• 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 63 files with 9,236 lines of code.
• 0 very long files (0 lines of code)
• 6 long files (3,762 lines of code)
• 10 medium size files (3,155 lines of codeclsfd_ftr_w_mp_ins)
• 8 small files (1,019 lines of code)
• 39 very small files (1,300 lines of code)

There are 8 files with lines longer than 120 characters. In total, there are 14 long lines.

File	# lines	# units	# long lines
client.py in arctic_inference/embedding	181	1	3
cot.py in arctic_inference/dynasor	135	4	3
py_custom_ops.py in arctic_inference	44	2	2
benchmark_http.py in benchmark/embedding	246	2	2
attention_generic.cuh in csrc/custom_ops	54	-	1
naive_client.py in projects/dynasor	105	1	1
llama_swiftkv.py in arctic_inference/vllm/swiftkv	703	28	1
benchmark.py in benchmark/embedding	254	3	1