protected]> * remove neural insight CI (#1903) Signed-off-by: Sun, Xuehao <[email protected]> * fix bf16 symbolic_trace bug (#1892) Description: fix bf16 symbolic_trace bug, - cause abnormal recursive calling. - missing necessary attributes - By moving BF16 fallback ahead of quantization and removing bf16_symbolic_trace, we fix it. --------- Signed-off-by: xin3he <[email protected]> Co-authored-by: Sun, Xuehao <[email protected]> * update fp4_e2m1 mapping list (#1906) * update fp4_e2m1 mapping list * Update utility.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Add docstring for `common` module (#1905) Signed-off-by: yiliu30 <[email protected]> * support habana fp8 UT test in CI (#1909) Signed-off-by: chensuyue <[email protected]> * bump version into 3.0 (#1908) Signed-off-by: chensuyue <[email protected]> * implement `incbench` command for ease-of-use benchmark (#1884) # Description implement incbench command as entrypoint for ease-of-use benchmark automatically check numa/socket info and dump it with table for ease-of-understand supports both Linux and Windows platform add benchmark documents dump benchmark summary add benchmark UTs # General Use Cases incbench main.py: run 1 instance on NUMA:0. incbench --num_i 2 main.py: run 2 instances on NUMA:0. incbench --num_c 2 main.py: run multi-instances with 2 cores per instance on NUMA:0. incbench -C 24-47 main.py: run 1 instance on COREs:24-47. incbench -C 24-47 --num_c 4 main.py: run multi-instances with 4 COREs per instance on COREs:24-47. --------- Signed-off-by: xin3he <[email protected]> Co-authored-by: chen, suyue <[email protected]> * Get default config based on the auto-detect CPU type (#1904) Signed-off-by: yiliu30 <[email protected]> * Add export support for TEQ (#1910) Signed-off-by: yiliu30 <[email protected]> * update Gaudi CI baseline artifacts name (#1912) Signed-off-by: chensuyue <[email protected]> * Remove deprecated modules (#1872) Signed-off-by: chensuyue <[email protected]> * fix CI docker container clean up issue (#1917) Signed-off-by: chensuyue <[email protected]> * remove 1x docs (#1900) Signed-off-by: yiliu30 <[email protected]> * Add `save`/`load` support for HQQ (#1913) Signed-off-by: yiliu30 <[email protected]> Co-authored-by: chen, suyue <[email protected]> * Support PT2E save and load (#1918) Signed-off-by: Kaihui-intel <[email protected]> * implement TorchBaseConfig (#1911) Signed-off-by: xin3he <[email protected]> * update documentation for 3x API (#1923) Signed-off-by: chensuyue <[email protected]> Signed-off-by: xin3he <[email protected]> Signed-off-by: yiliu30 <[email protected]> * fix typo in architecture diagram (#1924) Signed-off-by: Huang, Tai <[email protected]> * Support woq Autotune (#1921) Signed-off-by: Kaihui-intel <[email protected]> * Support absorb dict for awq (#1920) Signed-off-by: Kaihui-intel <[email protected]> * Support LayerWise for RTN/GPTQ (#1883) Signed-off-by: Kaihui-intel <[email protected]> Co-authored-by: chensuyue <[email protected]> * update itrex ut test (#1929) Signed-off-by: chensuyue <[email protected]> * add docstring for torch.quantization and torch.utils (#1928) Signed-off-by: xin3he <[email protected]> * Integrate AutoRound v0.3 (#1925) Signed-off-by: Kaihui-intel <[email protected]> * Integrate AutoRound v0.3 to 2x (#1926) Signed-off-by: Kaihui-intel <[email protected]> * Enhance load_empty_model import (#1930) Signed-off-by: Kaihui-intel <[email protected]> * Add doc for client usage (#1914) Signed-off-by: yiliu30 <[email protected]> * remove peft version limit (#1933) Signed-off-by: chensuyue <[email protected]> * Support xpu for ipex static quant (#1916) Signed-off-by: violetch24 <[email protected]> * Support calib_func on TF 3x API (#1934) Signed-off-by: zehao-intel <[email protected]> * 3.X API installation update (#1935) Signed-off-by: chensuyue <[email protected]> * Fix unused pkgs import (#1931) Signed-off-by: Kaihui-intel <[email protected]> * Add docstring for PT2E and HQQ (#1937) Signed-off-by: yiliu30 <[email protected]> * add docstring for static quant and smooth quant (#1936) * add docstring for static quant and smooth quant Signed-off-by: violetch24 <[email protected]> * format fix Signed-off-by: violetch24 <[email protected]> * update scan path Signed-off-by: violetch24 <[email protected]> * Update utility.py --------- Signed-off-by: violetch24 <[email protected]> Co-authored-by: violetch24 <[email protected]> * Update Example for Pytorch 3x Mixed Precision (#1882) Signed-off-by: zehao-intel <[email protected]> * add read permission token (#1942) Signed-off-by: Huang, Tai <[email protected]> * Add docstring for WOQ&LayerWise (#1938) Signed-off-by: Kaihui-intel <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: xinhe <[email protected]> * add docstring for mx quant (#1932) Signed-off-by: Mengni Wang <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: xinhe <[email protected]> * Update for API 3.0 online doc (#1940) Co-authored-by: ZhangJianyu <[email protected]> * Refine Pytorch 3x Mixed Precision Example (#1946) Signed-off-by: zehao-intel <[email protected]> * Update AutoRound commit version (#1941) Signed-off-by: Kaihui-intel <[email protected]> * Update publish.yml (#1949) * Update publish.yml * Update publish.yml * Update publish.yml (#1950) * Update doc for client-usage and LWQ (#1947) Signed-off-by: yiliu30 <[email protected]> * Add Docstring for TF 3x API and Torch 3x Mixed Precision (#1944) Signed-off-by: zehao-intel <[email protected]> * Update Examples for TF 3x API (#1901) Signed-off-by: zehao-intel <[email protected]> * Complement UT of calibration function for TF 3x API (#1945) Signed-off-by: zehao-intel <[email protected]> * Enable yolov5 Example for TF 3x API (#1943) Signed-off-by: zehao-intel <[email protected]> * add ipex xpu example to 3x API (#1948) Signed-off-by: violetch24 <[email protected]> * update 3x torch installation (#1957) Signed-off-by: chensuyue <[email protected]> * Add save/load for pt2e example (#1927) Signed-off-by: Kaihui-intel <[email protected]> * Fix itrex qbits nf4/int8 training core dumped issue (#1954) Signed-off-by: Kaihui-intel <[email protected]> Signed-off-by: chensuyue <[email protected]> * new previous results could not find all raise issues in CI model test (#1958) Signed-off-by: chensuyue <[email protected]> * Set low_gpu_mem_usage=False for AutoRound Signed-off-by: Kaihui-intel <[email protected]> * Bump tensorflow version (#1961) Signed-off-by: dependabot[bot] <[email protected]> * fix docs link (#1959) Signed-off-by: chensuyue <[email protected]> * fix welcome.html link issue (#1962) Co-authored-by: ZhangJianyu <[email protected]> * replenish docstring (#1955) * replenish docstring Signed-off-by: xin3he <[email protected]> * update Quantizer API docstring Signed-off-by: xin3he <[email protected]> * Add docstring for auto accelerator (#1956) Signed-off-by: yiliu30 <[email protected]> * temporary remove torch/quantization and add it back after fp8 code is updated. * Update config.py --------- Signed-off-by: xin3he <[email protected]> Signed-off-by: yiliu30 <[email protected]> Co-authored-by: Yi Liu <[email protected]> * add SDXL model example to INC 3.x (#1887) * add SDXL model example to INC 3.x Signed-off-by: Cheng, Zixuan <[email protected]> * add evaluation script Signed-off-by: violetch24 <[email protected]> * add test script Signed-off-by: violetch24 <[email protected]> * minor fix Signed-off-by: violetch24 <[email protected]> * Update run_quant.sh * add iter limit Signed-off-by: violetch24 <[email protected]> * modify test script Signed-off-by: violetch24 <[email protected]> * update json Signed-off-by: chensuyue <[email protected]> * add requirements Signed-off-by: violetch24 <[email protected]> * Update run_benchmark.sh * Update sdxl_smooth_quant.py * minor fix Signed-off-by: violetch24 <[email protected]> --------- Signed-off-by: Cheng, Zixuan <[email protected]> Signed-off-by: violetch24 <[email protected]> Signed-off-by: chensuyue <[email protected]> Co-authored-by: violetch24 <[email protected]> Co-authored-by: chensuyue <[email protected]> * example update for 3.x ipex sq (#1902) Signed-off-by: violetch24 <[email protected]> * Fix `opt_125m_woq_gptq_int4_dq_ggml` issue (#1965) Signed-off-by: Kaihui-intel <[email protected]> * remove unnecessary CI (#1966) Signed-off-by: Sun, Xuehao <[email protected]> * Add version mapping between INC and Gaudi SW Stack (#1967) Signed-off-by: Huang, Tai <[email protected]> * Add 3.x readme (#1971) Signed-off-by: Sun, Xuehao <[email protected]> * Fix broken link in docs (#1969) Signed-off-by: Huang, Tai <[email protected]> * Cherry pick v1.17.0 (#1964) * [SW-184941] INC CI, CD and Promotion Change-Id: I60c420f9776e1bdab7bb9e02e5bcbdb6891bfe52 * [SW-183320]updated setup.py Change-Id: I592af89486cb1d9e0b5197521c428920197a9103 * [SW-177474] add HQT FP8 porting code Change-Id: I4676f13a5ed43c444f2ec68675cc41335e7234dd Signed-off-by: Zhou Yuwen <[email protected]> * [SW-189361] Fix white list extend Change-Id: Ic2021c248798fce37710d28014a6d59259c868a3 * [SW-191317] Raise exception according to hqt config object Change-Id: I06ba8fa912c811c88912987c11e5c12ef328348a * [SW-184714] Port HQT code into INC HQT lib content was copied as is under fp8_quant Tests were copied to 3.x torch location Change-Id: Iec6e1fa7ac4bf1df1c95b429524c40e32bc13ac9 * [SW-184714] Add internal folder to fp8 quant This is a folder used for experiments, not to be used by users Change-Id: I9e221ae582794e304e95392c0f37638f7bce69bc * [SW-177468] Removed unused code + cleanup Change-Id: I4d27c067e87c1a30eb1da9df16a16c46d092c638 * Fix errors in regression_detection Change-Id: Iee5318bd5593ba349812516eb5641958ece3c438 * [SW-187731] Save orig module as member of patched module This allows direct usage of the original module methods, which solves torch compile issue Change-Id: I464d8bd1bacdfc3cd1f128a67114e1e43f092632 * [SW-190899] Install packages according to configuration Change-Id: I570b490658f5d2c5399ba1db93f8f52f56449525 * [SW-184689] use finalize_calibration intrenaly for one step flow Change-Id: Ie0b8b426c951cf57ed7e6e678c86813fb2d05c89 * [SW-191945] align requirement_pt.txt in gerrit INC with Github INC Change-Id: If5c0dbf21bf989af37a8e29246e4f8760cd215ef Signed-off-by: xinhe3 <[email protected]> * [SW-192358] Remove HQT reference in INC Change-Id: Ic25f9323486596fa2dc6d909cd568a37ab84dd5e * [SW-191415] update fp8 maxAbs observer using torch.copy_ Change-Id: I3923c832f9a8a2b14e392f3f4719d233a457702f * [SW-184943] Enhance INC WOQ model loading - Support loading huggingface WOQ model - Abstract WeightOnlyLinear base class. Add INCWeightOnlyLinear and HPUWeighOnlyLinear subclasses - Load woq linear weight module by module - Save hpu format tensor to reuse it once load it again Change-Id: I679a42759b49e1f45f52bbb0bdae8580a23d0bcf * [SW-190303] Implement HPUWeightOnlyLinear class in INC Change-Id: Ie05c8787e708e2c3559dce24ef0758d6c498ac41 * [SW-192809] fix json_file bug when instantiating FP8Config class Change-Id: I4a715d0a706efe20ccdb49033755cabbc729ccdc Signed-off-by: Zhou Yuwen <[email protected]> * [SW-192931] align setup.py with github INC and remove fp8_convert Change-Id: Ibbc157646cfcfad64b323ecfd96b9bbda5ba9e2f Signed-off-by: xinhe3 <[email protected]> * [SW-192917] Update all HQT logic files with pre-commit check Change-Id: I119dc8578cb10932fd1a8a674a8bdbf61f978e42 Signed-off-by: xinhe3 <[email protected]> * update docstring Signed-off-by: yuwenzho <[email protected]> * add fp8 example and document (#1639) Signed-off-by: xinhe3 <[email protected]> * Update settings to be compatible with gerrit * enhance ut Signed-off-by: yuwenzho <[email protected]> * move fp8 sample to helloworld folder Signed-off-by: yuwenzho <[email protected]> * update torch version of habana docker Signed-off-by: xinhe3 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update readme demo Signed-off-by: xinhe3 <[email protected]> * update WeightOnlyLinear to INCWeightOnlyLinear Signed-off-by: xinhe3 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add docstring for FP8Config Signed-off-by: xinhe3 <[email protected]> * fix pylint Signed-off-by: xinhe3 <[email protected]> * update fp8 test scripts Signed-off-by: chensuyue <[email protected]> * delete deps Signed-off-by: chensuyue <[email protected]> * update container into v1.17.0 Signed-off-by: chensuyue <[email protected]> * update docker version Signed-off-by: xinhe3 <[email protected]> * update pt ut Signed-off-by: chensuyue <[email protected]> * add lib path Signed-off-by: chensuyue <[email protected]> * fix dir issue Signed-off-by: xinhe3 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update fp8 test scope Signed-off-by: chensuyue <[email protected]> * fix typo Signed-off-by: xinhe3 <[email protected]> * update fp8 test scope Signed-off-by: chensuyue <[email protected]> * update pre-commit-ci Signed-off-by: chensuyue <[email protected]> * work around for hpu Signed-off-by: xinhe3 <[email protected]> * fix UT Signed-off-by: xinhe3 <[email protected]> * fix parameter Signed-off-by: chensuyue <[email protected]> * omit some test Signed-off-by: chensuyue <[email protected]> * update main page example to llm loading Signed-off-by: xinhe3 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix autotune Signed-off-by: xinhe3 <[email protected]> --------- Signed-off-by: Zhou Yuwen <[email protected]> Signed-off-by: xinhe3 <[email protected]> Signed-off-by: yuwenzho <[email protected]> Signed-off-by: chensuyue <[email protected]> Co-authored-by: yan tomsinsky <[email protected]> Co-authored-by: Ron Ben Moshe <[email protected]> Co-authored-by: Uri Livne <[email protected]> Co-authored-by: Danny Semiat <[email protected]> Co-authored-by: smarkovichgolan <[email protected]> Co-authored-by: Dudi Lester <[email protected]> * update main page (#1973) Signed-off-by: chensuyue <[email protected]> * fix online doc search issue (#1975) Co-authored-by: ZhangJianyu <[email protected]> * bump main version into v3.1 (#1974) Signed-off-by: chensuyue <[email protected]> * update readme for fp8 (#1979) Signed-off-by: xinhe3 <[email protected]> * Skip some tests for torch 2.4 (#1981) Signed-off-by: yiliu30 <[email protected]> * Fix UT env and upgrade torch to 2.4.0 (#1978) Signed-off-by: Sun, Xuehao <[email protected]> * support gptq `true_sequential` and `quant_lm_head` (#1977) Signed-off-by: Kaihui-intel <[email protected]> * update installation and ci test for 3x api (#1991) Signed-off-by: chensuyue <[email protected]> * add hasattr check for torch fp8 dtype (#1985) Signed-off-by: xin3he <[email protected]> * add quantize, save, load function for transformers-like api (#1986) Signed-off-by: changwangss <[email protected]> * Update installation_guide.md (#1989) Correct typo in installation doc * update 3x pt binary build (#1992) Signed-off-by: chensuyue <[email protected]> * add per_channel_minmax (#1990) Signed-off-by: yiliu30 <[email protected]> * Remove the save of gptq config (#1993) Signed-off-by: Kaihui-intel <[email protected]> * Add recent publications (#1995) * add recent publications Signed-off-by: Huang, Tai <[email protected]> * update total count Signed-off-by: Huang, Tai <[email protected]> --------- Signed-off-by: Huang, Tai <[email protected]> * update docker image prune rules (#2003) Signed-off-by: chensuyue <[email protected]> * Support transformers-like api for woq quantization (#1987) Signed-off-by: Kaihui-intel <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Wang, Chang <[email protected]> * add INC_FORCE_DEVICE introduction (#1988) * add INC_FORCE_DEVICE introduction Signed-off-by: xin3he <[email protected]> * Update PyTorch.md * Update PyTorch.md * Update docs/source/3x/PyTorch.md Co-authored-by: Yi Liu <[email protected]> * rename to INC_TARGET_DEVICE Signed-off-by: xin3he <[email protected]> --------- Signed-off-by: xin3he <[email protected]> Co-authored-by: Yi Liu <[email protected]> * Replace FORCE_DEVICE with INC_TARGET_DEVICE [transformers] (#2005) Signed-off-by: Kaihui-intel <[email protected]> * enable auto_round format export (#2002) Signed-off-by: Zhang, Weiwei1 <[email protected]> * remove accelerate version in unit test (#2007) Signed-off-by: Sun, Xuehao <[email protected]> * add repack_awq_to_optimum_format function (#1998) Signed-off-by: changwangss <[email protected]> * Update auto_round requirements for transformers example (#2013) Signed-off-by: Kaihui-intel <[email protected]> * add pad_to_buckets in evaluation for hpu performance (#2011) * add pad_to_buckets in evaluation for hpu performance --------- Signed-off-by: xin3he <[email protected]> * Update model accuracy (#2006) Signed-off-by: Sun, Xuehao <[email protected]> * fix xpu device set weight and bias (#2010) Signed-off-by: changwangss <[email protected]> Co-authored-by: Sun, Xuehao <[email protected]> * Add transformers-like api doc (#2018) Signed-off-by: Kaihui-intel <[email protected]> * Adapt transformers 4.45.1 (#2019) Signed-off-by: Kaihui-intel <[email protected]> Co-authored-by: changwangss <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * add autoround EMNLP24 to pub list (#2014) Signed-off-by: Huang, Tai <[email protected]> * Fix transformers rtn layer-wise quant (#2008) Signed-off-by: Kaihui-intel <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Remove itrex dependency for 3x example (#2016) Signed-off-by: Kaihui-intel <[email protected]> Co-authored-by: Sun, Xuehao <[email protected]> * add transformers-like api link in readme (#2022) Signed-off-by: Huang, Tai <[email protected]> * Add woq examples (#1982) Signed-off-by: Kaihui-intel <[email protected]> Signed-off-by: Sun, Xuehao <[email protected]> Co-authored-by: Sun, Xuehao <[email protected]> * remove ITREX unit test CI (#2021) Signed-off-by: Sun, Xuehao <[email protected]> * Support quant procedure on XPU (#2026) Signed-off-by: Kaihui-intel <[email protected]> * Support generation search for transformers examples (#2029) Signed-off-by: Kaihui-intel <[email protected]> * Remove itrex dependency for 2x example (#2024) Signed-off-by: Kaihui-intel <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update the PT2E CV example (#2032) Signed-off-by: yiliu30 <[email protected]> * Cherry pick Habana software 1.18.0 update (#2025) Signed-off-by: xinhe3 <[email protected]> Signed-off-by: Yi Liu <[email protected]> Signed-off-by: Sun, Xuehao <[email protected]> Signed-off-by: chensuyue <[email protected]> Co-authored-by: yan tomsinsky <[email protected]> Co-authored-by: Uri Livne <[email protected]> Co-authored-by: Dudi Lester <[email protected]> Co-authored-by: Danny <[email protected]> Co-authored-by: Tomer Gafni <[email protected]> Co-authored-by: Eran Geva <[email protected]> Co-authored-by: Daniel Ohayon <[email protected]> Co-authored-by: Roi Tiefenbrunn <[email protected]> Co-authored-by: Kamil Felskowski <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * update gaudi version mapping table for v3.1 (#2030) Signed-off-by: Huang, Tai <[email protected]> Co-authored-by: chen, suyue <[email protected]> * fix broken link to FP8 example (#2034) Signed-off-by: Huang, Tai <[email protected]> * add back missing image (#2035) Signed-off-by: xin3he <[email protected]> * Add vlm examples, bugfix (#2012) * add VLM examples Signed-off-by: Zhang, Weiwei1 <[email protected]> * bugfix, add utils Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix docstring issues Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * bugfix Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refine examples Signed-off-by: Zhang, Weiwei1 <[email protected]> * fix scan issue Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refine shell Signed-off-by: Zhang, Weiwei1 <[email protected]> * refine scripts & requirements Signed-off-by: Zhang, Weiwei1 <[email protected]> * typofix Signed-off-by: Zhang, Weiwei1 <[email protected]> * refine docs Signed-off-by: Zhang, Weiwei1 <[email protected]> * set attn_implementation for Phi3-vision Signed-off-by: Zhang, Weiwei1 <[email protected]> * refine phi3 example Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix code coverage Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update config Signed-off-by: Sun, Xuehao <[email protected]> * refine shells, docs and example. enable qwen2-vl quantization Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix ci Signed-off-by: Zhang, Weiwei1 <[email protected]> * fix EOF error Signed-off-by: Sun, Xuehao <[email protected]> * update qwen dir Signed-off-by: Sun, Xuehao <[email protected]> * refine shell, add llama3.2 inference to doc Signed-off-by: Zhang, Weiwei1 <[email protected]> * bugfix Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * bugfix Signed-off-by: Zhang, Weiwei1 <[email protected]> * bugfix Signed-off-by: Zhang, Weiwei1 <[email protected]> * refine eval shell Signed-off-by: Zhang, Weiwei1 <[email protected]> * fix eval device issue Signed-off-by: Zhang, Weiwei1 <[email protected]> * refine eval dtype Signed-off-by: Zhang, Weiwei1 <[email protected]> --------- Signed-off-by: Zhang, Weiwei1 <[email protected]> Signed-off-by: Sun, Xuehao <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Sun, Xuehao <[email protected]> * remove autoround limit (#2036) Signed-off-by: Sun, Xuehao <[email protected]> * Adapt autoround format (#2038) Signed-off-by: Kaihui-intel <[email protected]> * remove transformers import from utility (#2045) * remove transformers import from utility Signed-off-by: Zhang, Weiwei1 <[email protected]> * bugfix Signed-off-by: Zhang, Weiwei1 <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fixtypos Signed-off-by: Zhang, Weiwei1 <[email protected]> --------- Signed-off-by: Zhang, Weiwei1 <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * add buckets setting for lm_eval (#2044) * add buckets setting for lm_eval Signed-off-by: xinhe3 <[email protected]> * clear graph cache to avoid OOM Signed-off-by: xinhe3 <[email protected]> --------- Signed-off-by: xinhe3 <[email protected]> Co-authored-by: xinhe3 <[email protected]> * Enhance example for HPU performance (#2043) * Enhance example for HPU performance Signed-off-by: xinhe3 <[email protected]> * Update run_clm_no_trainer.py * remove wikitext to avoid oom for llama2-7b bs=8 * remove wikitext Signed-off-by: xinhe3 <[email protected]> --------- Signed-off-by: xinhe3 <[email protected]> Co-authored-by: xinhe3 <[email protected]> * remove useless code in setup.py (#2046) * Update the default PT2E config (#2041) Signed-off-by: yiliu30 <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Support non-contiguous weight saving (#2049) Signed-off-by: Kaihui-intel <[email protected]> * fix GPTQ oom issue on HPU (#2042) * fix GPTQ oom issue on HPU Signed-off-by: xinhe3 <[email protected]> --------- Signed-off-by: xinhe3 <[email protected]> Co-authored-by: xinhe3 <[email protected]> * fix bug and update readme (#2051) * fix bug and update readme --------- Signed-off-by: xinhe3 <[email protected]> Co-authored-by: xinhe3 <[email protected]> * Support safetensors loading for layerwise (#2047) Signed-off-by: Kaihui-intel <[email protected]> * Enhance WOQ example Readme and help (#2053) Signed-off-by: Kaihui-intel <[email protected]> Co-authored-by: xinhe <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * improve optimum-habana available check (#2054) Signed-off-by: changwang <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Fixed CI IPEX version (#2061) Signed-off-by: Sun, Xuehao <[email protected]> * Update torch config kwargs (#2055) Signed-off-by: Kaihui-intel <[email protected]> * Support client `use_layer_wise` setting (#2048) Signed-off-by: Kaihui-intel <[email protected]> * Check autoround before import it (#2062) Signed-off-by: yiliu30 <[email protected]> * Delete fp8_quant/scripts/regression_detection directory (#2059) A missed change when cherry-picking Habana software 1.18.0 * Make PatchedVLLMKVCache resiliant to forward API changes (#2067) Change-Id: I33fad5c3e80e017099f300782809f24669765d42 Co-authored-by: Konrad Zawora <[email protected]> * Fix glm-4-9b oom issue on BMG Signed-off-by: Kaihui-intel <[email protected]> * Update recipes & Bump version to 3.2 (#2037) Signed-off-by: Sun, Xuehao <[email protected]> * Docs: Add customer defined calibration and update docker run (#2057) Signed-off-by: fengding <[email protected]> * Adapt torch and ipex 2.5 (#2066) Signed-off-by: Kaihui-intel <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Sun, Xuehao <[email protected]> * Enhance `TBB` check (#2068) Signed-off-by: yiliu30 <[email protected]> * Fix the PT2E UT (#2071) Signed-off-by: yiliu30 <[email protected]> * Support gptq layerwise on client (#2069) Signed-off-by: Kaihui-intel <[email protected]> * Adapt autoround v0.4 (#2073) Signed-off-by: Kaihui-intel <[email protected]> * Ensure that mul operators with shared initializer will not be absorbed in SmoothQuant (#2063) Signed-off-by: duansheng.liu <[email protected]> * Integrate AutoRound v0.4 [3x] (#2072) Signed-off-by: Kaihui-intel <[email protected]> Signed-off-by: Zhang, Weiwei1 <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Update CI framework versions and README badge for release 3.1.1 (#2058) Signed-off-by: Sun, Xuehao <[email protected]> * Remove the examples force required torch 1.13.1 (#2074) * remove alexnet_fashion_mnist notebook Signed-off-by: chensuyue <[email protected]> * remove rnnt in pytorch examples Signed-off-by: chensuyue <[email protected]> --------- Signed-off-by: chensuyue <[email protected]> * Fix truthfulqa task evaluation issue Signed-off-by: Kaihui-intel <[email protected]> * Add required library for ONNX example (#2078) * Add required library for ONNX example * Update requirements.txt * support autoround new API for VLM (#2075) Signed-off-by: Zhang, Weiwei1 <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * add import check (#2076) Signed-off-by: Sun, Xuehao <[email protected]> * Update utility.py (#2079) * Add gptq known issue (#2080) Signed-off-by: Kaihui-intel <[email protected]> * Fix sdxl `q_unet` config (#2081) Signed-off-by: Kaihui-intel <[email protected]> * Fixed the PT2E LLM example (#2082) Signed-off-by: yiliu30 <[email protected]> * fix dlrm when using incbench (#2084) Signed-off-by: Xin He <[email protected]> * add mapping for v3.2 (#2085) Signed-off-by: Huang, Tai <[email protected]> * [SW-192753] unify StaticQuantConfig and FP8Config Change-Id: I2fe09ba4c575810a5b130268d63b9eee926bdf08 Signed-off-by: xinhe3 <[email protected]> Signed-off-by: Xin He <[email protected]> * [SW-200124] Set Scalar as default scale format + Compatibility check Set ScaleFormat.SCALAR as default value of 'scale_format' Add reduction of 'scale_format' to 'CONST' value if using a PCQ scale_format or fake_quant Add test to show Scalar models aren't giving wrong outputs Fix fakequant test as it is problematic use of 'hpu_initialize' and should be fixed in SW-202697 Change-Id: I43ff4900e9e02ce7f50edcdbb19a28f4f615ef9c Signed-off-by: Xin He <[email protected]> * [SW-201679] support unit_scales for FuseMoE Change-Id: I02a63332bc09f1f6cdc3f133dd5f58829fcbad5a Signed-off-by: Xin He <[email protected]> * [SW-203698] Add log for converting prepared model Change-Id: I1464f11bbab27d9041c9ba6f448e5ae6fa43bc2d Signed-off-by: Mengni Wang <[email protected]> * [SW-199737] Measurement dump improvements Add _validate_dump_path to make sure dump dir is writable and backup measurements Change-Id: Ib64abe772b4c309bbf04de89477cde92ea47ade4 * [SW-203452] Fixing and temp skipping G3 unittests Change-Id: Iafa4a6a8577724bd8a86581bfe38d3269dab2ea2 Signed-off-by: Xin He <[email protected]> * [SW-195965] [GPTQ] INC load model loads model in fp32 only Change-Id: I597d19273786c0c169ad952ebe5a357274e358dc Signed-off-by: xinhe3 <[email protected]> * [SW-204016] Enable scale calculation with disk offload in INC -move calculating scales and quantization config info during the module patching loop as the weights there guaranteed to be on cpu. Change-Id: Ifb2de4e67c1b36c611dcc50b4cd14731b0336c50 * [SW-202614] Llama70b int4 gptq with INC load flow - getting host OOM Change-Id: Id1797371bb136502d89c4e8d17abcac1eaac4534 Signed-off-by: xinhe3 <[email protected]> * [SW-199823] [HQT] fix INC one-step quantization API workflow 1. fix test_fp8_static_quant.py::TestFP8StaticQuant::test_one_step_quant_cv failure by deepcoping forward function in common.py 2. fix config.py: Object of type dict_keys is not JSON serializable by converting it to list 3. fix download issue of UT by using local tiny_gptj.json Change-Id: I2ad3eac411e8fca9d88a021f6a5b9594e6c75ae9 Signed-off-by: xinhe3 <[email protected]> * [SW-202617] vllm mixtral MoE quant and measure using forward call Change-Id: I919f1e3597b6c95c3fc60db78ac9c0c06242b416 Signed-off-by: Xin He <[email protected]> * [SW-200092] Allow fsdpa and softmax to use scalar scales in INC Change-Id: Ieba4c74c18624fb0c5fce6321671d6f4eb2b8c93 Signed-off-by: Xin He <[email protected]> * [SW-205363] Update _load_state_dict_into_meta_model Update _load_state_dict_into_meta_model to compatible with Transformer 4.45 release Change-Id: Ib5d8ca777d38c7ae225b7174a886b333b6246ab1 Signed-off-by: Xin He <[email protected]> * [SW-184948] INC Q/DQ optimization, included conv2d, kv_cache, fsdpa, softmax and other operators. Change-Id: I920f8ad85b3493f1bd4bbe770533343e214fc2d1 Signed-off-by: changwang <[email protected]> Signed-off-by: Xin He <[email protected]> * [SW-198585] Fix typo causing PatchedVLLMKVCache error Change-Id: Iafdcc935f702bc4756e2ba89935becb3bc47a728 * [SW-199208] QDQ Refactor for Registering Patched Modules, Scaling Methods, and Observers 1. Extension APIs - `PatchedModuleBase` , `register_patched_module` - `ScalingMethodBase`, `register_scaling_methods` - `ObserverBase` ``register_observer`, `register_module_config_for_observer` Related files: - fp8_quant/patched_module_base.py - fp8_quant/observer_base.py - fp8_quant/_core/measure.py - test_register_apis.py 2. Device-agnostic Patching - Replaced `hpu` with `cur_accelerator.name()` - Replaced `htcore.mark_step()` with `cur_accelerator.synchronize()` - Removed `torch.device("hpu")` under observers and scaling method - Updated `hpu_accelerator.synchronize()` to `htcore.mark_step()` + `torch.hpu.synchronize()` Change-Id: I83c6de928a991ed2c1b3b434d372f49e095c38d3 Signed-off-by: Yi Liu <[email protected]> Co-authored-by: Mengni Wang <[email protected]> Signed-off-by: Xin He <[email protected]> * [SW-203389] scalars scales doesn't provide dtype attribution Change-Id: I4e40dc9b2d9cb65bc9e49571cd57a9ab030f5d7b Signed-off-by: xinhe3 <[email protected]> Signed-off-by: Xin He <[email protected]> * [SW-199208] fix ModuleInfo conversion issue Change-Id: Ib6c35e1623dda3e470e569defccd607a18b43312 * [SW-200168] Enable working with G2 HW scales on G3 Change-Id: I17f71540eb78e828f01f1a11c8b233d60951293e Signed-off-by: Xin He <[email protected]> * [SW-203389] fix get_scale_dtype to support PCQ scales Change-Id: I923ace405a0f751a2e5a0a3aadb7abbb401a6c44 * [SW-199719] reduce PCQ scales memory usage removed persistent full weight scales during PCQ quantization instead we are keeping only the input and output channels scales creating temporary full scale tensor on input quant Op call since the full scale tensor is the same size as the orig bf16 weight keeping all full scales persistently and the quntized weights will result a quantized model that uses more memory than the unquantized. Change-Id: Idc91c5ac8b9cfea2e2a3ad053cb4dc5464cff776 * [SW-206112] INC Q/DQ improvement - use Q/DQ ops Change-Id: Ib03ea8744aa2cca8b606754c45944840da1c3898 Signed-off-by: changwang <[email protected]> Signed-off-by: Xin He <[email protected]> * [SW-206693] Convert conv2d_fp8 params to list if necessary It's needed for the new approach to dynamic shapes in PT2.5. Change-Id: I8d5e620153970b210675459e3d6aecad8ca7cbde * [SW-207411] Add catch for OSError in _validate_dump_path Change-Id: I82bae184257f3da982877b3797f2ee8b40a573c8 * [SW-207328] remove accuracy check due to random issue Change-Id: Ifbd985c31c3755b6ab353ef8fa45e911dd75d688 Signed-off-by: xinhe3 <[email protected]> * [SW-207559] Folder layout refactoring and cleanup (phase 1) Change-Id: Ic9bffd2b7477d4530b4e2a5e411760a731efb84b Signed-off-by: Yi Liu <[email protected]> Signed-off-by: Xin He <[email protected]> * [SW-193262] INC multi device save/load CP design in fp8 (#5) Signed-off-by: Xin <[email protected]> Signed-off-by: Xin He <[email protected]> * [SW-208521] one-step quantization got double memory usage (#3) * [SW-208521] one-step quantization got double memory usage Signed-off-by: Xin <[email protected]> * [SW-208789] Support quantizing FP16 model to FP8 (#15) Since layer-wise is using memory mapping from disk, the model could be fp16 as it saved on disk, for example, llama2-7b. We need to add logic to support this case to make sure layer-wise works well. Signed-off-by: Xin He <[email protected]> * [SW-205959] Update _load_state_dict_into_meta_model for model with bias (#7) Signed-off-by: Xin <[email protected]> * [SW-208700] release bf16 model memory on HPU in one-step quantization (#14) Signed-off-by: Xin <[email protected]> Signed-off-by: Xin He <[email protected]> * [SW-197077] refactoring maxabs scales and adding arbitrary scales. (#12) * [SW-197077] refactoring maxabs scales and adding arbitrary scales. Change-Id: I2c35cf925b6b21983f1770db7d35e14f3d7d3e47 * [SW-197077] refactoring scale: fix atol Change-Id: I1c99ddd9ade679286988e7d8a96338b32c0ddc07 * [SW-197077] adding arbitrary scales * Skip autoround test for HPU (#19) Change-Id: I6dc9724389c16a05252370b9e09a1db80bc8d696 Signed-off-by: Yi Liu <[email protected]> Co-authored-by: Yi Liu <[email protected]> * [SW-199728] [DeepSpeed] Buffers initialized by model are not correct … (#16) * [SW-199728] [DeepSpeed] Buffers initialized by model are not correct after tensor parallel --------- Signed-off-by: Xin <[email protected]> Co-authored-by: Danny Semiat <[email protected]> Signed-off-by: Xin He <[email protected]> * [SW-208151] CD 1.19.0 - PT Docker - test_quantization No module named… (#33) * [SW-209256] fix GPTQ oom issue on HPU (#2042) (#20) * fix GPTQ oom issue on HPU (#2042) --------- Signed-off-by: Xin <[email protected]> Co-authored-by: xinhe3 <[email protected]> * [SW-208151] CD 1.19.0 - PT Docker - test_quantization No module named 'safetensors' Signed-off-by: Xin <[email protected]> --------- Signed-off-by: Xin <[email protected]> Co-authored-by: xinhe3 <[email protected]> Co-authored-by: Danny Semiat <[email protected]> * [SW-207748] Support Auto-round on HPU (#25) Signed-off-by: Yi Liu <[email protected]> Co-authored-by: Yi Liu <[email protected]> * [SW-209878] Increase threshold to avoid random error in test_layer_wise.py (#36) Signed-off-by: Xin He <[email protected]> Co-authored-by: Xin He <[email protected]> * [SW-207579] support load vLLM compatible FP8 model (#18) Support load vLLM compatible FP8 model, both G2 and G3, both single card and multi-cards. --------- Signed-off-by: changwang <[email protected]> * [SW-207451] Implement block-wise calibration for LLM (#41) * [SW-207451] Implement block-wise calibration for LLM --------- Signed-off-by: Xin <[email protected]> Co-authored-by: Xin He <[email protected]> Signed-off-by: Xin He <[email protected]> * [SW-208986] fix save&load bug (#40) * [SW-208986] fix save&load bug --------- Signed-off-by: Xin He <[email protected]> Co-authored-by: Xin He <[email protected]> * [SW-207748] Add Auto-round Example (#42) * add autoround hpu example Change-Id: Ibd537f4667c7c077160427722a5eca2c721aa5cd Signed-off-by: Yi Liu <[email protected]> * add requirements Change-Id: I77a95ec05e41247db9903e8622c31f05259ca365 Signed-off-by: Yi Liu <[email protected]> --------- Signed-off-by: Yi Liu <[email protected]> Co-authored-by: Yi Liu <[email protected]> Co-authored-by: Uri Livne <[email protected]> Signed-off-by: Xin He <[email protected]> * [SW-197077] fix bug (#47) * [SW-210541] loading for fused_sdpa requires additional amax scale (#51) Signed-off-by: Xin He <[email protected]> Co-authored-by: Xin He <[email protected]> * fix PatchedLoRACompatibleLinear init (#65) Signed-off-by: changwangss <[email protected]> * align files with v1.19.0 in fp8_quant folder Signed-off-by: Xin He <[email protected]> * fix missing SaveLoadFormat Signed-off-by: Xin He <[email protected]> * align and fix config after cherry-pick Signed-off-by: Xin He <[email protected]> * Implicit relative imports is abandoned Signed-off-by: Xin He <[email protected]> * fix config issue blocking CI Signed-off-by: Xin He <[email protected]> * remove synchronize for `pack_unpack_tensor_with_numpy` (#2070) * remove pack&unpack synchronize --------- Signed-off-by: Kaihui-intel <[email protected]> * stop auto-fix of pre-commit Signed-off-by: Xin He <[email protected]> * update autoround example for release test Signed-off-by: xin3he <[email protected]> * fix AWQ&TEQ loading due to input scale Signed-off-by: xin3he <[email protected]> * fix HQQ state_dict loading caused by [SW-195965] Signed-off-by: xin3he <[email protected]> * use per_channel as default config (#2091) Signed-off-by: yiliu30 <[email protected]> * workaround transformers issue in version 4.47.0 (#2092) * workaround transformers issue in version 4.47.0 Signed-off-by: xin3he <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Refactor FP8 pytest script (#2089) * Refactor FP8 pytest script --------- Signed-off-by: Sun, Xuehao <[email protected]> * update ci scan scope Signed-off-by: chensuyue <[email protected]> * [SW-210500] [Optimum-Habana] [Regression] [fp8] [INC] No generated text for llava models [llava-1.5-7b-hf] [llava-1.5-13b-hf ] (#54) Signed-off-by: Xin He <[email protected]> Co-authored-by: Xin He <[email protected]> * [SW-213236] resolve CPU mem issue in CI (#76) Signed-off-by: Xin He <[email protected]> Co-authored-by: Xin He <[email protected]> * recover pre-commit Signed-off-by: Xin He <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix `is_sharded` setting for loading quant model (#2094) Signed-off-by: Kaihui-intel <[email protected]> * fix error message for different python version (#2099) Signed-off-by: changwangss <[email protected]> * fix UT of RTN on HPU (#2098) Signed-off-by: xin3he <[email protected]> Signed-off-by: Sun, Xuehao <[email protected]> * fix device issue during calibration (#2100) Signed-off-by: Xin He <[email protected]> * fix woq example and update document for v1.19.0 (#2097) Signed-off-by: xin3he <[email protected]> * Refactor version import paths to common module (#2095) Signed-off-by: Sun, Xuehao <[email protected]> * update CI gaudi-docker to 1.19.0 (#2096) Signed-off-by: Sun, Xuehao <[email protected]> * fix device mapping issue of llama gptq (#2101) Signed-off-by: Xin He <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * remove fix_measurements.py. exists with a different name - postprocessing_vllm_measurements.py * fix merge * remove unused imported functions with wrong path * change envar requested value from 1 to true --------- Signed-off-by: Cheng, Zixuan <[email protected]> Signed-off-by: zehao-intel <[email protected]> Signed-off-by: xin3he <[email protected]> Signed-off-by: Kaihui-intel <[email protected]> Signed-off-by: Sun, Xuehao <[email protected]> Signed-off-by: chensuyue <[email protected]> Signed-off-by: yiliu30 <[email protected]> Signed-off-by: He, Xin3 <[email protected]> Signed-off-by: changwangss <[email protected]> Signed-off-by: Huang, Tai <[email protected]> Signed-off-by: violetch24 <[email protected]> Signed-off-by: Mengni Wang <[email protected]> Signed-off-by: dependabot[bot] <[email protected]> Signed-off-by: Zhou Yuwen <[email protected]> Signed-off-by: xinhe3 <[email protected]> Signed-off-by: yuwenzho <[email protected]> Signed-off-by: xinhe3 <[email protected]> Signed-off-by: Zhang, Weiwei1 <[email protected]> Signed-off-by: Yi Liu <[email protected]> Signed-off-by: changwang <[email protected]> Signed-off-by: fengding <[email protected]> Signed-off-by: duansheng.liu <[email protected]> Signed-off-by: Xin He <[email protected]> Signed-off-by: Mengni Wang <[email protected]> Signed-off-by: Xin <[email protected]> Signed-off-by: changwangss <[email protected]> Co-authored-by: Zixuan Cheng <[email protected]> Co-authored-by: xinhe <[email protected]> Co-authored-by: zehao-intel <[email protected]> Co-authored-by: Kaihui-intel <[email protected]> Co-authored-by: Sun, Xuehao <[email protected]> Co-authored-by: chen, suyue <[email protected]> Co-authored-by: Yi Liu <[email protected]> Co-authored-by: Dina Suehiro Jones <[email protected]> Co-authored-by: Wang, Chang <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Huang, Tai <[email protected]> Co-authored-by: violetch24 <[email protected]> Co-authored-by: Wang, Mengni <[email protected]> Co-authored-by: Neo Zhang Jianyu <[email protected]> Co-authored-by: ZhangJianyu <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: yan tomsinsky <[email protected]> Co-authored-by: Ron Ben Moshe <[email protected]> Co-authored-by: Uri Livne <[email protected]> Co-authored-by: Danny Semiat <[email protected]> Co-authored-by: smarkovichgolan <[email protected]> Co-authored-by: Dudi Lester <[email protected]> Co-authored-by: Yi Liu <[email protected]> Co-authored-by: WeiweiZhang1 <[email protected]> Co-authored-by: Tomer Gafni <[email protected]> Co-authored-by: Eran Geva <[email protected]> Co-authored-by: Daniel Ohayon <[email protected]> Co-authored-by: Roi Tiefenbrunn <[email protected]> Co-authored-by: Kamil Felskowski <[email protected]> Co-authored-by: xinhe3 <[email protected]> Co-authored-by: Konrad Zawora <[email protected]> Co-authored-by: feng-intel <[email protected]> Co-authored-by: duanshengliu <[email protected]> Co-authored-by: Mengni Wang <[email protected]> Co-authored-by: Jimin Ha <[email protected]> Co-authored-by: changwang <[email protected]> Co-authored-by: Yi Liu <[email protected]> Co-authored-by: Amadeusz Skrzypczak <[email protected]> Co-authored-by: Linoy Buchnik <[email protected]>
- Loading branch information
40 people
authored
Jan 7, 2025
1 parent
370cc68
commit be9adc2