huggingface / optimum-quanto 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 355 units with 3,091 lines of code in units (35.9% of code).

0 very complex units (0 lines of code)
0 complex units (0 lines of code)
9 medium complex units (361 lines of code)
27 simple units (519 lines of code)
319 very simple units (2,211 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 create() in optimum/quanto/tensor/weights/qbits.py	29	24	9
def latency() in bench/generation/metrics/latency.py	68	16	7
def from_pretrained() in optimum/quanto/models/diffusers_models.py	42	15	4
def from_pretrained() in optimum/quanto/models/transformers_models.py	36	14	4
def __torch_dispatch__() in optimum/quanto/tensor/weights/qbytes.py	43	14	5
def prepare_inputs_for_generation() in bench/generation/setup/awq.py	33	14	5
def run_benchmark() in bench/kernels/benchmark_w4a16.py	41	13	2
def main() in bench/generation/evaluate_configurations.py	50	12	0
def equal() in optimum/quanto/tensor/qtensor.py	19	11	2
def __torch_function__() in optimum/quanto/calibrate.py	14	10	4
def __torch_dispatch__() in optimum/quanto/tensor/weights/qbits.py	23	10	5
def cat() in optimum/quanto/tensor/activations/qbytes_ops.py	14	9	3
def _save_to_state_dict() in optimum/quanto/nn/qmodule.py	11	9	4
def timing() in bench/kernels/benchmark.py	43	9	3
def get_max_cuda_arch() in optimum/quanto/library/extensions/cuda/__init__.py	12	8	0
def qbytes_mm_impl_cuda() in optimum/quanto/library/qbytes_mm.py	15	8	3
def qbytes_mm_impl_cpu() in optimum/quanto/library/qbytes_mm.py	13	8	3
def bmm() in optimum/quanto/tensor/activations/qbytes_ops.py	10	8	3
def stack() in optimum/quanto/tensor/activations/qbytes_ops.py	14	8	3
def __torch_dispatch__() in optimum/quanto/tensor/weights/marlin/fp8/packed.py	21	8	5
def _get_perm() in optimum/quanto/tensor/weights/marlin/int4/packed.py	20	8	0
def __init__() in optimum/quanto/tensor/weights/tinygemm/qbits.py	23	8	9
def __torch_dispatch__() in optimum/quanto/tensor/weights/tinygemm/packed.py	20	8	5
def __torch_dispatch__() in optimum/quanto/tensor/weights/awq/packed.py	18	8	5
def _process_batch() in bench/generation/metrics/perplexity.py	20	8	7
void mul() in optimum/quanto/library/extensions/cuda/marlin/marlin_cuda.cpp	48	7	10
def qbytes_mm_impl_mps() in optimum/quanto/library/qbytes_mm.py	14	7	3
def main() in bench/kernels/benchmark.py	24	7	0
def calibrate_input() in optimum/quanto/calibrate.py	11	6	4
def run() in optimum/quanto/subpackage/commands/quantize.py	29	6	1
def lib() in optimum/quanto/library/extensions/extension.py	23	6	1
def group() in optimum/quanto/tensor/grouped.py	13	6	3
def forward() in optimum/quanto/tensor/qbits.py	17	6	2
def __torch_dispatch__() in optimum/quanto/tensor/packed.py	14	6	5
def __init__() in optimum/quanto/tensor/weights/marlin/int4/qbits.py	16	6	10
def __torch_dispatch__() in optimum/quanto/tensor/weights/marlin/int4/packed.py	19	6	5
def _save_pretrained() in optimum/quanto/models/transformers_models.py	12	5	2
def quantization_map() in optimum/quanto/quantize.py	9	5	1
def load_from_state_dict() in optimum/quanto/tensor/weights/qbytes.py	19	5	8
def __init__() in optimum/quanto/tensor/weights/marlin/fp8/qbits.py	16	5	8
def _get_perms() in optimum/quanto/tensor/weights/marlin/permutations.py	8	5	0
def load_from_state_dict() in optimum/quanto/tensor/weights/qbits.py	30	5	8
def unpack() in optimum/quanto/tensor/weights/tinygemm/packed.py	12	5	1
def __init__() in optimum/quanto/tensor/weights/awq/qbits.py	13	5	10
def gen_barchart() in bench/generation/gen_barchart.py	24	5	5
def main() in bench/generation/evaluate_model.py	46	5	0
def lt() in optimum/quanto/tensor/activations/qbytes_ops.py	8	4	3
def where() in optimum/quanto/tensor/activations/qbytes_ops.py	7	4	4
def ungroup() in optimum/quanto/tensor/grouped.py	11	4	3
def save_to_state_dict() in optimum/quanto/tensor/qtensor.py	10	4	4