• File size measurements show the distribution of size of files.
• Files are classified in four categories based on their size (lines of code): 1-100 (very small files), 101-200 (small files), 201-500 (medium size files), 501-1000 (long files), 1001+(very long files).
• It is a good practice to keep files small. Long files may become "bloaters", code that have increased to such gargantuan proportions that they are hard to work with.

• There are 113 files with 8,601 lines of code.
• 1 very long files (1,150 lines of code)
• 2 long files (1,744 lines of code)
• 5 medium size files (1,198 lines of codeclsfd_ftr_w_mp_ins)
• 16 small files (1,954 lines of code)
• 89 very small files (2,555 lines of code)

There are 14 files with lines longer than 120 characters. In total, there are 99 long lines.

File	# lines	# units	# long lines
gemm_cuda.cu in optimum/quanto/library/extensions/cuda/awq/v2	968	-	79
marlin_cuda_kernel.cu in optimum/quanto/library/extensions/cuda/marlin	776	-	4
unpack.mm in optimum/quanto/library/extensions/mps	90	5	3
fp8_marlin.cu in optimum/quanto/library/extensions/cuda/marlin	1150	-	2
gemv_cuda.cu in optimum/quanto/library/extensions/cuda/awq/v2	280	-	2
transformers_models.py in optimum/quanto/models	105	9	1
diffusers_models.py in optimum/quanto/models	109	8	1
quantize.py in optimum/quanto/subpackage/commands	101	3	1
quantize.py in optimum/quanto/library	50	2	1
gptq_marlin_dtypes.cuh in optimum/quanto/library/extensions/cuda/marlin	60	-	1
gptq_marlin_repack.cu in optimum/quanto/library/extensions/cuda/marlin	271	-	1
gemm_cuda.h in optimum/quanto/library/extensions/cuda/awq/v2	2	-	1
dequantize.cuh in optimum/quanto/library/extensions/cuda/awq	67	-	1
extension.py in optimum/quanto/library/extensions	54	5	1