├── README.md ├── convert_llama_weights_to_hf.py ├── datautils.py ├── gptq.py ├── llama.py ├── llama_inference.py ├── llama_inference_offload.py ├── modelutils.py ├── opt.py ├── quant.py ├── quant_cuda.cpp ├── quant_cuda_kernel.cu ├── requirements.txt ├── setup_cuda.py └── test_kernel.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/README.md -------------------------------------------------------------------------------- /convert_llama_weights_to_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/convert_llama_weights_to_hf.py -------------------------------------------------------------------------------- /datautils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/datautils.py -------------------------------------------------------------------------------- /gptq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/gptq.py -------------------------------------------------------------------------------- /llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/llama.py -------------------------------------------------------------------------------- /llama_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/llama_inference.py -------------------------------------------------------------------------------- /llama_inference_offload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/llama_inference_offload.py -------------------------------------------------------------------------------- /modelutils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/modelutils.py -------------------------------------------------------------------------------- /opt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/opt.py -------------------------------------------------------------------------------- /quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/quant.py -------------------------------------------------------------------------------- /quant_cuda.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/quant_cuda.cpp -------------------------------------------------------------------------------- /quant_cuda_kernel.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/quant_cuda_kernel.cu -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/requirements.txt -------------------------------------------------------------------------------- /setup_cuda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/setup_cuda.py -------------------------------------------------------------------------------- /test_kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oobabooga/GPTQ-for-LLaMa/HEAD/test_kernel.py --------------------------------------------------------------------------------