transformers

8ebfd84f - Fully deprecate AutoGPTQ and AutoAWQ for GPT-QModel (#41567)

Fully deprecate AutoGPTQ and AutoAWQ for GPT-QModel (#41567) * fully deprecate autogptq * remove use_cuda and use_exllama toggles are fully deprecated in gptqmodel * format * add `act_group_aware` property * fix QUANT_TYPE assert Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * format * mod awq import * remove autoawq fuse support * remove remove autoawq.config fuse * cleanup * remove awq fuse test * fix import * use gptqmodel * cleanup * remove get_modules_to_fuse * mod require_auto_awq -> require_gptqmodel * convert vertion to checkpoint_format * check is_gptqmodel_available * revert modules_to_not_convert * pass bits, sym, desc_act * fix awqconfig init * fix wrong args * fix ipex * mod ipex version check * cleanup * fix awq_linear * remove self.exllama_config = exllama_config * cleanuo * Revert "cleanuo" This reverts commit 90019c6fc4f7a617ed9db482a42ecd1cd07f9108. * update is_trainable * cleanup * remove fused * call hf_select_quant_linear_v2() Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * Remove the "version" field from AwqConfig Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * Add torch_fused inferencefix test_gptq test Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * fix test_awq Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * fix test_awq Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * fix AwqConfig Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * call hf_select_quant_linear_v2() Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * remove auto_awq Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * fix typo Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * Compatible with legacy field: checkpoint_format Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * Compatible with legacy field: checkpoint_format Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * format Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * CLEANUP Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * update test_awq Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * fix get_modules_to_not_convert() Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * fix test_awq.py::AwqTest::test_quantized_model_exllama Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * Apply style fixes * test_awq.py added EXPECTED_OUTPUT Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * update test_gptq.py Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * fix test_awq.py::AwqTest::test_save_pretrained Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * use assertEqual() instead of assertTrue() Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * fix test_quantized_layers_class() Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * remove ExllamaV1 Test Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * format Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * fix get_modules_to_not_convert() Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * added EXPECTED_OUTPUT Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * remove ExllamaV1 Test Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * add AwqBackend.AUTO_TRAINABLE Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> * Update docs/source/zh/llm_tutorial.md Co-authored-by: Mohamed Mekkouri <93391238+MekkCyber@users.noreply.github.com> * revert temporarily fix Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> --------- Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai> Co-authored-by: ZX-ModelCloud <zx@modelcloud.ai> Co-authored-by: LRL2-ModelCloud <lrl2@modelcloud.ai> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: ZX-ModelCloud <165115237+ZX-ModelCloud@users.noreply.github.com> Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com> Co-authored-by: Mohamed Mekkouri <93391238+MekkCyber@users.noreply.github.com>