vllm-project/llm-compressor

Pattern Findings

The scanner identified 1256 distinct pattern matches across 22 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Hyper-Verbose Identifiers599 hits · 598 pts

Severity	File	Line	Snippet	Context
LOW	tests/testing_utils.py	381	def requires_compute_capability(major: int, minor: int = 0) -> pytest.MarkDecorator:	CODE
LOW	tests/test_testing_utils.py	7	def test_requires_compute_capability_skips_non_cuda_accelerator():	CODE
LOW	tests/sparsity/test_sparse.py	34	def test_module_quantization_info():	CODE
LOW	tests/sparsity/test_sparse.py	67	def test_module_sparsity_info():	CODE
LOW	tests/sparsity/test_module.py	25	def test_expand_special_targets():	CODE
LOW	tests/sparsity/test_module.py	69	def test_build_parameterized_layers(simple_model):	CODE
LOW	tests/sparsity/test_helpers.py	37	def test_tensors_to_device_cpu(tensors):	CODE
LOW	tests/sparsity/test_helpers.py	72	def test_tensors_to_device_cuda(tensors):	CODE
LOW	tests/sparsity/test_helpers.py	106	def test_tensors_to_precision_full_cpu(tensors):	CODE
LOW	tests/sparsity/test_helpers.py	140	def test_tensors_to_precision_half_cpu(tensors):	CODE
LOW	tests/sparsity/test_helpers.py	177	def test_tensors_to_precision_full_cuda(tensors):	CODE
LOW	tests/sparsity/test_helpers.py	215	def test_tensors_to_precision_half_cuda(tensors):	CODE
LOW	tests/sparsity/test_helpers.py	360	def test_tensors_module_forward(module, tensors, check_feat_lab_inp):	CODE
LOW	tests/sparsity/test_helpers.py	424	def test_tensors_module_forward_cuda(module, tensors, check_feat_lab_inp):	CODE
LOW	tests/sparsity/test_helpers.py	497	def test_tensor_sparsity_cuda(tensor, dim, expected_sparsity):	CODE
LOW	tests/sparsity/test_sparsity_helpers.py	56	def test_reduce_targets_and_ignores_into_lists(	CODE
LOW	tests/sparsity/test_sparsity_helpers.py	66	def _assert_list_contents_match(list1, list2):	CODE
LOW	tests/sparsity/constant/test_pytorch.py	144	def test_constant_pruning_pytorch_is_registered():	CODE
LOW	tests/sparsity/sparsegpt/test_consecutive_runs.py	26	def test_consecutive_runs_small(config, tmp_path):	CODE
LOW	tests/sparsity/sparsegpt/test_consecutive_runs.py	40	def test_consecutive_runs_gpu(config, tmp_path):	CODE
LOW	…sparsity/sparsegpt/test_mask_structure_preservation.py	50	def test_mask_structure_preserved(args_to_test, tmp_path):	CODE
LOW	tests/sparsity/sparsegpt/test_oneshot_with_modifier.py	15	def test_oneshot_with_modifier_object(tmp_path, config):	CODE
LOW	tests/sparsity/sparsegpt/test_base.py	11	def test_sparse_gpt_is_registered():	CODE
LOW	tests/sparsity/sparsegpt/test_base.py	36	def test_invalid_layerwise_recipes_raise_exceptions(sparsity, targets):	CODE
LOW	tests/sparsity/sparsegpt/test_base.py	50	def test_successful_layerwise_recipe():	CODE
LOW	tests/sparsity/sparsegpt/test_sparsegpt_completion.py	61	def test_oneshot_completion_gpu(config, tmp_path):	CODE
LOW	tests/sparsity/sparsegpt/test_sparsegpt_owl.py	15	def test_infer_owl_layer_sparsity():	CODE
LOW	tests/unit/test_logger.py	14	def test_default_logger_settings(capsys):	CODE
LOW	tests/unit/test_logger.py	26	def test_configure_logger_console_settings(capsys):	CODE
LOW	tests/unit/test_logger.py	38	def test_configure_logger_file_settings(tmp_path):	CODE
LOW	tests/unit/test_logger.py	52	def test_configure_logger_console_and_file(capsys, tmp_path):	CODE
LOW	tests/unit/test_logger.py	72	def test_environment_variable_override(monkeypatch, capsys, tmp_path):	CODE
LOW	tests/unit/test_logger.py	95	def test_environment_variable_disable_logging(monkeypatch, capsys):	CODE
LOW	tests/unit/test_logger.py	108	def test_environment_variable_enable_logging(monkeypatch, capsys):	CODE
LOW	tests/unit/core/test_state.py	7	def test_state_initialization():	CODE
LOW	tests/unit/core/test_state.py	20	def test_modified_state_initialization():	CODE
LOW	tests/unit/core/test_state.py	61	def test_state_sparsification_ready():	CODE
LOW	tests/tools/test_lint_cuda.py	17	def test_detect_torch_cuda_is_available():	CODE
LOW	tests/tools/test_lint_cuda.py	36	def test_detect_torch_cuda_stream():	STRING
LOW	tests/tools/test_lint_cuda.py	54	def test_detect_torch_cuda_event():	STRING
LOW	tests/tools/test_lint_cuda.py	72	def test_detect_torch_cuda_context_manager():	STRING
LOW	tests/tools/test_lint_cuda.py	92	def test_detect_memory_functions():	STRING
LOW	tests/tools/test_lint_cuda.py	126	def test_ignore_non_cuda_torch():	STRING
LOW	tests/tools/test_lint_cuda.py	164	def test_lint_file_integration():	STRING
LOW	tests/tools/test_lint_cuda.py	185	def test_no_duplicate_reports():	STRING
LOW	tests/llmcompressor/modifiers/conf.py	33	def trigger_modifier_for_epochs(self, modifier, num_epochs):	CODE
LOW	…sts/llmcompressor/modifiers/calibration/test_frozen.py	15	def test_set_module_for_calibration():	CODE
LOW	…/llmcompressor/modifiers/calibration/test_lifecycle.py	123	def test_static_weight_quantization(	CODE
LOW	…/llmcompressor/modifiers/calibration/test_lifecycle.py	219	def test_static_activation_quantization(	CODE
LOW	…/llmcompressor/modifiers/calibration/test_lifecycle.py	310	def test_static_attention_quantization(	CODE
LOW	…/llmcompressor/modifiers/calibration/test_observers.py	114	def test_observer_min_max_vals(name, kwargs, observed, exp_min_vals, exp_max_vals):	CODE
LOW	…/llmcompressor/modifiers/calibration/test_observers.py	134	def test_observe_skips_container_modules():	CODE
LOW	…sor/modifiers/utils/test_update_fused_layer_weights.py	80	def test_fused_observers_produce_identical_global_scale(module_class, layer_names):	CODE
LOW	…sor/modifiers/utils/test_update_fused_layer_weights.py	132	def test_unfused_observers_produce_different_global_scale(module_class, layer_names):	CODE
LOW	…sor/modifiers/utils/test_update_fused_layer_weights.py	159	def test_non_tensor_group_not_affected():	CODE
LOW	…sor/modifiers/utils/test_update_fused_layer_weights.py	180	def test_fused_recompute_after_weight_change():	CODE
LOW	tests/llmcompressor/modifiers/utils/test_hooks.py	67	def test_remove_hooks_parameterized():	CODE
LOW	tests/llmcompressor/modifiers/utils/test_hooks.py	132	def test_disable_hooks_composable():	CODE
LOW	…essor/modifiers/quantization/test_observer_defaults.py	4	def test_observer_defaults_are_based_on_scheme_location():	CODE
LOW	…essor/modifiers/quantization/test_observer_defaults.py	22	def test_scheme_observer_is_preserved():	CODE
539 more matches not shown…

Decorative Section Separators108 hits · 396 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/testing_utils.py	163	# -------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/testing_utils.py	165	# -------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/testing_utils.py	171	# -------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/testing_utils.py	173	# -------------------------------------------------------------------------	COMMENT
MEDIUM	tests/testing_utils.py	208	# -------------------------------------------------------------------------	COMMENT
MEDIUM	tests/testing_utils.py	210	# -------------------------------------------------------------------------	COMMENT
MEDIUM	tests/testing_utils.py	230	# -------------------------------------------------------------------------	COMMENT
MEDIUM	tests/testing_utils.py	232	# -------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/testing_utils.py	254	# -------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/testing_utils.py	256	# -------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/testing_utils.py	266	# -------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/testing_utils.py	268	# -------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/modifiers/pruning/reap/test_base.py	18	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/modifiers/pruning/reap/test_base.py	20	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/modifiers/pruning/reap/test_base.py	201	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/modifiers/pruning/reap/test_base.py	203	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/modifiers/pruning/reap/test_base.py	479	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/modifiers/pruning/reap/test_base.py	481	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/modifiers/pruning/reap/test_base.py	525	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/modifiers/pruning/reap/test_base.py	527	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/modifiers/pruning/reap/test_base.py	682	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/modifiers/pruning/reap/test_base.py	684	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…essor/transformers/compression/test_compression_ddp.py	48	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…essor/transformers/compression/test_compression_ddp.py	50	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…essor/transformers/compression/test_compression_ddp.py	171	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…essor/transformers/compression/test_compression_ddp.py	173	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…essor/transformers/compression/test_compression_ddp.py	346	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…essor/transformers/compression/test_compression_ddp.py	348	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…ansformers/smoothquant/test_smoothquant_distributed.py	22	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…ansformers/smoothquant/test_smoothquant_distributed.py	24	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…essor/entrypoints/model_free/test_dynamic_multi_gpu.py	84	# ── helpers ──────────────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	57	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	59	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	111	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	113	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	278	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	280	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	322	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	324	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	418	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	420	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	474	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/llmcompressor/observers/test_imatrix.py	476	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/observers/test_imatrix.py	14	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/observers/test_imatrix.py	16	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/observers/test_imatrix.py	160	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/llmcompressor/observers/test_imatrix.py	162	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	docs/scripts/zensical_gen_files.py	20	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	docs/scripts/zensical_gen_files.py	22	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	docs/scripts/zensical_gen_files.py	29	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	docs/scripts/zensical_gen_files.py	31	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	docs/scripts/zensical_gen_files.py	45	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	docs/scripts/zensical_gen_files.py	47	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	docs/scripts/zensical_gen_files.py	127	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	docs/scripts/zensical_gen_files.py	129	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	docs/scripts/zensical_gen_files.py	193	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	docs/scripts/zensical_gen_files.py	195	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	docs/scripts/zensical_gen_files.py	428	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	docs/scripts/zensical_gen_files.py	430	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…es/quantization_w8a8_int8/benchmark_smoothquant_ddp.py	30	# ---------------------------------------------------------------------------	COMMENT
48 more matches not shown…

Unused Imports190 hits · 190 pts

Severity	File	Line	Context
LOW	tests/llmcompressor/modifiers/pruning/reap/test_ddp.py	12	CODE
LOW	…essor/transformers/compression/test_compression_ddp.py	19	CODE
LOW	…ansformers/smoothquant/test_smoothquant_distributed.py	14	CODE
LOW	tests/test_timer/__init__.py	3	CODE
LOW	tests/examples/test_example_scripts.py	1	CODE
LOW	benchmarks/trace_subgraphs/benchmark.py	16	CODE
LOW	src/llmcompressor/__init__.py	12	CODE
LOW	src/llmcompressor/__init__.py	12	CODE
LOW	src/llmcompressor/__init__.py	12	CODE
LOW	src/llmcompressor/__init__.py	13	CODE
LOW	src/llmcompressor/__init__.py	13	CODE
LOW	src/llmcompressor/__init__.py	23	CODE
LOW	src/llmcompressor/__init__.py	23	CODE
LOW	src/llmcompressor/__init__.py	23	CODE
LOW	src/llmcompressor/__init__.py	23	CODE
LOW	src/llmcompressor/__init__.py	29	CODE
LOW	src/llmcompressor/__init__.py	29	CODE
LOW	src/llmcompressor/__init__.py	29	CODE
LOW	src/llmcompressor/modifiers/__init__.py	10	CODE
LOW	src/llmcompressor/modifiers/__init__.py	11	CODE
LOW	src/llmcompressor/modifiers/__init__.py	12	CODE
LOW	…pressor/modifiers/logarithmic_equalization/__init__.py	3	CODE
LOW	src/llmcompressor/modifiers/awq/__init__.py	40	CODE
LOW	src/llmcompressor/modifiers/awq/__init__.py	40	CODE
LOW	src/llmcompressor/modifiers/awq/__init__.py	40	CODE
LOW	src/llmcompressor/modifiers/awq/__init__.py	40	CODE
LOW	src/llmcompressor/modifiers/awq/__init__.py	40	CODE
LOW	src/llmcompressor/modifiers/quantization/__init__.py	3	CODE
LOW	src/llmcompressor/modifiers/quantization/__init__.py	4	CODE
LOW	…ressor/modifiers/quantization/group_size_validation.py	25	CODE
LOW	…ressor/modifiers/quantization/quantization/__init__.py	3	CODE
LOW	…ressor/modifiers/quantization/quantization/__init__.py	4	CODE
LOW	…/llmcompressor/modifiers/quantization/gptq/__init__.py	11	CODE
LOW	src/llmcompressor/modifiers/pruning/__init__.py	3	CODE
LOW	src/llmcompressor/modifiers/pruning/__init__.py	4	CODE
LOW	src/llmcompressor/modifiers/pruning/__init__.py	5	CODE
LOW	src/llmcompressor/modifiers/pruning/__init__.py	6	CODE
LOW	src/llmcompressor/modifiers/pruning/__init__.py	7	CODE
LOW	src/llmcompressor/modifiers/pruning/reap/__init__.py	3	CODE
LOW	…compressor/modifiers/pruning/utils/pytorch/__init__.py	3	CODE
LOW	…compressor/modifiers/pruning/utils/pytorch/__init__.py	4	CODE
LOW	src/llmcompressor/modifiers/pruning/wanda/__init__.py	3	CODE
LOW	…c/llmcompressor/modifiers/pruning/constant/__init__.py	3	CODE
LOW	…/llmcompressor/modifiers/pruning/magnitude/__init__.py	3	CODE
LOW	…/llmcompressor/modifiers/pruning/sparsegpt/__init__.py	3	CODE
LOW	src/llmcompressor/modifiers/autoround/__init__.py	3	CODE
LOW	src/llmcompressor/modifiers/autoround/__init__.py	4	CODE
LOW	src/llmcompressor/modifiers/qad/__init__.py	1	CODE
LOW	src/llmcompressor/modifiers/gptq/__init__.py	3	CODE
LOW	src/llmcompressor/modifiers/gptq/__init__.py	4	CODE
LOW	src/llmcompressor/modifiers/obcq/__init__.py	3	CODE
LOW	src/llmcompressor/modifiers/transform/__init__.py	3	CODE
LOW	src/llmcompressor/modifiers/transform/__init__.py	4	CODE
LOW	src/llmcompressor/modifiers/transform/__init__.py	5	CODE
LOW	src/llmcompressor/modifiers/transform/__init__.py	6	CODE
LOW	…lmcompressor/modifiers/transform/spinquant/__init__.py	3	CODE
LOW	src/llmcompressor/modifiers/transform/awq/__init__.py	3	CODE
LOW	src/llmcompressor/modifiers/transform/awq/__init__.py	4	CODE
LOW	src/llmcompressor/modifiers/transform/awq/__init__.py	5	CODE
LOW	src/llmcompressor/modifiers/transform/utils/__init__.py	1	CODE
130 more matches not shown…

Modern Structural Boilerplate112 hits · 114 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_timer/timer.py	9	__all__ = ["Timer"]	CODE
LOW	tests/test_timer/timer_utils.py	5	__all__ = ["log_time", "get_singleton_manager"]	CODE
LOW	src/llmcompressor/__init__.py	15	__all__ = [	CODE
LOW	src/llmcompressor/logger.py	44	__all__ = ["LoggerConfig", "configure_logger", "logger", "configure_distributed_logger"]	CODE
LOW	src/llmcompressor/modifiers/interface.py	6	__all__ = ["ModifierInterface"]	CODE
LOW	src/llmcompressor/modifiers/modifier.py	11	__all__ = ["Modifier"]	CODE
LOW	src/llmcompressor/modifiers/__init__.py	14	__all__ = [	CODE
LOW	src/llmcompressor/modifiers/factory.py	6	__all__ = ["ModifierFactory"]	CODE
LOW	…mcompressor/modifiers/logarithmic_equalization/base.py	5	__all__ = ["LogarithmicEqualizationModifier"]	CODE
LOW	src/llmcompressor/modifiers/awq/__init__.py	48	__all__ = [	CODE
LOW	src/llmcompressor/modifiers/utils/hooks.py	16	__all__ = ["HooksMixin"]	CODE
LOW	src/llmcompressor/modifiers/utils/pytorch_helpers.py	13	__all__ = [	CODE
LOW	…ressor/modifiers/quantization/group_size_validation.py	32	__all__ = [	CODE
LOW	src/llmcompressor/modifiers/quantization/calibration.py	21	__all__ = [	CODE
LOW	…ompressor/modifiers/quantization/quantization/mixin.py	55	__all__ = ["QuantizationMixin"]	CODE
LOW	…compressor/modifiers/quantization/quantization/base.py	19	__all__ = ["QuantizationModifier"]	CODE
LOW	src/llmcompressor/modifiers/pruning/helpers.py	17	__all__ = [	CODE
LOW	src/llmcompressor/modifiers/pruning/reap/utils.py	27	__all__ = [	CODE
LOW	src/llmcompressor/modifiers/pruning/reap/base.py	35	__all__ = ["REAPPruningModifier"]	CODE
LOW	…ressor/modifiers/pruning/utils/pytorch/mask_factory.py	9	__all__ = [	CODE
LOW	…mpressor/modifiers/pruning/utils/pytorch/layer_mask.py	9	__all__ = ["LayerParamMasking", "param_mask_name"]	CODE
LOW	src/llmcompressor/modifiers/pruning/wanda/base.py	19	__all__ = ["WandaPruningModifier"]	CODE
LOW	src/llmcompressor/modifiers/pruning/constant/base.py	11	__all__ = ["ConstantPruningModifier"]	CODE
LOW	src/llmcompressor/modifiers/pruning/magnitude/base.py	21	__all__ = ["MagnitudePruningModifier"]	CODE
LOW	…/llmcompressor/modifiers/pruning/sparsegpt/__init__.py	5	__all__ = ["SparseGPTModifier"]	CODE
LOW	src/llmcompressor/modifiers/pruning/sparsegpt/base.py	21	__all__ = ["SparseGPTModifier"]	CODE
LOW	src/llmcompressor/modifiers/autoround/utils.py	7	__all__ = [	CODE
LOW	src/llmcompressor/modifiers/autoround/base.py	38	__all__ = ["AutoRoundModifier", "fix_batch_if_needed"]	CODE
LOW	src/llmcompressor/modifiers/qad/__init__.py	3	__all__ = ["QADModifier"]	CODE
LOW	src/llmcompressor/modifiers/qad/base.py	26	__all__ = ["QADModifier"]	CODE
LOW	src/llmcompressor/modifiers/gptq/gptq_quantize.py	23	__all__ = [	CODE
LOW	src/llmcompressor/modifiers/gptq/base.py	45	__all__ = ["GPTQModifier"]	CODE
LOW	src/llmcompressor/modifiers/obcq/sgpt_base.py	7	__all__ = ["SparseGPTModifier"]	CODE
LOW	…pressor/modifiers/transform/spinquant/norm_mappings.py	5	__all__ = ["infer_norm_mapping_from_model"]	CODE
LOW	…lmcompressor/modifiers/transform/spinquant/mappings.py	5	__all__ = ["SpinQuantMapping", "infer_mapping_from_model"]	CODE
LOW	…compressor/modifiers/transform/awq/dynamic_mappings.py	26	__all__ = ["AWQ_DYNAMIC_MAPPING_REGISTRY", "get_layer_mappings_from_model"]	CODE
LOW	src/llmcompressor/modifiers/transform/awq/__init__.py	7	__all__ = [	CODE
LOW	src/llmcompressor/modifiers/transform/awq/base.py	52	__all__ = ["AWQModifier"]	CODE
LOW	src/llmcompressor/modifiers/transform/awq/base.py	281	def _set_resolved_mappings(self, model: Module) -> None:	CODE
LOW	src/llmcompressor/modifiers/transform/awq/base.py	389	def _setup_activation_cache_hooks(self) -> None:	CODE
LOW	src/llmcompressor/modifiers/transform/awq/mappings.py	5	__all__ = [	CODE
LOW	src/llmcompressor/modifiers/transform/utils/__init__.py	6	__all__ = [	CODE
LOW	src/llmcompressor/modifiers/transform/quip/base.py	22	__all__ = ["QuIPModifier"]	CODE
LOW	…or/modifiers/transform/smoothquant/dynamic_mappings.py	19	__all__ = ["SMOOTHQUANT_DYNAMIC_MAPPING_REGISTRY", "get_layer_mappings_from_model"]	CODE
LOW	…llmcompressor/modifiers/transform/smoothquant/utils.py	6	__all__ = [	CODE
LOW	…/llmcompressor/modifiers/transform/smoothquant/base.py	29	__all__ = ["SmoothQuantScale", "SmoothQuantMapping", "SmoothQuantModifier"]	CODE
LOW	src/llmcompressor/modifiers/smoothquant/__init__.py	23	__all__ = ["SmoothQuantModifier"]	CODE
LOW	src/llmcompressor/core/model_layer.py	12	__all__ = ["ModelParameterizedLayer"]	CODE
LOW	src/llmcompressor/core/session.py	19	__all__ = [	CODE
LOW	src/llmcompressor/core/__init__.py	22	__all__ = [	CODE
LOW	src/llmcompressor/core/session_functions.py	22	__all__ = [	CODE
LOW	src/llmcompressor/core/lifecycle.py	17	__all__ = ["CompressionLifecycle"]	CODE
LOW	src/llmcompressor/core/state.py	15	__all__ = ["State", "Data", "Hardware", "ModifiedState"]	CODE
LOW	src/llmcompressor/core/events/event.py	15	__all__ = [	CODE
LOW	src/llmcompressor/core/events/__init__.py	12	__all__ = ["Event", "EventType"]	CODE
LOW	src/llmcompressor/recipe/metadata.py	13	__all__ = [	CODE
LOW	src/llmcompressor/recipe/__init__.py	13	__all__ = [	CODE
LOW	src/llmcompressor/recipe/recipe.py	19	__all__ = [	CODE
LOW	src/llmcompressor/pipelines/registry.py	14	__all__ = ["CalibrationPipeline"]	CODE
LOW	src/llmcompressor/pipelines/data_free/pipeline.py	14	__all__ = ["DataFreePipeline"]	CODE
52 more matches not shown…

Hallucination Indicators10 hits · 100 pts

Severity	File	Line	Snippet	Context
CRITICAL	tests/llmcompressor/modifiers/qad/test_teacher.py	14	from llmcompressor.utils.helpers import DisableQuantization	CODE
CRITICAL	tests/llmcompressor/modifiers/qad/test_reobserve.py	7	from llmcompressor.utils.helpers import DisableQuantization	CODE
CRITICAL	tests/llmcompressor/modifiers/qad/test_base.py	24	from llmcompressor.utils.helpers import DisableQuantization	CODE
CRITICAL	src/llmcompressor/modifiers/transform/awq/base.py	49	from llmcompressor.utils.helpers import calibration_forward_context	CODE
CRITICAL	src/llmcompressor/pipelines/sequential/pipeline.py	33	from llmcompressor.utils.helpers import DisableQuantization, calibration_forward_context	CODE
CRITICAL	src/llmcompressor/pipelines/sequential/helpers.py	24	from llmcompressor.utils.helpers import calibration_forward_context	CODE
CRITICAL	src/llmcompressor/pipelines/basic/pipeline.py	14	from llmcompressor.utils.helpers import DisableQuantization	CODE
CRITICAL	src/llmcompressor/utils/dist.py	14	from compressed_tensors.utils.helpers import deprecated	CODE
CRITICAL	src/llmcompressor/entrypoints/oneshot.py	42	from llmcompressor.utils.helpers import use_eager_attention	CODE
CRITICAL	…ressor/entrypoints/model_free/reindex_fused_weights.py	3	from compressed_tensors.utils.helpers import deprecated	CODE

Cross-File Repetition17 hits · 85 pts

Severity	File	Snippet	Context
HIGH	examples/quantization_kv_cache/llama3_fp8_kv_example.py	quant_stage: quant_modifiers: quantizationmodifier: ignore: ["lm_head"] config_groups: group_0: weights: num_bits: 8 typ	STRING
HIGH	examples/quantization_kv_cache/phi3.5_fp8_kv_example.py	quant_stage: quant_modifiers: quantizationmodifier: ignore: ["lm_head"] config_groups: group_0: weights: num_bits: 8 typ	STRING
HIGH	examples/quantization_kv_cache/README.md	quant_stage: quant_modifiers: quantizationmodifier: ignore: ["lm_head"] config_groups: group_0: weights: num_bits: 8 typ	STRING
HIGH	examples/quantization_kv_cache/gemma2_fp8_kv_example.py	quant_stage: quant_modifiers: quantizationmodifier: ignore: ["lm_head"] config_groups: group_0: weights: num_bits: 8 typ	STRING
HIGH	…compressor/modifiers/quantization/quantization/base.py	finish calibrating by removing observers and calibration hooks	STRING
HIGH	src/llmcompressor/modifiers/autoround/base.py	finish calibrating by removing observers and calibration hooks	STRING
HIGH	src/llmcompressor/modifiers/gptq/base.py	finish calibrating by removing observers and calibration hooks	STRING
HIGH	src/llmcompressor/modifiers/pruning/wanda/base.py	calibration hook used to accumulate the hessian of the input to the module :param module: module being calibrated :param	STRING
HIGH	src/llmcompressor/modifiers/pruning/sparsegpt/base.py	calibration hook used to accumulate the hessian of the input to the module :param module: module being calibrated :param	STRING
HIGH	src/llmcompressor/modifiers/gptq/base.py	calibration hook used to accumulate the hessian of the input to the module :param module: module being calibrated :param	STRING
HIGH	src/llmcompressor/transformers/data/c4.py	text generation class for the cnn/dailymail dataset :param dataset_args: configuration settings for dataset loading :par	STRING
HIGH	src/llmcompressor/transformers/data/open_platypus.py	text generation class for the cnn/dailymail dataset :param dataset_args: configuration settings for dataset loading :par	STRING
HIGH	src/llmcompressor/transformers/data/wikitext.py	text generation class for the cnn/dailymail dataset :param dataset_args: configuration settings for dataset loading :par	STRING
HIGH	src/llmcompressor/transformers/data/ultrachat_200k.py	text generation class for the cnn/dailymail dataset :param dataset_args: configuration settings for dataset loading :par	STRING
HIGH	src/llmcompressor/transformers/data/evolcodealpaca.py	text generation class for the cnn/dailymail dataset :param dataset_args: configuration settings for dataset loading :par	STRING
HIGH	src/llmcompressor/transformers/data/perfectblend.py	text generation class for the cnn/dailymail dataset :param dataset_args: configuration settings for dataset loading :par	STRING
HIGH	src/llmcompressor/transformers/data/cnn_dailymail.py	text generation class for the cnn/dailymail dataset :param dataset_args: configuration settings for dataset loading :par	STRING

Deep Nesting79 hits · 76 pts

Severity	File	Line	Context
LOW	tools/collect_env.py	18	CODE
LOW	tools/lint_cuda.py	96	CODE
LOW	tools/lint_cuda.py	250	CODE
LOW	tests/testing_utils.py	640	CODE
LOW	tests/sparsity/test_helpers.py	37	CODE
LOW	tests/sparsity/test_helpers.py	72	CODE
LOW	tests/sparsity/test_helpers.py	106	CODE
LOW	tests/sparsity/test_helpers.py	140	CODE
LOW	tests/sparsity/test_helpers.py	177	CODE
LOW	tests/sparsity/test_helpers.py	215	CODE
LOW	…essor/modifiers/transform/awq/test_dynamic_mappings.py	645	CODE
LOW	…sts/llmcompressor/pipelines/sequential/test_helpers.py	126	CODE
LOW	…mpressor/transformers/compression/test_quantization.py	37	CODE
LOW	tests/llmcompressor/observers/test_mse_vs_minmax.py	205	CODE
LOW	tests/e2e/e2e_utils.py	221	CODE
LOW	docs/scripts/zensical_gen_files.py	198	CODE
LOW	docs/scripts/zensical_gen_files.py	280	CODE
LOW	docs/scripts/zensical_gen_files.py	293	CODE
LOW	docs/scripts/zensical_gen_files.py	340	CODE
LOW	docs/scripts/zensical_gen_files.py	364	CODE
LOW	examples/quantizing_moe/deepseek_v4_example.py	52	CODE
LOW	examples/quantizing_moe/deepseek_v4_pro_example.py	58	CODE
LOW	…amples/quantizing_moe/deepseek_v4_mixed_mxfp4_mxfp8.py	52	CODE
LOW	examples/qad/modelopt_mix.py	107	CODE
LOW	examples/qad/modelopt_mix.py	131	CODE
LOW	src/llmcompressor/modifiers/factory.py	38	CODE
LOW	src/llmcompressor/modifiers/factory.py	75	CODE
LOW	src/llmcompressor/modifiers/factory.py	50	CODE
LOW	…ompressor/modifiers/quantization/quantization/mixin.py	420	CODE
LOW	src/llmcompressor/modifiers/pruning/reap/utils.py	59	CODE
LOW	…ompressor/modifiers/pruning/sparsegpt/sgpt_sparsify.py	58	CODE
LOW	src/llmcompressor/modifiers/autoround/base.py	265	CODE
LOW	src/llmcompressor/modifiers/autoround/base.py	493	CODE
LOW	src/llmcompressor/modifiers/autoround/base.py	509	CODE
LOW	src/llmcompressor/modifiers/autoround/base.py	615	CODE
LOW	src/llmcompressor/modifiers/autoround/base.py	785	CODE
LOW	src/llmcompressor/modifiers/gptq/gptq_quantize.py	345	CODE
LOW	src/llmcompressor/modifiers/gptq/helpers.py	283	CODE
LOW	src/llmcompressor/modifiers/gptq/helpers.py	343	CODE
LOW	src/llmcompressor/modifiers/gptq/base.py	308	CODE
LOW	src/llmcompressor/modifiers/transform/awq/base.py	281	CODE
LOW	src/llmcompressor/modifiers/transform/awq/base.py	483	CODE
LOW	src/llmcompressor/modifiers/transform/awq/base.py	885	CODE
LOW	…/llmcompressor/modifiers/transform/smoothquant/base.py	322	CODE
LOW	src/llmcompressor/recipe/utils.py	112	CODE
LOW	src/llmcompressor/recipe/recipe.py	88	CODE
LOW	src/llmcompressor/recipe/recipe.py	168	CODE
LOW	…ompressor/pipelines/sequential/transformers_helpers.py	356	CODE
LOW	…ompressor/pipelines/sequential/transformers_helpers.py	821	CODE
LOW	…ompressor/pipelines/sequential/transformers_helpers.py	1020	CODE
LOW	…ompressor/pipelines/sequential/transformers_helpers.py	1241	CODE
LOW	…ompressor/pipelines/sequential/transformers_helpers.py	1392	CODE
LOW	…ompressor/pipelines/sequential/transformers_helpers.py	1433	CODE
LOW	src/llmcompressor/pipelines/sequential/pipeline.py	81	CODE
LOW	src/llmcompressor/pipelines/sequential/helpers.py	285	CODE
LOW	src/llmcompressor/utils/helpers.py	165	CODE
LOW	src/llmcompressor/utils/dist.py	55	CODE
LOW	src/llmcompressor/utils/pytorch/module.py	29	CODE
LOW	src/llmcompressor/modeling/kimi_k3/encoding_k3.py	292	CODE
LOW	src/llmcompressor/modeling/kimi_k3/encoding_k3.py	384	CODE
19 more matches not shown…

Self-Referential Comments19 hits · 58 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/llmcompressor/modifiers/pruning/reap/test_base.py	662	# Create a config with text_config wrapper	COMMENT
MEDIUM	tests/llmcompressor/modifiers/pruning/reap/test_base.py	463	# Create a mock moe_attrs with group info	COMMENT
MEDIUM	…sts/llmcompressor/modifiers/transform/awq/test_base.py	187	# Create a simplified MoE model structure	COMMENT
MEDIUM	…sts/llmcompressor/modifiers/transform/awq/test_base.py	262	# Create a Qwen3Next-like MoE model structure with shared_expert	COMMENT
MEDIUM	…sts/llmcompressor/modifiers/transform/awq/test_base.py	354	# Create a Qwen3Next-like model with both self_attn and linear_attn layers	COMMENT
MEDIUM	tests/llmcompressor/pipelines/test_cache.py	150	# Create a cache with GPU as model device and CPU as offload device	COMMENT
MEDIUM	tests/llmcompressor/modeling/test_linear_experts.py	20	# Create a Qwen3MoeConfig	COMMENT
MEDIUM	…mcompressor/transformers/test_tokenizer_parallelism.py	27	# Create a minimal Oneshot instance to trigger __init__	COMMENT
MEDIUM	examples/quantizing_moe/qwen3_vl_moe_example.py	70	# Define a oneshot data collator for multimodal inputs.	COMMENT
MEDIUM	examples/multimodal_vision/qwen2_vl_example.py	74	# Define a oneshot data collator for multimodal inputs.	COMMENT
MEDIUM	examples/multimodal_vision/phi3_vision_example.py	67	# Define a oneshot data collator for multimodal inputs.	COMMENT
MEDIUM	examples/multimodal_vision/idefics3_example.py	23	# Define a oneshot data collator for multimodal inputs.	COMMENT
MEDIUM	examples/multimodal_vision/qwen_2_5_vl_example.py	68	# Define a oneshot data collator for multimodal inputs.	COMMENT
MEDIUM	examples/multimodal_vision/qwen3_vl_example.py	69	# Define a oneshot data collator for multimodal inputs.	COMMENT
MEDIUM	src/llmcompressor/pipelines/cache.py	277	# Create a dedicated CUDA stream for H2D transfers so they run on a	COMMENT
MEDIUM	…ompressor/pipelines/sequential/transformers_helpers.py	1493	# Creating a random input shape to generate dummy inputs.	COMMENT
MEDIUM	src/llmcompressor/modeling/deepseekv32/config.py	1	# This file contains code copied from the DeepSeek-V3.2-Exp project.	COMMENT
MEDIUM	src/llmcompressor/modeling/deepseekv32/kernel.py	1	# This file contains code copied from the DeepSeek-V3.2-Exp project.	COMMENT
MEDIUM	src/llmcompressor/modeling/deepseekv32/model.py	1	# This file contains code copied from the DeepSeek-V3.2-Exp project.	COMMENT

Excessive Try-Catch Wrapping34 hits · 40 pts

Severity	File	Line	Snippet	Context
LOW	tools/lint_cuda.py	164	except Exception as e:	CODE
MEDIUM	tools/lint_cuda.py	166	print(f"Error applying fixes to {filepath}: {e}", file=sys.stderr)	CODE
LOW	tools/lint_cuda.py	198	except Exception as e:	CODE
MEDIUM	tools/lint_cuda.py	200	print(f"Error processing {filepath}: {e}", file=sys.stderr)	CODE
MEDIUM	tools/lint_cuda.py	282	print(f"Error: Path '{path}' does not exist", file=sys.stderr)	CODE
LOW	tests/testing_utils.py	832	except Exception as e:	CODE
LOW	tests/testing_utils.py	868	except Exception as e:	CODE
LOW	tests/tools/test_lint_cuda.py	272	except Exception as e:	CODE
LOW	…r/modifiers/quantization/test_group_size_validation.py	107	except Exception:	CODE
LOW	tests/llmcompressor/observers/test_mse_vs_minmax.py	237	except Exception as e:	CODE
LOW	tests/e2e/test_vllm.py	171	except Exception as e:	CODE
LOW	docs/scripts/zensical_gen_files.py	215	except Exception:	CODE
LOW	examples/qad/modelopt_mix.py	182	except Exception as error:	CODE
LOW	src/llmcompressor/modifiers/factory.py	68	except Exception:	CODE
LOW	src/llmcompressor/modifiers/factory.py	121	except Exception as err:	CODE
LOW	src/llmcompressor/modifiers/factory.py	124	except Exception as module_err:	CODE
LOW	…ressor/modifiers/pruning/utils/pytorch/mask_factory.py	57	except Exception:	CODE
LOW	src/llmcompressor/modifiers/gptq/helpers.py	194	except Exception:	CODE
LOW	…llmcompressor/modifiers/transform/smoothquant/utils.py	205	except Exception as original_exception:	CODE
MEDIUM	…llmcompressor/modifiers/transform/smoothquant/utils.py	202	def wrapper(args, *kwargs):	CODE
LOW	src/llmcompressor/core/lifecycle.py	67	except Exception as e:	CODE
LOW	…ompressor/pipelines/sequential/transformers_helpers.py	1316	except Exception as e:	CODE
LOW	src/llmcompressor/pipelines/sequential/ast_helpers.py	142	except Exception as exception:	CODE
MEDIUM	src/llmcompressor/pipelines/sequential/ast_helpers.py	139	def append_autowrap_source_on_fail():	CODE
LOW	…pressor/pipelines/sequential/ast_utils/auto_wrapper.py	121	except Exception:	CODE
LOW	…pressor/pipelines/sequential/ast_utils/auto_wrapper.py	169	except Exception:	CODE
LOW	…llmcompressor/modeling/kimi_k3/modeling_kimi_linear.py	427	except Exception as e:	CODE
LOW	src/llmcompressor/transformers/utils/helpers.py	136	except Exception as e: # TODO: narrow acceptable exceptions	CODE
LOW	…r/transformers/compression/compressed_tensors_utils.py	293	except Exception:	CODE
LOW	…r/transformers/compression/compressed_tensors_utils.py	303	except Exception:	CODE
LOW	src/llmcompressor/entrypoints/utils.py	71	except Exception as e:	CODE
LOW⚡	src/llmcompressor/entrypoints/higgs/utils.py	91	except Exception as e:	CODE
LOW	src/llmcompressor/entrypoints/model_free/lifecycle.py	34	except Exception as exc:	CODE
LOW	src/llmcompressor/pytorch/utils/helpers.py	15	except Exception as _err:	CODE

Structural Annotation Overuse22 hits · 34 pts

Severity	File	Line	Snippet	Context
LOW	docs/guides/entrypoints/convert.md	169	# Step 1: convert to bfloat16	COMMENT
LOW	docs/guides/entrypoints/convert.md	181	# Step 2: re-quantize with oneshot	COMMENT
LOW	examples/quantizing_moe/README.md	25	### Step 1: Load the Model and Tokenizer	COMMENT
LOW	examples/quantizing_moe/README.md	39	### Step 2: Prepare the Calibration Dataset	COMMENT
LOW	examples/quantizing_moe/README.md	81	### Step 3: Configure the Quantization Recipe	COMMENT
LOW	examples/quantizing_moe/README.md	109	### Step 4: Run Quantization with `oneshot`	COMMENT
LOW	examples/quantizing_moe/README.md	130	### Step 5: Save the Quantized Model	COMMENT
LOW	…es/quantization_higgs/higgs_nvfp4a16_fp8_model_free.py	52	# Step 1: get optimal mixed-precision config (model-free)	COMMENT
LOW	…es/quantization_higgs/higgs_nvfp4a16_fp8_model_free.py	66	# Step 2: apply the mixed-precision config without loading the model	COMMENT
LOW	examples/multimodal_vision/README_internvl3.md	4	## Step 1: Compressing Your Own Model	COMMENT
LOW	examples/multimodal_vision/README_internvl3.md	12	## Step 2: Load datasets	COMMENT
LOW	examples/multimodal_vision/README_internvl3.md	23	## Step 3: Preprocess and tokenize	COMMENT
LOW	examples/multimodal_vision/README_internvl3.md	43	## Step 4: Adding Your Own Data Collator	COMMENT
LOW	examples/multimodal_vision/README_internvl3.md	56	## Step 5: Define the recipe	COMMENT
LOW	examples/multimodal_vision/README_internvl3.md	65	## Step 6: Oneshot and save	COMMENT
LOW	examples/multimodal_vision/README_internvl3.md	81	## Step 7: Evaluate	COMMENT
LOW	examples/transform/README.md	25	### Step 1: Select a Model, Dataset, and Recipe	COMMENT
LOW	examples/transform/README.md	48	### Step 2: Run Quantization Using Oneshot	COMMENT
LOW	examples/transform/README.md	64	### Step 3: Run optimized model in vLLM	COMMENT
LOW⚡	src/llmcompressor/modeling/offset_norm.py	122	# Step 1: Collect all offset-norm modules that need replacement	COMMENT
LOW⚡	src/llmcompressor/modeling/offset_norm.py	130	# Step 2: Replace modules	COMMENT
LOW	src/llmcompressor/modeling/offset_norm.py	145	# Step 3: Restore original modules with updated weights	COMMENT

Empty Error Handlers5 hits · 25 pts

Severity	File	Line	Snippet	Context
HIGH	tests/llmcompressor/conftest.py	42	except FileNotFoundError:	CODE
HIGH	docs/scripts/zensical_gen_files.py	215	except Exception:	CODE
HIGH	src/llmcompressor/modifiers/factory.py	68	except Exception:	CODE
HIGH	…ressor/modifiers/pruning/utils/pytorch/mask_factory.py	57	except Exception:	CODE
HIGH	src/llmcompressor/modeling/moe/helpers.py	174	except (ImportError, AttributeError):	CODE

AI Structural Patterns17 hits · 16 pts

Severity	File	Line	Context
LOW	tests/sparsity/test_helpers.py	250	CODE
LOW	tests/sparsity/test_helpers.py	281	CODE
LOW	tests/llmcompressor/modifiers/pruning/reap/test_base.py	170	CODE
LOW	src/llmcompressor/modifiers/quantization/calibration.py	203	CODE
LOW	src/llmcompressor/core/session.py	74	CODE
LOW	src/llmcompressor/core/state.py	120	CODE
LOW	src/llmcompressor/modeling/deepseekv32/config.py	94	CODE
LOW	src/llmcompressor/modeling/kimi_k3/modeling_kimi_k3.py	295	CODE
LOW	src/llmcompressor/modeling/kimi_k3/modeling_kimi_k3.py	299	CODE
LOW	src/llmcompressor/modeling/kimi_k3/modeling_kimi_k3.py	475	CODE
LOW	src/llmcompressor/modeling/kimi_k3/modeling_kimi_k3.py	1143	CODE
LOW	src/llmcompressor/modeling/kimi_k3/tokenization_kimi.py	374	CODE
LOW	…lmcompressor/modeling/kimi_k3/configuration_kimi_k3.py	10	CODE
LOW	…lmcompressor/modeling/kimi_k3/configuration_kimi_k3.py	160	CODE
LOW	…llmcompressor/modeling/kimi_k3/modeling_kimi_linear.py	1434	CODE
LOW	src/llmcompressor/transformers/data/base.py	338	CODE
LOW	src/llmcompressor/entrypoints/oneshot.py	330	CODE

Redundant / Tautological Comments11 hits · 16 pts

Severity	File	Line	Snippet	Context
LOW	tests/lmeval/test_lmeval.py	328	# Check if within ±5% relative tolerance	COMMENT
LOW	tests/examples/test_example_scripts.py	220	# Check if this is a multi-GPU test	COMMENT
LOW	…ts/skills/create-tiny-model/scripts/save_tiny_model.py	12	# Check if the model is multimodal.	COMMENT
LOW	src/llmcompressor/modifiers/gptq/base.py	293	# Assign modules to ranks	COMMENT
LOW	src/llmcompressor/modifiers/transform/awq/base.py	183	# Check if we have a MoE model	COMMENT
LOW	src/llmcompressor/modifiers/transform/awq/base.py	318	# Check if at least one layer is targeted for quantization	COMMENT
LOW	src/llmcompressor/modifiers/transform/awq/base.py	896	# Check if this is an up_proj -> down_proj mapping	COMMENT
LOW	…/llmcompressor/modifiers/transform/smoothquant/base.py	226	# Check if at least one layer would be smoothed (not ignored)	COMMENT
LOW	src/llmcompressor/pipelines/cache.py	471	# Check if the operation is equality	COMMENT
LOW	src/llmcompressor/transformers/utils/helpers.py	114	# Check if offline mode is enabled	COMMENT
LOW	…ompressor/transformers/compression/sparsity_helpers.py	45	# Check if the number of zeros in each chunk atleast n	COMMENT

Over-Commented Block10 hits · 10 pts

Severity	File	Line	Snippet	Context
LOW	tests/lmeval/configs/qwen36_nvfp4_fp8.yaml	21	# Note: recovery will be dependent on	COMMENT
LOW	docs/developer-tutorials/add-modifier.md	61	def on_start(self, state: State, event: Event, **kwargs):	COMMENT
LOW	examples/quantization_w4a4_fp4/qwen_30b_a3b.py	21	recipe = QuantizationModifier(	COMMENT
LOW	examples/model_free_ptq/deepseek_r1_nvfp4_fp8_block.py	41	# - model.layers.0.mlp.gate_proj.weight	COMMENT
LOW	src/llmcompressor/modifiers/transform/awq/mappings.py	201	]	COMMENT
LOW	…ompressor/pipelines/sequential/transformers_helpers.py	1	# ruff: noqa	COMMENT
LOW	src/llmcompressor/pipelines/sequential/pipeline.py	161		COMMENT
LOW	src/llmcompressor/modeling/kimi_k3/modeling_kimi_k3.py	1	# coding=utf-8	COMMENT
LOW	…llmcompressor/modeling/kimi_k3/modeling_kimi_linear.py	1	# coding=utf-8	COMMENT
LOW	…llmcompressor/modeling/kimi_k3/modeling_kimi_linear.py	21	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.	COMMENT

Docstring Block Structure2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	src/llmcompressor/modeling/deepseekv32/model.py	56	Forward pass for parallel embedding layer. Args: x (torch.Tensor): Input tensor containing	STRING
HIGH	src/llmcompressor/entrypoints/higgs/ilp_solver.py	33	Solve ILP to select optimal quantization scheme for each layer. Formulation: Decision variables: x[lay	STRING

Dead Code5 hits · 10 pts

Severity	File	Line	Context
MEDIUM	src/llmcompressor/modeling/kimi_k3/modeling_kimi_k3.py	864	CODE
MEDIUM	src/llmcompressor/modeling/kimi_k3/modeling_kimi_k3.py	870	CODE
MEDIUM	src/llmcompressor/modeling/kimi_k3/modeling_kimi_k3.py	873	CODE
MEDIUM	…llmcompressor/modeling/kimi_k3/modeling_kimi_linear.py	1199	CODE
MEDIUM	…llmcompressor/modeling/kimi_k3/modeling_kimi_linear.py	1200	CODE

Verbosity Indicators5 hits · 9 pts

Severity	File	Line	Snippet	Context
LOW	…es/quantization_higgs/higgs_nvfp4a16_fp8_model_free.py	52	# Step 1: get optimal mixed-precision config (model-free)	COMMENT
LOW	…es/quantization_higgs/higgs_nvfp4a16_fp8_model_free.py	66	# Step 2: apply the mixed-precision config without loading the model	COMMENT
LOW⚡	src/llmcompressor/modeling/offset_norm.py	122	# Step 1: Collect all offset-norm modules that need replacement	COMMENT
LOW⚡	src/llmcompressor/modeling/offset_norm.py	130	# Step 2: Replace modules	COMMENT
LOW	src/llmcompressor/modeling/offset_norm.py	145	# Step 3: Restore original modules with updated weights	COMMENT

AI Slop Vocabulary3 hits · 8 pts

Severity	File	Line	Snippet	Context
MEDIUM	…ssor/entrypoints/model_free/test_convert_checkpoint.py	22	# here to leverage llm-compressor's nightly testing CI/CD.	COMMENT
MEDIUM	…ization_non_uniform/quantization_multiple_modifiers.py	32	# only include mappings pertaining to target layers	COMMENT
LOW	src/llmcompressor/entrypoints/higgs/ilp_solver.py	192	# just use actual performance numbers at the end of the day.	COMMENT

AI Response Leakage1 hit · 8 pts

Severity	File	Line	Snippet	Context
HIGH	examples/disk_offloading/qwen3_example.py	12	# In this example, we emulate large model quantization with disk offloading by	COMMENT

Fake / Example Data5 hits · 5 pts

Severity	File	Line	Snippet	Context
LOW	examples/multimodal_audio/qwen2_audio.py	44	{"type": "audio", "audio_url": "placeholder"},	CODE
LOW	examples/multimodal_audio/qwen2_audio.py	104	{"type": "audio", "audio_url": "placeholder"},	CODE
LOW	…ompressor/pipelines/sequential/transformers_helpers.py	1255	if kind == "placeholder" and target in self.meta_args:	CODE
LOW	…ompressor/pipelines/sequential/transformers_helpers.py	1552	if node.op == "placeholder":	CODE
LOW	src/llmcompressor/pipelines/sequential/helpers.py	468	input_names = set(node.name for node in graph.nodes if node.op == "placeholder")	CODE

Synthetic Comment Markers1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	src/llmcompressor/modeling/deepseekv32/README.md	16	- add `bf16_index` kernel that mimics the `fp8_index` tilelang kernel (in original model definition's kernel.py). `b	CODE

Slop Phrases1 hit · 3 pts

Severity	File	Line	Snippet	Context
MEDIUM	examples/transform/quip_example.py	15	# example, you can use additional GPUs to support larger models	COMMENT

Maintenance and Governance Review

Risk Review · v3

What These Metrics Mean

Pattern-Signal History

Severity Breakdown

Directory Score Breakdown

Pattern Findings