huggingface / optimum-tpu Conditional Complexity

Intro

Conditional complexity (also called cyclomatic complexity) is a term used to measure the complexity of software. The term refers to the number of possible paths through a program function. A higher value ofter means higher maintenance and testing costs (infosecinstitute.com).
Conditional complexity is calculated by counting all conditions in the program that can affect the execution path (e.g. if statement, loops, switches, and/or operators, try and catch blocks...).
Conditional complexity is measured at the unit level (methods, functions...).
Units are classified in four categories based on the measured McCabe index: 1-5 (simple units), 6-10 (medium complex units), 11-25 (complex units), 26+ (very complex units).

Learn more...

Conditional Complexity Overall

There are 352 units with 2,783 lines of code in units (44.2% of code).

0 very complex units (0 lines of code)
1 complex units (106 lines of code)
5 medium complex units (226 lines of code)
10 simple units (252 lines of code)
336 very simple units (2,199 lines of code)

Legend:

51+

26-50

11-25

6-10

1-5

Alternative Visuals

3D view of all units

Conditional Complexity per Extension

51+

26-50

11-25

6-10

1-5

Conditional Complexity per Logical Component

primary logical decomposition

51+

26-50

11-25

6-10

1-5

Most Complex Units

Top 50 most complex units

Unit	# lines	McCabe index	# params
def prefill() in text-generation-inference/server/text_generation_server/generator.py	106	33	2
def decode() in text-generation-inference/server/text_generation_server/generator.py	64	21	2
def decode() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	30	19	2
def warmup() in text-generation-inference/server/text_generation_server/generator.py	39	14	2
def prefill() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	51	12	2
def _mp_fn() in optimum/tpu/distributed_model.py	42	11	4
def warmup() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	36	9	2
def __call__() in text-generation-inference/server/text_generation_server/jetstream_pt_support/logits_process.py	20	8	2
def __call__() in optimum/tpu/generation/logits_process.py	22	8	2
def load_hook() in optimum/tpu/modeling_llama.py	31	8	4
def get_fsdp_training_args() in optimum/tpu/fsdp_v2.py	23	8	1
def load_hook() in optimum/tpu/modeling_mistral.py	31	8	4
def load_hook() in optimum/tpu/modeling_gemma.py	29	7	4
def _post_generate() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	31	6	4
def pad_to_shard() in text-generation-inference/server/text_generation_server/jetstream_pt_support/engine_loader.py	10	6	3
def forward() in optimum/tpu/xla_model_parallel.py	19	6	2
def select() in text-generation-inference/server/text_generation_server/jetstream_pt_support/token_selector.py	9	5	3
def _sample() in text-generation-inference/server/text_generation_server/jetstream_pt_support/token_selector.py	18	5	3
def __init__() in optimum/tpu/modeling_gemma.py	3	5	3
def _init_weights() in optimum/tpu/modeling_gemma.py	10	5	2
def __init__() in optimum/tpu/modeling_gemma.py	22	5	4
def __init__() in optimum/tpu/modeling_gemma.py	15	5	4
def forward() in optimum/tpu/modeling_llama.py	18	5	2
def __init__() in optimum/tpu/modeling_llama.py	3	5	3
def _init_weights() in optimum/tpu/modeling_llama.py	10	5	2
def __init__() in optimum/tpu/modeling_llama.py	19	5	4
def __init__() in optimum/tpu/modeling_llama.py	21	5	4
def forward() in optimum/tpu/xla_model_parallel.py	15	5	2
def __init__() in optimum/tpu/modeling_mistral.py	3	5	3
def _init_weights() in optimum/tpu/modeling_mistral.py	10	5	2
def __init__() in optimum/tpu/modeling_mistral.py	16	5	4
def __init__() in optimum/tpu/modeling_mistral.py	21	5	4
def clear() in text-generation-inference/server/text_generation_server/generator.py	5	4	2
def _clear() in text-generation-inference/server/text_generation_server/generator.py	5	4	2
def decode() in text-generation-inference/server/text_generation_server/generator.py	6	4	2
def apply_scaling() in text-generation-inference/server/text_generation_server/jetstream_pt_support/models/llama_model_exportable_hf.py	21	4	2
def _get_slot() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	5	4	1
def _cached_batch() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	8	4	3
def clear() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	5	4	2
def _clear() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	5	4	2
def load_model_info() in text-generation-inference/server/text_generation_server/jetstream_pt_support/engine_loader.py	22	4	1
def config_name_to_class() in optimum/tpu/modeling.py	12	4	1
def get_seq_length() in optimum/tpu/static_cache_xla.py	6	4	2
def _init_rope() in optimum/tpu/modeling_llama.py	26	4	1
def _unwrap_model() in optimum/tpu/fsdp_v2.py	8	4	1
def my_reduce() in optimum/tpu/xla_model_parallel.py	8	4	4
def my_gather() in optimum/tpu/xla_model_parallel.py	16	4	4
def forward() in optimum/tpu/xla_model_parallel.py	18	4	2
def _upad_input() in optimum/tpu/modeling_mistral.py	33	4	6
def __init__() in optimum/tpu/modeling_mistral.py	13	4	2