ColossalAI/colossalai/inference/quant/smoothquant/models
Xu Kai 450115bd0f [refactor] refactor gptq and smoothquant llama (#5012)
* refactor gptq and smoothquant llama

* fix import error

* fix linear import torch-int

* fix smoothquant llama import error

* fix import accelerate error

* fix bug

* fix import smooth cuda

* fix smoothcuda
2023-11-09 10:12:11 +08:00
..
__init__.py [refactor] refactor gptq and smoothquant llama (#5012) 2023-11-09 10:12:11 +08:00
base_model.py [refactor] refactor gptq and smoothquant llama (#5012) 2023-11-09 10:12:11 +08:00
linear.py [refactor] refactor gptq and smoothquant llama (#5012) 2023-11-09 10:12:11 +08:00
llama.py [refactor] refactor gptq and smoothquant llama (#5012) 2023-11-09 10:12:11 +08:00
parallel_linear.py [refactor] refactor gptq and smoothquant llama (#5012) 2023-11-09 10:12:11 +08:00