├── .gitignore ├── LICENSE ├── README.md ├── any_precision ├── LICENSE ├── __init__.py ├── analyzer │ ├── __init__.py │ ├── analyzer.py │ ├── architectures │ │ ├── gemma3.yaml │ │ ├── llama.yaml │ │ ├── mistral.yaml │ │ ├── opt.yaml │ │ ├── phi.yaml │ │ └── qwen3.yaml │ ├── splitted_models │ │ ├── __init__.py │ │ ├── gemma3.py │ │ ├── llama.py │ │ └── qwen3.py │ └── utils.py ├── evaluate │ ├── __init__.py │ ├── eval.py │ └── helpers │ │ ├── __init__.py │ │ ├── dataloader.py │ │ └── utils.py ├── modules │ ├── AnyPrecisionForCausalLM.py │ ├── AnyPrecisionLinear.py │ └── __init__.py └── quantization │ ├── __init__.py │ ├── activations.py │ ├── config.py │ ├── datautils.py │ ├── finetune_utils.py │ ├── full_datautils.py │ ├── full_main.py │ ├── full_utils_v1.py │ ├── full_utils_v2.py │ ├── gradients.py │ ├── layerwise_main.py │ ├── layerwise_quantize.py │ ├── main.py │ ├── pack.py │ ├── quantize.py │ └── utils.py ├── assets ├── demo.png ├── guidedquant-logo.png ├── objective-dark.png └── objective-light.png ├── full_nuq.py ├── inference ├── APLinear.py ├── LUTGEMMLinear.py ├── ap_gemv │ ├── anyprec.cu │ ├── anyprec.h │ ├── bindings.cpp │ ├── datatype.h │ ├── gemv.cu │ ├── gemv.h │ ├── install.sh │ ├── lutgemm.cu │ ├── lutgemm.h │ ├── setup.py │ └── typetraits.h ├── convert.sh ├── convert_pt.sh ├── generate.py ├── lib │ ├── __init__.py │ ├── algo │ │ ├── __init__.py │ │ ├── finetune.py │ │ └── ldlq.py │ ├── codebook │ │ ├── __init__.py │ │ └── bitshift.py │ ├── linear │ │ ├── __init__.py │ │ └── quantized_linear.py │ └── utils │ │ ├── __init__.py │ │ ├── data_utils.py │ │ ├── finetune.py │ │ ├── gptq_data_utils.py │ │ ├── graph_wrapper.py │ │ ├── kernel_check.py │ │ ├── kernel_decompress.py │ │ ├── math_utils.py │ │ ├── matmul_had.py │ │ ├── misc.py │ │ ├── shard_model.py │ │ └── unsafe_import.py ├── model.py ├── plugin.py ├── pt_llama_convert_fuse.py ├── qtip_convert_no_fuse.py ├── run.sh └── sqllm_llama_convert_fuse.py ├── inference_example.py ├── layerwise_nuq.py ├── qtip ├── .gitignore ├── LICENSE ├── README.md ├── assets │ └── qtip_overview.png ├── eval │ ├── eval_ppl.py │ ├── eval_zeroshot.py │ └── interactive_gen.py ├── exps │ ├── lufree_noft_ours.sh │ └── lufree_noft_qtip.sh ├── lib │ ├── __init__.py │ ├── algo │ │ ├── __init__.py │ │ ├── finetune.py │ │ └── ldlq.py │ ├── codebook │ │ ├── __init__.py │ │ └── bitshift.py │ ├── linear │ │ ├── __init__.py │ │ └── quantized_linear.py │ └── utils │ │ ├── __init__.py │ │ ├── data_utils.py │ │ ├── finetune.py │ │ ├── gptq_data_utils.py │ │ ├── graph_wrapper.py │ │ ├── kernel_check.py │ │ ├── kernel_decompress.py │ │ ├── math_utils.py │ │ ├── matmul_had.py │ │ ├── misc.py │ │ ├── shard_model.py │ │ └── unsafe_import.py ├── model │ ├── cache_utils.py │ └── llama.py ├── qtip-kernels │ ├── .gitignore │ ├── prof.sh │ ├── setup.py │ ├── src │ │ ├── Makefile │ │ ├── baseline.py │ │ ├── inference.cu │ │ ├── inference.h │ │ ├── qtip_torch.cu │ │ ├── test.cu │ │ └── wrapper.cpp │ └── test_decompress_matvec.py ├── quantize_llama │ ├── finetune_e2e_llama.py │ ├── hfize_llama.py │ ├── input_hessian_llama.py │ ├── manifest_model.py │ └── quantize_finetune_llama.py └── scripts │ └── download_hf.py ├── quantize.py ├── requirements.txt ├── run_eval.py ├── scripts ├── download_calibration.sh ├── run_lnq.sh └── run_sqllm.sh ├── setup.py └── spin_quant ├── .gitignore ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── LICENSE ├── README.md ├── SpinQuant.png ├── eval_utils ├── gptq_guided_utils.py ├── gptq_utils.py ├── main.py ├── modeling_llama.py └── rotation_utils.py ├── optimize_rotation.py ├── ptq.py ├── scripts ├── 10_optimize_rotation.sh ├── 11_optimize_rotation_fsdp.sh ├── 2_eval_ptq_guided_load_13b_g1.sh ├── 2_eval_ptq_guided_load_70b_g1.sh ├── 2_eval_ptq_guided_load_7b_g1.sh ├── 2_eval_ptq_guided_save_wikitext2_13b_g1.sh ├── 2_eval_ptq_guided_save_wikitext2_70b_g1.sh ├── 2_eval_ptq_guided_save_wikitext2_7b_g1.sh ├── 2_eval_ptq_load_13b.sh ├── 2_eval_ptq_load_70b.sh ├── 2_eval_ptq_load_7b.sh ├── 2_eval_ptq_save_13b.sh ├── 2_eval_ptq_save_70b.sh ├── 2_eval_ptq_save_7b.sh ├── 2_eval_spinquant_ppl.sh ├── 2_eval_spinquant_ppl_guided_g1.sh ├── 2_eval_spinquant_quant.sh ├── 2_eval_spinquant_quant_guided_g1.sh ├── 31_optimize_rotation_executorch.sh └── 32_eval_ptq_executorch.sh ├── train_utils ├── apply_r3_r4.py ├── fsdp_trainer.py ├── main.py ├── modeling_llama_quant.py ├── optimizer.py ├── quant_linear.py └── rtn_utils.py └── utils ├── convert_to_executorch.py ├── data_utils.py ├── eval_utils.py ├── fuse_norm_utils.py ├── hadamard_utils.py ├── model_utils.py ├── monkeypatch.py ├── process_args.py ├── quant_utils.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/README.md -------------------------------------------------------------------------------- /any_precision/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/LICENSE -------------------------------------------------------------------------------- /any_precision/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/__init__.py -------------------------------------------------------------------------------- /any_precision/analyzer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/__init__.py -------------------------------------------------------------------------------- /any_precision/analyzer/analyzer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/analyzer.py -------------------------------------------------------------------------------- /any_precision/analyzer/architectures/gemma3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/architectures/gemma3.yaml -------------------------------------------------------------------------------- /any_precision/analyzer/architectures/llama.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/architectures/llama.yaml -------------------------------------------------------------------------------- /any_precision/analyzer/architectures/mistral.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/architectures/mistral.yaml -------------------------------------------------------------------------------- /any_precision/analyzer/architectures/opt.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/architectures/opt.yaml -------------------------------------------------------------------------------- /any_precision/analyzer/architectures/phi.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/architectures/phi.yaml -------------------------------------------------------------------------------- /any_precision/analyzer/architectures/qwen3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/architectures/qwen3.yaml -------------------------------------------------------------------------------- /any_precision/analyzer/splitted_models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/splitted_models/__init__.py -------------------------------------------------------------------------------- /any_precision/analyzer/splitted_models/gemma3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/splitted_models/gemma3.py -------------------------------------------------------------------------------- /any_precision/analyzer/splitted_models/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/splitted_models/llama.py -------------------------------------------------------------------------------- /any_precision/analyzer/splitted_models/qwen3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/splitted_models/qwen3.py -------------------------------------------------------------------------------- /any_precision/analyzer/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/analyzer/utils.py -------------------------------------------------------------------------------- /any_precision/evaluate/__init__.py: -------------------------------------------------------------------------------- 1 | from . import helpers 2 | -------------------------------------------------------------------------------- /any_precision/evaluate/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/evaluate/eval.py -------------------------------------------------------------------------------- /any_precision/evaluate/helpers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /any_precision/evaluate/helpers/dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/evaluate/helpers/dataloader.py -------------------------------------------------------------------------------- /any_precision/evaluate/helpers/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/evaluate/helpers/utils.py -------------------------------------------------------------------------------- /any_precision/modules/AnyPrecisionForCausalLM.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/modules/AnyPrecisionForCausalLM.py -------------------------------------------------------------------------------- /any_precision/modules/AnyPrecisionLinear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/modules/AnyPrecisionLinear.py -------------------------------------------------------------------------------- /any_precision/modules/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/modules/__init__.py -------------------------------------------------------------------------------- /any_precision/quantization/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/__init__.py -------------------------------------------------------------------------------- /any_precision/quantization/activations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/activations.py -------------------------------------------------------------------------------- /any_precision/quantization/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/config.py -------------------------------------------------------------------------------- /any_precision/quantization/datautils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/datautils.py -------------------------------------------------------------------------------- /any_precision/quantization/finetune_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/finetune_utils.py -------------------------------------------------------------------------------- /any_precision/quantization/full_datautils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/full_datautils.py -------------------------------------------------------------------------------- /any_precision/quantization/full_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/full_main.py -------------------------------------------------------------------------------- /any_precision/quantization/full_utils_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/full_utils_v1.py -------------------------------------------------------------------------------- /any_precision/quantization/full_utils_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/full_utils_v2.py -------------------------------------------------------------------------------- /any_precision/quantization/gradients.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/gradients.py -------------------------------------------------------------------------------- /any_precision/quantization/layerwise_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/layerwise_main.py -------------------------------------------------------------------------------- /any_precision/quantization/layerwise_quantize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/layerwise_quantize.py -------------------------------------------------------------------------------- /any_precision/quantization/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/main.py -------------------------------------------------------------------------------- /any_precision/quantization/pack.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/pack.py -------------------------------------------------------------------------------- /any_precision/quantization/quantize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/quantize.py -------------------------------------------------------------------------------- /any_precision/quantization/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/any_precision/quantization/utils.py -------------------------------------------------------------------------------- /assets/demo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/assets/demo.png -------------------------------------------------------------------------------- /assets/guidedquant-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/assets/guidedquant-logo.png -------------------------------------------------------------------------------- /assets/objective-dark.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/assets/objective-dark.png -------------------------------------------------------------------------------- /assets/objective-light.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/assets/objective-light.png -------------------------------------------------------------------------------- /full_nuq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/full_nuq.py -------------------------------------------------------------------------------- /inference/APLinear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/APLinear.py -------------------------------------------------------------------------------- /inference/LUTGEMMLinear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/LUTGEMMLinear.py -------------------------------------------------------------------------------- /inference/ap_gemv/anyprec.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/ap_gemv/anyprec.cu -------------------------------------------------------------------------------- /inference/ap_gemv/anyprec.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/ap_gemv/anyprec.h -------------------------------------------------------------------------------- /inference/ap_gemv/bindings.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/ap_gemv/bindings.cpp -------------------------------------------------------------------------------- /inference/ap_gemv/datatype.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/ap_gemv/datatype.h -------------------------------------------------------------------------------- /inference/ap_gemv/gemv.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/ap_gemv/gemv.cu -------------------------------------------------------------------------------- /inference/ap_gemv/gemv.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/ap_gemv/gemv.h -------------------------------------------------------------------------------- /inference/ap_gemv/install.sh: -------------------------------------------------------------------------------- 1 | MAX_JOBS=8 CC=g++ pip install . 2 | -------------------------------------------------------------------------------- /inference/ap_gemv/lutgemm.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/ap_gemv/lutgemm.cu -------------------------------------------------------------------------------- /inference/ap_gemv/lutgemm.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/ap_gemv/lutgemm.h -------------------------------------------------------------------------------- /inference/ap_gemv/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/ap_gemv/setup.py -------------------------------------------------------------------------------- /inference/ap_gemv/typetraits.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/ap_gemv/typetraits.h -------------------------------------------------------------------------------- /inference/convert.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/convert.sh -------------------------------------------------------------------------------- /inference/convert_pt.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/convert_pt.sh -------------------------------------------------------------------------------- /inference/generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/generate.py -------------------------------------------------------------------------------- /inference/lib/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /inference/lib/algo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /inference/lib/algo/finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/algo/finetune.py -------------------------------------------------------------------------------- /inference/lib/algo/ldlq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/algo/ldlq.py -------------------------------------------------------------------------------- /inference/lib/codebook/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/codebook/__init__.py -------------------------------------------------------------------------------- /inference/lib/codebook/bitshift.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/codebook/bitshift.py -------------------------------------------------------------------------------- /inference/lib/linear/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/linear/__init__.py -------------------------------------------------------------------------------- /inference/lib/linear/quantized_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/linear/quantized_linear.py -------------------------------------------------------------------------------- /inference/lib/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/__init__.py -------------------------------------------------------------------------------- /inference/lib/utils/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/data_utils.py -------------------------------------------------------------------------------- /inference/lib/utils/finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/finetune.py -------------------------------------------------------------------------------- /inference/lib/utils/gptq_data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/gptq_data_utils.py -------------------------------------------------------------------------------- /inference/lib/utils/graph_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/graph_wrapper.py -------------------------------------------------------------------------------- /inference/lib/utils/kernel_check.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/kernel_check.py -------------------------------------------------------------------------------- /inference/lib/utils/kernel_decompress.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/kernel_decompress.py -------------------------------------------------------------------------------- /inference/lib/utils/math_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/math_utils.py -------------------------------------------------------------------------------- /inference/lib/utils/matmul_had.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/matmul_had.py -------------------------------------------------------------------------------- /inference/lib/utils/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/misc.py -------------------------------------------------------------------------------- /inference/lib/utils/shard_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/shard_model.py -------------------------------------------------------------------------------- /inference/lib/utils/unsafe_import.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/lib/utils/unsafe_import.py -------------------------------------------------------------------------------- /inference/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/model.py -------------------------------------------------------------------------------- /inference/plugin.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/plugin.py -------------------------------------------------------------------------------- /inference/pt_llama_convert_fuse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/pt_llama_convert_fuse.py -------------------------------------------------------------------------------- /inference/qtip_convert_no_fuse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/qtip_convert_no_fuse.py -------------------------------------------------------------------------------- /inference/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/run.sh -------------------------------------------------------------------------------- /inference/sqllm_llama_convert_fuse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference/sqllm_llama_convert_fuse.py -------------------------------------------------------------------------------- /inference_example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/inference_example.py -------------------------------------------------------------------------------- /layerwise_nuq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/layerwise_nuq.py -------------------------------------------------------------------------------- /qtip/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/.gitignore -------------------------------------------------------------------------------- /qtip/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/LICENSE -------------------------------------------------------------------------------- /qtip/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/README.md -------------------------------------------------------------------------------- /qtip/assets/qtip_overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/assets/qtip_overview.png -------------------------------------------------------------------------------- /qtip/eval/eval_ppl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/eval/eval_ppl.py -------------------------------------------------------------------------------- /qtip/eval/eval_zeroshot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/eval/eval_zeroshot.py -------------------------------------------------------------------------------- /qtip/eval/interactive_gen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/eval/interactive_gen.py -------------------------------------------------------------------------------- /qtip/exps/lufree_noft_ours.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/exps/lufree_noft_ours.sh -------------------------------------------------------------------------------- /qtip/exps/lufree_noft_qtip.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/exps/lufree_noft_qtip.sh -------------------------------------------------------------------------------- /qtip/lib/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /qtip/lib/algo/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /qtip/lib/algo/finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/algo/finetune.py -------------------------------------------------------------------------------- /qtip/lib/algo/ldlq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/algo/ldlq.py -------------------------------------------------------------------------------- /qtip/lib/codebook/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/codebook/__init__.py -------------------------------------------------------------------------------- /qtip/lib/codebook/bitshift.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/codebook/bitshift.py -------------------------------------------------------------------------------- /qtip/lib/linear/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/linear/__init__.py -------------------------------------------------------------------------------- /qtip/lib/linear/quantized_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/linear/quantized_linear.py -------------------------------------------------------------------------------- /qtip/lib/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/__init__.py -------------------------------------------------------------------------------- /qtip/lib/utils/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/data_utils.py -------------------------------------------------------------------------------- /qtip/lib/utils/finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/finetune.py -------------------------------------------------------------------------------- /qtip/lib/utils/gptq_data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/gptq_data_utils.py -------------------------------------------------------------------------------- /qtip/lib/utils/graph_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/graph_wrapper.py -------------------------------------------------------------------------------- /qtip/lib/utils/kernel_check.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/kernel_check.py -------------------------------------------------------------------------------- /qtip/lib/utils/kernel_decompress.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/kernel_decompress.py -------------------------------------------------------------------------------- /qtip/lib/utils/math_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/math_utils.py -------------------------------------------------------------------------------- /qtip/lib/utils/matmul_had.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/matmul_had.py -------------------------------------------------------------------------------- /qtip/lib/utils/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/misc.py -------------------------------------------------------------------------------- /qtip/lib/utils/shard_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/shard_model.py -------------------------------------------------------------------------------- /qtip/lib/utils/unsafe_import.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/lib/utils/unsafe_import.py -------------------------------------------------------------------------------- /qtip/model/cache_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/model/cache_utils.py -------------------------------------------------------------------------------- /qtip/model/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/model/llama.py -------------------------------------------------------------------------------- /qtip/qtip-kernels/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/qtip-kernels/.gitignore -------------------------------------------------------------------------------- /qtip/qtip-kernels/prof.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/qtip-kernels/prof.sh -------------------------------------------------------------------------------- /qtip/qtip-kernels/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/qtip-kernels/setup.py -------------------------------------------------------------------------------- /qtip/qtip-kernels/src/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/qtip-kernels/src/Makefile -------------------------------------------------------------------------------- /qtip/qtip-kernels/src/baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/qtip-kernels/src/baseline.py -------------------------------------------------------------------------------- /qtip/qtip-kernels/src/inference.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/qtip-kernels/src/inference.cu -------------------------------------------------------------------------------- /qtip/qtip-kernels/src/inference.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/qtip-kernels/src/inference.h -------------------------------------------------------------------------------- /qtip/qtip-kernels/src/qtip_torch.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/qtip-kernels/src/qtip_torch.cu -------------------------------------------------------------------------------- /qtip/qtip-kernels/src/test.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/qtip-kernels/src/test.cu -------------------------------------------------------------------------------- /qtip/qtip-kernels/src/wrapper.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/qtip-kernels/src/wrapper.cpp -------------------------------------------------------------------------------- /qtip/qtip-kernels/test_decompress_matvec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/qtip-kernels/test_decompress_matvec.py -------------------------------------------------------------------------------- /qtip/quantize_llama/finetune_e2e_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/quantize_llama/finetune_e2e_llama.py -------------------------------------------------------------------------------- /qtip/quantize_llama/hfize_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/quantize_llama/hfize_llama.py -------------------------------------------------------------------------------- /qtip/quantize_llama/input_hessian_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/quantize_llama/input_hessian_llama.py -------------------------------------------------------------------------------- /qtip/quantize_llama/manifest_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/quantize_llama/manifest_model.py -------------------------------------------------------------------------------- /qtip/quantize_llama/quantize_finetune_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/quantize_llama/quantize_finetune_llama.py -------------------------------------------------------------------------------- /qtip/scripts/download_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/qtip/scripts/download_hf.py -------------------------------------------------------------------------------- /quantize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/quantize.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/requirements.txt -------------------------------------------------------------------------------- /run_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/run_eval.py -------------------------------------------------------------------------------- /scripts/download_calibration.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/scripts/download_calibration.sh -------------------------------------------------------------------------------- /scripts/run_lnq.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/scripts/run_lnq.sh -------------------------------------------------------------------------------- /scripts/run_sqllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/scripts/run_sqllm.sh -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/setup.py -------------------------------------------------------------------------------- /spin_quant/.gitignore: -------------------------------------------------------------------------------- 1 | checkpoint* 2 | rotation/ 3 | logs 4 | cache_input_tokens 5 | *.txt 6 | -------------------------------------------------------------------------------- /spin_quant/CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /spin_quant/CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/CONTRIBUTING.md -------------------------------------------------------------------------------- /spin_quant/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/LICENSE -------------------------------------------------------------------------------- /spin_quant/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/README.md -------------------------------------------------------------------------------- /spin_quant/SpinQuant.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/SpinQuant.png -------------------------------------------------------------------------------- /spin_quant/eval_utils/gptq_guided_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/eval_utils/gptq_guided_utils.py -------------------------------------------------------------------------------- /spin_quant/eval_utils/gptq_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/eval_utils/gptq_utils.py -------------------------------------------------------------------------------- /spin_quant/eval_utils/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/eval_utils/main.py -------------------------------------------------------------------------------- /spin_quant/eval_utils/modeling_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/eval_utils/modeling_llama.py -------------------------------------------------------------------------------- /spin_quant/eval_utils/rotation_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/eval_utils/rotation_utils.py -------------------------------------------------------------------------------- /spin_quant/optimize_rotation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/optimize_rotation.py -------------------------------------------------------------------------------- /spin_quant/ptq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/ptq.py -------------------------------------------------------------------------------- /spin_quant/scripts/10_optimize_rotation.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/10_optimize_rotation.sh -------------------------------------------------------------------------------- /spin_quant/scripts/11_optimize_rotation_fsdp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/11_optimize_rotation_fsdp.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_guided_load_13b_g1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_guided_load_13b_g1.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_guided_load_70b_g1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_guided_load_70b_g1.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_guided_load_7b_g1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_guided_load_7b_g1.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_guided_save_wikitext2_13b_g1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_guided_save_wikitext2_13b_g1.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_guided_save_wikitext2_70b_g1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_guided_save_wikitext2_70b_g1.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_guided_save_wikitext2_7b_g1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_guided_save_wikitext2_7b_g1.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_load_13b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_load_13b.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_load_70b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_load_70b.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_load_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_load_7b.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_save_13b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_save_13b.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_save_70b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_save_70b.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_ptq_save_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_ptq_save_7b.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_spinquant_ppl.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_spinquant_ppl.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_spinquant_ppl_guided_g1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_spinquant_ppl_guided_g1.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_spinquant_quant.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_spinquant_quant.sh -------------------------------------------------------------------------------- /spin_quant/scripts/2_eval_spinquant_quant_guided_g1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/2_eval_spinquant_quant_guided_g1.sh -------------------------------------------------------------------------------- /spin_quant/scripts/31_optimize_rotation_executorch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/31_optimize_rotation_executorch.sh -------------------------------------------------------------------------------- /spin_quant/scripts/32_eval_ptq_executorch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/scripts/32_eval_ptq_executorch.sh -------------------------------------------------------------------------------- /spin_quant/train_utils/apply_r3_r4.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/train_utils/apply_r3_r4.py -------------------------------------------------------------------------------- /spin_quant/train_utils/fsdp_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/train_utils/fsdp_trainer.py -------------------------------------------------------------------------------- /spin_quant/train_utils/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/train_utils/main.py -------------------------------------------------------------------------------- /spin_quant/train_utils/modeling_llama_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/train_utils/modeling_llama_quant.py -------------------------------------------------------------------------------- /spin_quant/train_utils/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/train_utils/optimizer.py -------------------------------------------------------------------------------- /spin_quant/train_utils/quant_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/train_utils/quant_linear.py -------------------------------------------------------------------------------- /spin_quant/train_utils/rtn_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/train_utils/rtn_utils.py -------------------------------------------------------------------------------- /spin_quant/utils/convert_to_executorch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/utils/convert_to_executorch.py -------------------------------------------------------------------------------- /spin_quant/utils/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/utils/data_utils.py -------------------------------------------------------------------------------- /spin_quant/utils/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/utils/eval_utils.py -------------------------------------------------------------------------------- /spin_quant/utils/fuse_norm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/utils/fuse_norm_utils.py -------------------------------------------------------------------------------- /spin_quant/utils/hadamard_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/utils/hadamard_utils.py -------------------------------------------------------------------------------- /spin_quant/utils/model_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/utils/model_utils.py -------------------------------------------------------------------------------- /spin_quant/utils/monkeypatch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/utils/monkeypatch.py -------------------------------------------------------------------------------- /spin_quant/utils/process_args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/utils/process_args.py -------------------------------------------------------------------------------- /spin_quant/utils/quant_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/utils/quant_utils.py -------------------------------------------------------------------------------- /spin_quant/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/snu-mllab/GuidedQuant/HEAD/spin_quant/utils/utils.py --------------------------------------------------------------------------------