Bibliography (8):

1. OPT: Open Pre-trained Transformer Language Models

2. Bigscience/bloom

3. GLM-130B: An Open Bilingual Pre-trained Model

4. https://github.com/NVIDIA/FasterTransformer

5. https://github.com/mit-han-lab/smoothquant

6. Wikipedia Bibliography:

   1. Quantization (signal processing)

   2. https://en.wikipedia.org/wiki/Integer_(computer_science)#Common_integral_data_types  :

      https://en.wikipedia.org/wiki/Integer_(computer_science)#Common_integral_data_types

   3. https://en.wikipedia.org/wiki/Basic_Linear_Algebra_Subprograms#Level_3  :

      https://en.wikipedia.org/wiki/Basic_Linear_Algebra_Subprograms#Level_3