├── .gitignore ├── LICENSE ├── Notice ├── README.md ├── datautils.py ├── gptq.py ├── llama.py ├── modelutils.py ├── quant.py ├── requirements.txt ├── test_bigtable.sh ├── test_hessian_weighting.sh ├── test_kmeans_init.sh ├── test_m_step.sh ├── test_non_unif_no_opt.sh ├── test_scaling.sh ├── test_target_bitwidth.sh ├── uniform_quantizers.py └── vq_quant.py /.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/LICENSE -------------------------------------------------------------------------------- /Notice: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/Notice -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/README.md -------------------------------------------------------------------------------- /datautils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/datautils.py -------------------------------------------------------------------------------- /gptq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/gptq.py -------------------------------------------------------------------------------- /llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/llama.py -------------------------------------------------------------------------------- /modelutils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/modelutils.py -------------------------------------------------------------------------------- /quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/quant.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/requirements.txt -------------------------------------------------------------------------------- /test_bigtable.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/test_bigtable.sh -------------------------------------------------------------------------------- /test_hessian_weighting.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/test_hessian_weighting.sh -------------------------------------------------------------------------------- /test_kmeans_init.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/test_kmeans_init.sh -------------------------------------------------------------------------------- /test_m_step.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/test_m_step.sh -------------------------------------------------------------------------------- /test_non_unif_no_opt.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/test_non_unif_no_opt.sh -------------------------------------------------------------------------------- /test_scaling.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/test_scaling.sh -------------------------------------------------------------------------------- /test_target_bitwidth.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/test_target_bitwidth.sh -------------------------------------------------------------------------------- /uniform_quantizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/uniform_quantizers.py -------------------------------------------------------------------------------- /vq_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Qualcomm-AI-research/gptvq/HEAD/vq_quant.py --------------------------------------------------------------------------------