huggingface / optimum-tpu Unit Size

Intro

Unit size measurements show the distribution of size of units of code (methods, functions...).
Units are classified in four categories based on their size (lines of code): 1-20 (small units), 20-50 (medium size units), 51-100 (long units), 101+ (very long units).
You should aim at keeping units small (< 20 lines). Long units may become "bloaters", code that have increased to such gargantuan proportions that they are hard to work with.

Learn more...

Unit Size Overall

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

1 very long units (106 lines of code)
3 long units (174 lines of code)
23 medium size units (647 lines of code)
45 small units (638 lines of code)
280 very small units (1,218 lines of code)

Legend:

101+

51-100

21-50

11-20

1-10

Unit Size per Extension

101+

51-100

21-50

11-20

1-10

Unit Size per Logical Component

primary logical decomposition

101+

51-100

21-50

11-20

1-10

Alternative Visuals

3D view of all units

Longest Units

Top 50 longest 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 __init__() in optimum/tpu/modeling_mistral.py	59	3	5
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/generator.py	39	14	2
def warmup() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	36	9	2
def _upad_input() in optimum/tpu/modeling_gemma.py	34	3	6
def _upad_input() in optimum/tpu/modeling_llama.py	34	3	6
def _upad_input() in optimum/tpu/modeling_mistral.py	33	4	6
def _post_generate() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	31	6	4
def load_hook() in optimum/tpu/modeling_llama.py	31	8	4
def load_hook() in optimum/tpu/modeling_mistral.py	31	8	4
def decode() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	30	19	2
def load_hook() in optimum/tpu/modeling_gemma.py	29	7	4
def __init__() in optimum/tpu/modeling_llama.py	29	1	4
def __init__() in optimum/tpu/modeling_gemma.py	26	2	4
def _init_rope() in optimum/tpu/modeling_llama.py	26	4	1
def get_fsdp_training_args() in optimum/tpu/fsdp_v2.py	23	8	1
def _create_dummy_request() in text-generation-inference/server/text_generation_server/generator.py	22	1	2
def _create_dummy_request() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	22	1	2
def load_model_info() in text-generation-inference/server/text_generation_server/jetstream_pt_support/engine_loader.py	22	4	1
def __call__() in optimum/tpu/generation/logits_process.py	22	8	2
def __init__() in optimum/tpu/modeling_gemma.py	22	5	4
def apply_scaling() in text-generation-inference/server/text_generation_server/jetstream_pt_support/models/llama_model_exportable_hf.py	21	4	2
def __init__() in optimum/tpu/modeling_llama.py	21	5	4
def __init__() in optimum/tpu/modeling_mistral.py	21	5	4
def _token_encode() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	20	2	3
def __call__() in text-generation-inference/server/text_generation_server/jetstream_pt_support/logits_process.py	20	8	2
def _find_qparams() in optimum/tpu/xla_model_parallel.py	20	3	2
def __init__() in optimum/tpu/modeling_llama.py	19	5	4
def forward() in optimum/tpu/xla_model_parallel.py	19	6	2
def _sample() in text-generation-inference/server/text_generation_server/jetstream_pt_support/token_selector.py	18	5	3
def forward() in optimum/tpu/modeling_llama.py	18	5	2
def forward() in optimum/tpu/xla_model_parallel.py	18	4	2
def clear() in text-generation-inference/server/text_generation_server/generator.py	17	1	1
def assign() in text-generation-inference/server/text_generation_server/generator.py	16	1	4
def assign() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	16	1	4
def my_gather() in optimum/tpu/xla_model_parallel.py	16	4	4
def __init__() in optimum/tpu/modeling_mistral.py	16	5	4
def __init__() in optimum/tpu/modeling_gemma.py	15	5	4
def __init__() in optimum/tpu/xla_model_parallel.py	15	1	0
def forward() in optimum/tpu/xla_model_parallel.py	15	5	2
def clear() in text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py	14	1	1
def quantize() in optimum/tpu/xla_model_parallel.py	14	1	1
def quantize() in optimum/tpu/xla_model_parallel.py	14	1	1
def __init__() in optimum/tpu/modeling_mistral.py	14	1	4
def shard_weights() in text-generation-inference/server/text_generation_server/jetstream_pt_support/engine_loader.py	13	3	3
def forward() in optimum/tpu/modeling_gemma.py	13	1	0
def forward() in optimum/tpu/modeling_llama.py	13	1	0