vllm-project/vllm-omni

Pattern Findings

The scanner identified 27852 distinct pattern matches across 25 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 Identifiers17194 hits · 16117 pts

Severity	File	Line	Snippet	Context
LOW	collect_env.py	135	def run_and_parse_first_match(run_lambda, command, regex):	CODE
LOW	collect_env.py	146	def run_and_return_first_line(run_lambda, command):	CODE
LOW	collect_env.py	179	def get_nvidia_driver_version(run_lambda):	CODE
LOW	collect_env.py	318	def summarize_vllm_build_flags():	CODE
LOW	collect_env.py	473	def get_cachingallocator_config():	CODE
LOW	collect_env.py	478	def get_cuda_module_loading_config():	CODE
LOW	tools/run_jobs_common.sh	526	def timeout_kill_after_seconds() -> int:	CODE
LOW	tools/run_jobs_common.sh	535	def prepend_timeout_to_pytest(pytest_line: str, timeout_min: int \| None) -> str:	CODE
LOW	tools/run_jobs_common.sh	547	def _write_job_timeouts_manifest(jobs_dir: Path, job_timeouts: dict[str, int]) -> None:	CODE
LOW	tools/breeze_tts_2_compare_golden.py	69	def _longest_exact_frame_prefix(upstream: torch.Tensor, actual: torch.Tensor) -> int:	CODE
LOW	tools/breeze_tts_2_upstream_golden.py	92	def _capture_first_backbone_hidden(_module, _inputs, output):	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	89	def extract_pytest_targets_from_line(line: str) -> list[str]:	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	141	def get_pytest_targets_from_step(step: dict) -> list[tuple[str, str]]:	CODE
LOW⚡	tools/nightly/buildkite_testcase_statistics.py	161	def _strip_ignore_clauses_from_args_fragment(fragment: str) -> str:	CODE
LOW⚡	tools/nightly/buildkite_testcase_statistics.py	166	def _strip_test_config_file_clauses_from_args_fragment(fragment: str) -> str:	CODE
LOW⚡	tools/nightly/buildkite_testcase_statistics.py	171	def _pytest_collect_sidecar_args(raw_line: str) -> list[str]:	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	211	def _parse_extra_args_from_line(raw_line: str) -> list[str]:	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	216	def _parse_collect_only_stdout(stdout: str, *, raise_on_empty: bool = True, stderr: str = "") -> list[str]:	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	271	def _format_pytest_collect_failure(	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	386	def get_docstring_for_node_id(repo_root: Path, node_id: str) -> str:	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	429	def get_test_file_for_node_id(node_id: str) -> str:	CODE
LOW	tools/nightly/generate_nightly_perf_excel.py	224	def _ensure_omni_summary_columns(summary_columns: list[str]) -> list[str]:	CODE
LOW	tools/nightly/generate_nightly_perf_excel.py	277	def _default_diffusion_input_dir(input_dir: str) -> str:	CODE
LOW	tools/nightly/generate_nightly_perf_excel.py	471	def _parse_diffusion_result_from_filename(filename: str) -> dict[str, Any]:	CODE
LOW	tools/nightly/generate_nightly_perf_excel.py	531	def _collect_diffusion_records(diffusion_input_dir: str) -> list[dict[str, Any]]:	CODE
LOW	tools/nightly/generate_nightly_perf_excel.py	560	def _process_diffusion_record(record: dict[str, Any]) -> dict[str, Any]:	CODE
LOW	tools/nightly/generate_nightly_perf_excel.py	576	def _apply_build_metadata_to_latest_only(	CODE
LOW	tools/nightly/generate_nightly_perf_excel.py	614	def _sort_records_for_summary(records: list[dict[str, Any]]) -> list[dict[str, Any]]:	CODE
LOW	tools/nightly/generate_nightly_perf_excel.py	623	def _sort_diffusion_records_for_summary(records: list[dict[str, Any]]) -> list[dict[str, Any]]:	CODE
LOW	tools/nightly/generate_nightly_perf_html.py	55	def _default_diffusion_input_dir(input_dir: str) -> str:	CODE
LOW	tools/nightly/generate_nightly_perf_html.py	176	def _parse_diffusion_from_filename(filename: str) -> dict[str, Any]:	CODE
LOW	tools/nightly/generate_nightly_perf_html.py	195	def _iter_diffusion_json_records(input_dir: str) -> Iterable[dict[str, Any]]:	CODE
LOW	tools/nightly/generate_nightly_perf_html.py	251	def _collect_diffusion_records(input_dir: str) -> list[dict[str, Any]]:	CODE
LOW	tools/nightly/run_nightly_jobs.sh	568	def timeout_kill_after_seconds() -> int:	CODE
LOW	tools/nightly/run_nightly_jobs.sh	577	def prepend_timeout_to_pytest(pytest_line: str, timeout_min: int \| None) -> str:	CODE
LOW	tools/nightly/run_nightly_jobs.sh	589	def _write_job_timeouts_manifest(jobs_dir: Path, job_timeouts: dict[str, int]) -> None:	CODE
LOW	tools/nightly/run_nightly_jobs.sh	685	def local_test_files_by_filename(substr: str) -> list[str]:	CODE
LOW	tools/nightly/run_nightly_jobs.sh	730	def perf_json_matches_model_type(json_basename: str, model_types: list[str]) -> bool:	CODE
LOW	tools/pre_commit/check_test_marks.py	145	def get_files_missing_markers(	CODE
LOW	tools/wan22/assemble_wan22_i2v_diffusers.py	62	def _load_shard_files_from_index(index_file: Path, role: str) -> tuple[Path, ...]:	CODE
LOW	tests/metrics/test_stats.py	21	def test_orchestrator_aggregator_builds_summary() -> None:	CODE
LOW	tests/metrics/test_stats.py	97	def test_build_and_log_summary_multiple_requests() -> None:	CODE
LOW	tests/metrics/test_stats.py	163	def test_log_timing_summary_skips_tables_unless_debug(monkeypatch) -> None:	CODE
LOW	tests/metrics/test_prometheus.py	53	def test_all_metric_families_present(self, scrape_output: str) -> None:	CODE
LOW⚡	tests/metrics/test_prometheus.py	102	def test_pipeline_metrics_carry_model_name(self, scrape_output: str) -> None:	CODE
LOW⚡	tests/metrics/test_prometheus.py	107	def test_no_legacy_engine_label(self, scrape_output: str) -> None:	CODE
LOW⚡	tests/metrics/test_prometheus.py	110	def test_no_legacy_seconds_or_ms_families(self, scrape_output: str) -> None:	CODE
LOW⚡	tests/metrics/test_prometheus.py	120	def test_omni_metrics_in_default_registry(self, scrape_output: str) -> None:	CODE
LOW⚡	tests/metrics/test_prometheus.py	124	def test_process_metrics_in_default_registry(self, scrape_output: str) -> None:	CODE
LOW	tests/metrics/test_prometheus.py	147	def test_running_and_waiting_zero_after_request_completes(self, registry: CollectorRegistry) -> None:	CODE
LOW	tests/metrics/test_prometheus.py	175	def test_gauges_reflect_remaining_requests_after_one_completes(self, registry: CollectorRegistry) -> None:	CODE
LOW	tests/metrics/test_prometheus.py	200	def test_engine_queued_requests_count_as_waiting(self, registry: CollectorRegistry) -> None:	CODE
LOW	tests/metrics/test_metrics_utils.py	35	def test_count_video_frames_handles_short_channel_last_outputs(shape, expected_frames):	CODE
LOW	tests/metrics/test_metrics_utils.py	47	def test_count_audio_chunk_frames(audio_chunk: object, expected: int) -> None:	CODE
LOW	tests/metrics/test_metrics_utils.py	51	def test_count_audio_frames_sums_audio_chunks() -> None:	CODE
LOW	tests/metrics/test_metrics_utils.py	62	def test_count_audio_frames_supports_model_outputs() -> None:	CODE
LOW	tests/metrics/test_metrics_utils.py	74	def test_count_audio_frames_returns_zero_without_audio(mm_out: dict[str, object]) -> None:	CODE
LOW	tests/metrics/test_metrics_utils.py	94	def test_count_image_pixels_sums_nested_values() -> None:	CODE
LOW	tests/metrics/test_metrics_utils.py	106	def test_count_tokens_from_outputs() -> None:	CODE
LOW⚡	tests/metrics/test_transfer.py	42	def test_all_four_families_present(self, tx: OmniTransferMetrics) -> None:	CODE
17134 more matches not shown…

Decorative Section Separators2423 hits · 8228 pts

Severity	File	Line	Snippet	Context
MEDIUM	tools/run_jobs_common.sh	26	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/run_jobs_common.sh	28	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/run_jobs_common.sh	179	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/run_jobs_common.sh	186	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_transfer.py	36	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_transfer.py	38	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_transfer.py	62	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_transfer.py	64	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_transfer.py	118	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_transfer.py	120	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_transfer.py	151	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_transfer.py	153	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_transfer.py	173	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_transfer.py	175	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_modality.py	92	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_modality.py	94	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_modality.py	204	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_modality.py	206	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_modality.py	248	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_modality.py	250	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/metrics/test_modality.py	38	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/metrics/test_modality.py	40	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	83	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	85	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	105	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	107	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	232	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	234	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	268	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	270	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	291	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	293	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	318	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	322	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	384	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	391	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	417	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_stat_logger.py	424	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/metrics/test_stat_logger.py	48	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/metrics/test_stat_logger.py	50	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_emit_calls.py	28	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_emit_calls.py	30	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_emit_calls.py	364	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/metrics/test_emit_calls.py	367	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/metrics/test_emit_calls.py	416	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/metrics/test_emit_calls.py	418	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/clients/test_duplex_client.py	287	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/clients/test_duplex_client.py	918	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	66	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	114	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	195	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	239	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	322	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	371	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	435	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	620	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	757	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	941	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	957	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/clients/test_duplex_client.py	1484	# ---------------------------------------------------------------------------	COMMENT
2363 more matches not shown…

Unused Imports2730 hits · 2540 pts

Severity	File	Line	Context
LOW	tools/sheetsage2_transcribe.py	10	CODE
LOW	tools/auk_parity_reference.py	32	CODE
LOW	tools/prepare_auk_checkpoint.py	42	CODE
LOW	tools/breeze_tts_2_compare_golden.py	7	CODE
LOW	tools/configure_stage_memory.py	19	CODE
LOW	tools/breeze_tts_2_upstream_golden.py	13	CODE
LOW	tools/nightly/send_nightly_email.py	9	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	21	CODE
LOW	tools/nightly/generate_nightly_perf_excel.py	10	CODE
LOW	tools/nightly/generate_nightly_perf_html.py	10	CODE
LOW	tools/pre_commit/mypy.py	18	CODE
LOW	tools/pre_commit/check_test_marks.py	20	CODE
LOW	tools/pre_commit/check_tts_adapter.py	21	CODE
LOW	tools/pre_commit/check_buildkite.py	12	CODE
LOW	tools/minimax_h3/build_adaln_cache.py	5	CODE
LOW	tools/wan22/assemble_wan22_i2v_diffusers.py	22	CODE
LOW	tools/baselines/omni_hash_baseline.py	44	CODE
LOW	tests/conftest.py	13	CODE
LOW	tests/metrics/test_stats.py	4	CODE
LOW	tests/metrics/test_prometheus.py	1	CODE
LOW	tests/metrics/test_metrics_utils.py	4	CODE
LOW	tests/metrics/test_transfer.py	1	CODE
LOW	tests/metrics/test_modality.py	4	CODE
LOW	tests/metrics/test_stat_logger.py	4	CODE
LOW	tests/metrics/test_emit_calls.py	9	CODE
LOW	tests/clients/test_duplex_client.py	11	CODE
LOW	tests/platforms/npu/test_a5_patches.py	13	CODE
LOW	tests/platforms/npu/test_310p_patches.py	9	CODE
LOW	…tforms/npu/test_npu_generation_runner_prewarm_hooks.py	10	CODE
LOW	tests/platforms/npu/test_step_audio2_token2wav.py	5	CODE
LOW	…/platforms/npu/test_diffusion_attn_backend_selector.py	15	CODE
LOW	tests/platforms/npu/quant/test_kv_quant_npu.py	10	CODE
LOW	tests/platforms/npu/quant/test_kv_quant_npu.py	53	CODE
LOW	tests/tools/test_check_tts_adapter.py	9	CODE
LOW	tests/core/test_prefix_cache.py	22	CODE
LOW	tests/core/test_prefix_cache_runner_mixin.py	16	CODE
LOW	…/core/sched/test_omni_scheduler_async_chunk_prewarm.py	10	CODE
LOW	…e/sched/test_omni_ar_scheduler_free_request_cleanup.py	8	CODE
LOW	…e/sched/test_omni_ar_scheduler_free_request_cleanup.py	18	CODE
LOW	tests/core/sched/test_omni_ar_scheduler_stale_drain.py	27	CODE
LOW	tests/core/sched/test_omni_ar_scheduler_stale_drain.py	37	CODE
LOW	…sched/test_omni_scheduler_input_coordinator_cleanup.py	4	CODE
LOW	…s/core/sched/test_omni_sched_prefill_stats_finalize.py	13	CODE
LOW	…s/core/sched/test_omni_sched_prefill_stats_finalize.py	22	CODE
LOW	…sched/test_omni_generation_scheduler_update_session.py	12	CODE
LOW	…sched/test_omni_generation_scheduler_update_session.py	23	CODE
LOW	…re/sched/test_omni_ar_scheduler_aborted_queue_sweep.py	18	CODE
LOW	tests/core/sched/test_omni_scheduling_coordinator.py	12	CODE
LOW	tests/core/sched/test_omni_scheduler_mixin_timeouts.py	13	CODE
LOW	tests/core/sched/test_omni_sched_deferred_free_fence.py	24	CODE
LOW	tests/core/sched/test_omni_sched_deferred_free_fence.py	33	CODE
LOW	tests/core/sched/test_sched_package_imports.py	4	CODE
LOW	…ched/test_omni_ar_scheduler_unified_decode_deferral.py	4	CODE
LOW	tests/core/sched/test_omni_ar_scheduler_streaming.py	6	CODE
LOW	tests/core/sched/test_omni_ar_scheduler_streaming.py	17	CODE
LOW	…e/sched/test_omni_scheduler_streaming_input_counter.py	26	CODE
LOW	tests/core/sched/test_omni_sched_ec_request_finish.py	15	CODE
LOW	tests/core/sched/test_omni_sched_ec_request_finish.py	24	CODE
LOW	…re/sched/test_omni_scheduler_forces_v1_model_runner.py	15	CODE
LOW	tests/core/sched/test_omni_ar_scheduler_logprobs.py	6	CODE
2670 more matches not shown…

Empty Error Handlers352 hits · 1755 pts

Severity	File	Line	Snippet	Context
HIGH	setup.py	94	except Exception:	CODE
HIGH	setup.py	103	except Exception:	CODE
HIGH	setup.py	112	except Exception:	CODE
HIGH	tools/configure_stage_memory.py	39	except Exception:	CODE
HIGH	tools/configure_stage_memory.py	255	except ValueError:	CODE
HIGH	tools/nightly/generate_nightly_perf_excel.py	406	except (TypeError, ValueError):	CODE
HIGH	tools/nightly/generate_nightly_perf_excel.py	411	except (TypeError, ValueError):	CODE
HIGH	tools/nightly/generate_nightly_perf_excel.py	764	except (ValueError, TypeError):	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	122	except (TypeError, ValueError):	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	127	except (TypeError, ValueError):	CODE
HIGH	tests/core/sched/test_generation_scheduler_restore.py	257	except Exception:	CODE
HIGH	tests/core/sched/test_generation_scheduler_restore.py	280	except Exception:	CODE
HIGH	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	75	except Exception:	CODE
HIGH	…ributed/omni_connectors/test_chunk_transfer_adapter.py	684	except ValueError:	CODE
HIGH	…buted/omni_connectors/test_bagel_mooncake_connector.py	319	except OSError:	CODE
HIGH	…buted/omni_connectors/test_bagel_mooncake_connector.py	324	except OSError:	CODE
HIGH	tests/model_executor/helpers.py	54	except Exception:	CODE
HIGH	…s/model_executor/models/glm_image/test_glm_image_ar.py	185	except Exception:	CODE
HIGH	…s/model_executor/models/minicpmo_4_5/test_dit_fused.py	24	except ImportError:	CODE
HIGH	…xecutor/models/minicpmo_4_5/test_cuda_graph_wrapper.py	2265	except ImportError:	CODE
HIGH	…executor/models/minicpmo_4_5/test_code2wav_batching.py	1843	except ImportError:	CODE
HIGH	tests/diffusion/attention/test_ulysses_uaa.py	1022	except OSError:	CODE
HIGH	tests/diffusion/attention/test_ulysses_uaa.py	841	except OSError:	CODE
HIGH	tests/diffusion/attention/test_ulysses_uaa.py	1121	except OSError:	CODE
HIGH	tests/diffusion/attention/test_ulysses_uaa.py	1232	except OSError:	CODE
HIGH	…eractive_generation/test_diffusion_streaming_output.py	206	except Exception:	CODE
HIGH	tests/diffusion/ar_diffusion/test_paged_attention.py	98	except ImportError:	CODE
HIGH	tests/diffusion/distributed/test_boogu_image_sp.py	316	except OSError:	CODE
HIGH	…n/models/flux2/test_flux2_klein_num_inference_steps.py	60	except _StopAfterCheckInputsError:	CODE
HIGH	tests/examples/helpers.py	159	except ValueError:	CODE
HIGH	tests/benchmarks/conftest.py	33	except ImportError:	CODE
HIGH	tests/benchmarks/patch/test_patch.py	1348	except ConnectionResetError:	CODE
HIGH	tests/benchmarks/patch/test_patch.py	1359	except (ConnectionResetError, BrokenPipeError):	CODE
HIGH	tests/dfx/stability/helpers.py	51	except subprocess.TimeoutExpired:	CODE
HIGH	tests/dfx/perf/scripts/run_diffusion_benchmark.py	351	except psutil.NoSuchProcess:	CODE
HIGH	tests/dfx/perf/scripts/run_diffusion_benchmark.py	304	except Exception:	CODE
HIGH	tests/dfx/perf/scripts/run_diffusion_benchmark.py	323	except psutil.NoSuchProcess:	CODE
HIGH	tests/dfx/perf/scripts/run_diffusion_benchmark.py	330	except psutil.NoSuchProcess:	CODE
HIGH	tests/dfx/perf/scripts/run_diffusion_benchmark.py	339	except psutil.NoSuchProcess:	CODE
HIGH	tests/dfx/perf/scripts/run_diffusion_benchmark.py	349	except Exception:	CODE
HIGH	tests/entrypoints/test_pd_disaggregation.py	140	except Exception:	CODE
HIGH	tests/entrypoints/test_pd_disaggregation.py	147	except Exception:	CODE
HIGH	tests/entrypoints/test_omni_sleep_mode.py	272	except (psutil.NoSuchProcess, psutil.AccessDenied):	CODE
HIGH	tests/worker/test_omni_connector_mixin.py	1895	except Exception:	CODE
HIGH	tests/worker/test_pp_async_token_broadcast.py	282	except _StopAtBookkeepingError:	CODE
HIGH	tests/e2e/offline_inference/test_voxcpm2_tts.py	77	except ImportError:	CODE
HIGH	tests/e2e/features/comfyui/test_comfyui_integration.py	649	except requests.RequestException:	CODE
HIGH	…ures/custom_pipeline/test_async_omni_collective_rpc.py	202	except Exception:	CODE
HIGH	tests/e2e/features/helpers/custom_pipeline.py	271	except Exception: # noqa: BLE001	CODE
HIGH	tests/e2e/accuracy/omni_duplex_eval/conftest.py	93	except Exception:	CODE
HIGH	tests/e2e/accuracy/omni_duplex_eval/conftest.py	140	except Exception:	CODE
HIGH	tests/e2e/online_serving/personaplex_realtime_duplex.py	88	except asyncio.CancelledError:	CODE
HIGH	…_serving/helpers/minicpmo_realtime_duplex_scenarios.py	1571	except asyncio.CancelledError:	CODE
HIGH	…_serving/helpers/minicpmo_realtime_duplex_scenarios.py	1565	except (ConnectionClosed, TimeoutError):	CODE
HIGH	…_serving/helpers/minicpmo_realtime_duplex_scenarios.py	218	except Exception:	CODE
HIGH	tests/engine/test_membership_controller.py	441	except asyncio.CancelledError:	CODE
HIGH	tests/engine/test_membership_controller.py	487	except asyncio.CancelledError:	CODE
HIGH	tests/engine/test_membership_controller.py	539	except asyncio.CancelledError:	CODE
HIGH	tests/engine/test_membership_controller.py	603	except asyncio.CancelledError:	CODE
HIGH	tests/helpers/media.py	87	except OSError:	CODE
292 more matches not shown…

Excessive Try-Catch Wrapping1489 hits · 1531 pts

Severity	File	Line	Snippet	Context
LOW	collect_env.py	499	except Exception:	CODE
MEDIUM	collect_env.py	293	def get_vllm_omni_version(run_lambda):	CODE
LOW	setup.py	39	except Exception as e:	CODE
LOW⚡	setup.py	94	except Exception:	CODE
LOW⚡	setup.py	103	except Exception:	CODE
LOW⚡	setup.py	112	except Exception:	CODE
LOW	setup.py	150	except Exception as e:	CODE
LOW	tools/configure_stage_memory.py	39	except Exception:	CODE
LOW	tools/configure_stage_memory.py	65	except Exception as e:	CODE
MEDIUM	tools/configure_stage_memory.py	317	print(f"Error: {config_path} not found", file=sys.stderr)	STRING
LOW	tools/nightly/send_nightly_email.py	277	except Exception as e:	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	405	except Exception:	CODE
LOW	tools/nightly/run_nightly_jobs.sh	725	except Exception as exc:	CODE
LOW	tools/pre_commit/check_buildkite.py	110	except Exception as exc: # noqa: BLE001 - surface expander errors as hook failures	CODE
LOW	tools/wan22/assemble_wan22_i2v_diffusers.py	66	except Exception as exc:	CODE
LOW	tools/baselines/omni_hash_baseline.py	90	except Exception:	CODE
LOW	tools/baselines/omni_hash_baseline.py	99	except Exception:	CODE
MEDIUM	tools/baselines/omni_hash_baseline.py	87	def _git_commit() -> str:	CODE
LOW⚡	tests/core/sched/test_generation_scheduler_restore.py	257	except Exception:	CODE
LOW	tests/core/sched/test_generation_scheduler_restore.py	280	except Exception:	CODE
MEDIUM	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	402	def worker(rid, data):	CODE
MEDIUM	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	613	def producer_worker(rid, tensor):	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	75	except Exception:	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	124	except Exception as exc:	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	157	except Exception as exc:	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	408	except Exception as e:	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	562	except Exception as e:	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	624	except Exception as e:	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	657	except Exception as e:	CODE
LOW⚡	…ributed/omni_connectors/test_chunk_transfer_adapter.py	2220	except Exception as e:	CODE
LOW⚡	…ributed/omni_connectors/test_chunk_transfer_adapter.py	2229	except Exception as e:	CODE
LOW	…mni_connectors/test_mooncake_transfer_engine_buffer.py	78	except Exception as e:	CODE
MEDIUM	…mni_connectors/test_mooncake_transfer_engine_buffer.py	72	def worker(worker_id):	CODE
LOW	…tributed/omni_connectors/test_nixl_connector_native.py	150	except Exception as error:	CODE
LOW	…tributed/omni_connectors/test_nixl_connector_native.py	247	except Exception as error:	CODE
MEDIUM	…tributed/omni_connectors/test_nixl_connector_native.py	19	def _native_nixl_available() -> bool:	CODE
LOW	…ributed/omni_connectors/test_omni_connector_configs.py	89	except Exception as e:	CODE
LOW	tests/model_executor/helpers.py	54	except Exception:	CODE
LOW	…s/model_executor/models/glm_image/test_glm_image_ar.py	185	except Exception:	CODE
LOW	…l_executor/models/qwen3_tts/test_cuda_graph_decoder.py	33	except Exception:	CODE
LOW	tests/utils/test_speaker_cache.py	127	except Exception as e:	CODE
MEDIUM	tests/utils/test_speaker_cache.py	122	def worker(tid):	CODE
LOW	tests/diffusion/test_diffusion_config_fields.py	18	except Exception:	CODE
LOW	tests/diffusion/test_stage_diffusion_client.py	49	except Exception as e:	CODE
MEDIUM	tests/diffusion/test_stage_diffusion_client.py	46	def run():	CODE
LOW	tests/diffusion/offloader/test_diffusion_cpu_offload.py	136	except Exception:	CODE
LOW	tests/diffusion/attention/test_trtllm_attn.py	29	except Exception:	CODE
LOW	tests/diffusion/attention/test_flash_attn.py	1124	except Exception as e:	CODE
LOW	tests/diffusion/attention/test_flash_attn.py	1133	except Exception as e:	CODE
LOW	…eractive_generation/test_diffusion_streaming_output.py	88	except Exception as exc:	CODE
LOW	…eractive_generation/test_diffusion_streaming_output.py	206	except Exception:	CODE
MEDIUM	…eractive_generation/test_diffusion_streaming_output.py	85	def step_streaming(self, request):	CODE
LOW	tests/diffusion/ar_diffusion/test_paged_attention.py	107	except Exception:	CODE
LOW	tests/diffusion/ar_diffusion/test_paged_attention.py	118	except Exception:	CODE
LOW	tests/diffusion/models/pi0/test_pi0_parity.py	354	except Exception as e: # noqa: BLE001	CODE
LOW	…s/hunyuan_image3/test_hunyuan_image3_it2i_ar_format.py	114	except Exception:	CODE
LOW⚡	tests/diffusion/batching/test_diffusion_batching.py	514	except Exception as e:	CODE
LOW	tests/diffusion/batching/test_diffusion_batching.py	338	except Exception as e:	CODE
LOW	tests/diffusion/batching/test_diffusion_batching.py	378	except Exception as e:	CODE
LOW	tests/diffusion/batching/test_diffusion_batching.py	480	except Exception as e:	CODE
1429 more matches not shown…

Deep Nesting1194 hits · 996 pts

Severity	File	Line	Context
LOW	collect_env.py	187	CODE
LOW	collect_env.py	356	CODE
LOW	setup.py	43	CODE
LOW	setup.py	123	CODE
LOW	tools/configure_stage_memory.py	192	CODE
LOW	tools/nightly/send_nightly_email.py	211	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	327	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	386	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	440	CODE
LOW	tools/nightly/buildkite_testcase_statistics.py	991	CODE
LOW	tools/nightly/generate_nightly_perf_excel.py	742	CODE
LOW	tools/nightly/generate_nightly_perf_html.py	195	CODE
LOW	tools/pre_commit/check_tts_adapter.py	83	CODE
LOW	tools/pre_commit/check_spdx_header.py	115	CODE
LOW	tools/pre_commit/check_spdx_header.py	164	CODE
LOW	tools/baselines/omni_hash_baseline.py	144	CODE
LOW	…tforms/npu/test_npu_generation_runner_prewarm_hooks.py	28	CODE
LOW	…tforms/npu/test_npu_generation_runner_prewarm_hooks.py	59	CODE
LOW	tests/core/sched/test_generation_batch_coalescing.py	30	CODE
LOW	tests/core/sched/test_generation_batch_coalescing.py	124	CODE
LOW	tests/host_weight_runtime/test_contracts.py	208	CODE
LOW	tests/host_weight_runtime/test_filesystem_store.py	1877	CODE
LOW	tests/host_weight_runtime/test_filesystem_store.py	292	CODE
LOW	…sts/distributed/omni_connectors/test_nixl_connector.py	1293	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	40	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	80	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	360	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	597	CODE
LOW	…/omni_connectors/test_mooncake_transfer_engine_rdma.py	630	CODE
LOW	tests/config/test_environment_variables.py	26	CODE
LOW	tests/config/test_environment_variables.py	44	CODE
LOW	tests/config/test_environment_variables.py	71	CODE
LOW	tests/config/test_environment_variables.py	114	CODE
LOW	tests/config/test_environment_variables.py	136	CODE
LOW	tests/model_executor/models/test_gepard_wiring.py	168	CODE
LOW	tests/model_executor/models/test_breeze_tts_2_graphs.py	244	CODE
LOW	…xecutor/models/test_breeze_tts_2_first_code_sampler.py	92	CODE
LOW	…xecutor/models/test_breeze_tts_2_first_code_sampler.py	118	CODE
LOW	tests/model_executor/models/test_breeze_tts_2.py	106	CODE
LOW	tests/model_executor/models/test_omni_processing.py	257	CODE
LOW	…sts/model_executor/models/voxcpm2/test_startup_lora.py	114	CODE
LOW	…or/models/cosyvoice3/test_cosyvoice3_f0_weight_norm.py	238	CODE
LOW	…ts/model_executor/models/common/test_audio_in_video.py	33	CODE
LOW	…cutor/models/higgs_audio_v3/test_codec_snake_kernel.py	32	CODE
LOW	…ecutor/models/personaplex/test_ring_per_row_offsets.py	242	CODE
LOW	…ecutor/models/personaplex/test_ring_per_row_offsets.py	282	CODE
LOW	…del_executor/models/personaplex/test_mimi_cudagraph.py	161	CODE
LOW	…l_executor/models/qwen3_tts/test_time_major_decoder.py	17	CODE
LOW	…executor/models/qwen3_tts/test_code_predictor_dtype.py	1033	CODE
LOW	…executor/models/qwen3_tts/test_code_predictor_dtype.py	1146	CODE
LOW	…executor/models/qwen3_tts/test_code_predictor_dtype.py	1273	CODE
LOW	…xecutor/models/qwen3_tts/test_cached_code_predictor.py	16	CODE
LOW	…cutor/models/qwen3_tts/test_code_predictor_sampling.py	93	CODE
LOW	…tor/models/qwen3_omni/test_vision_encoder_cudagraph.py	195	CODE
LOW	…odels/qwen3_omni/test_vision_encoder_cudagraph_cuda.py	96	CODE
LOW	…el_executor/models/qwen2_5_omni/test_weight_loading.py	39	CODE
LOW	…xecutor/models/minicpmo_4_5/test_flow_encoder_graph.py	598	CODE
LOW	…xecutor/models/minicpmo_4_5/test_encoder_cuda_graph.py	361	CODE
LOW	…del_executor/stage_input_processors/test_minimax_h3.py	340	CODE
LOW	…del_executor/stage_input_processors/test_minimax_h3.py	614	CODE
1134 more matches not shown…

Cross-Language Confusion161 hits · 926 pts

Severity	File	Line	Snippet	Context
HIGH⚡	tools/nightly/buildkite_testcase_statistics.py	880	const fileName = (fileDetail.dataset.testFile \|\| fileDetail.textContent \|\| "").toLowerCase();	CODE
HIGH⚡	tools/nightly/buildkite_testcase_statistics.py	881	const pathOk = !query \|\| fileName.includes(query);	CODE
HIGH⚡	tools/nightly/buildkite_testcase_statistics.py	886	const matched = pathOk && anyRowVisible;	CODE
HIGH	tools/nightly/generate_nightly_perf_excel.py	123	# and max_concurrency (null); leave those as-is. If they become float in the future, they are	COMMENT
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	652	if (value === null \|\| value === undefined) return "";	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	652	if (value === null \|\| value === undefined) return "";	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	662	const items = new Set(arr.filter(v => v !== null && v !== undefined && String(v).trim() !== ""));	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	667	if (v === null \|\| v === undefined) return null;	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	667	if (v === null \|\| v === undefined) return null;	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	668	if (typeof v === "number") return Number.isFinite(v) ? v : null;	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	670	if (!s \|\| s.toLowerCase() === "inf") return null;	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	670	if (!s \|\| s.toLowerCase() === "inf") return null;	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	672	return Number.isFinite(n) ? n : null;	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	1009	if (x < padLeft \|\| x > padLeft + innerW \|\| y < padTop \|\| y > padTop + innerH) {{	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	1016	let best = null;	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	1022	if (!best \|\| dist < best.dist) {{	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	1031	.filter(([, value]) => value !== null && value !== undefined && String(value).trim() !== "")	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	1183	if (filters.model && String(row[filters.modelKey] \|\| "") !== filters.model) return false;	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	1184	if (filters.testName && String(row.test_name \|\| "") !== filters.testName) return false;	CODE
HIGH⚡	tools/nightly/generate_nightly_perf_html.py	1185	if (filters.datasetName && String(row[filters.datasetKey] \|\| "") !== filters.datasetName) return false;	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	708	row.max_concurrency !== undefined && row.max_concurrency !== null ? `c${{row.max_concurrency}}` : "",	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	709	row.num_prompts !== undefined && row.num_prompts !== null ? `p${{row.num_prompts}}` : "",	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	724	row.max_concurrency !== undefined && row.max_concurrency !== null ? `c${{row.max_concurrency}}` : "",	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	725	row.num_prompts !== undefined && row.num_prompts !== null ? `p${{row.num_prompts}}` : "",	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	737	const raw = value === null \|\| value === undefined ? "" : String(value);	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	790	if (previous && values.map((v) => String(v)).includes(String(previous))) {{	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	875	if (display.title && display.title !== display.text) {{	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	894	const dpr = window.devicePixelRatio \|\| 1;	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	916	xLabels.push(p.x);	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1061	.filter((value) => value !== null && value !== undefined && String(value).trim() !== "")	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1066	if (y === null) return;	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1078	seriesByKey.get(key).points.push({{ x: dateStr, y, meta }});	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1104	if (latest && latest.date) {{	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1105	lines.push(`date: <code>${{escapeHtml(formatDate(latest.date))}}</code>`);	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1116	lines.push(`${{escapeHtml(keyName)}}: <code>${{escapeHtml(String(latest[keyName]))}}</code>`);	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1120	if (value) lines.push(`${{escapeHtml(metric)}}: <code>${{value}}</code>`);	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1138	if (!r \|\| r.width < 10 \|\| r.height < 10) return;	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1198	if (filters.backend && String(row[filters.backendKey] \|\| "") !== filters.backend) return false;	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1215	const values = rows.map((row) => toNumber(row[key])).filter((v) => v !== null);	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1405	if (extraKey && extraInput && !extraInput.value.trim()) {{	CODE
HIGH	tools/nightly/generate_nightly_perf_html.py	1417	const latest = filteredAsc[filteredAsc.length - 1] \|\| null;	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	446	assert cancelled.push(torch.ones(4), False) is None	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	448	assert replacement.push(torch.full((4,), 2.0), False).tolist() == [2.0] * 4	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	470	assert state.push(torch.ones(4), False).numel() == 4	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	471	assert state.push(torch.ones(4), False) is None	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	472	assert state.push(torch.ones(4), True).numel() == 8	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	515	assert state.push(np.arange(8, dtype=np.float32), False) is None	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	518	chunk = state.push(torch.arange(8, 12, dtype=torch.bfloat16), True)	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	523	assert state.push(np.ones(4, dtype=np.float32), False) is None	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	524	assert replacement.push(np.full(4, 99, dtype=np.float32), False).tolist() == [99] * 4	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	525	replacement.push(np.ones(4, dtype=np.float32), False)	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	753	assert replacement.push(torch.full((4,), 99), False).tolist() == [99] * 4	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	761	assert state.push(torch.arange(4), False) is None	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	763	assert state.push(torch.arange(4, 8), False) is None	CODE
HIGH⚡	tests/worker_v2/test_omni_ar_model_runner.py	764	chunk = state.push(torch.arange(8, 12), True)	CODE
HIGH	tests/worker_v2/test_omni_ar_model_runner.py	582	request.push(torch.ones(4), False)	CODE
HIGH	tests/worker_v2/test_omni_ar_model_runner.py	583	request.push(torch.ones(4), False)	CODE
HIGH	tests/diffusion/attention/test_attention_sp.py	382	"""Packed cu_seqlens combined with joint attention is undefined; fail closed."""	STRING
HIGH⚡	tests/diffusion/ar_diffusion/test_slot_mapping.py	61	Every slot for the in-flight chunk must land inside a real (non-null) block	STRING
HIGH⚡	tests/diffusion/utils/test_chunked_video.py	95	session.push(torch.zeros(1, 3, 4, 16, 32))	CODE
101 more matches not shown…

Cross-File Repetition154 hits · 770 pts

Severity	File	Line	Snippet	Context
HIGH	…buted/omni_connectors/test_bagel_mooncake_connector.py	0	validate that image pixels match expected reference values. args: image: the pil image to validate. reference_pixels: li	STRING
HIGH	…/omni_connectors/test_bagel_shared_memory_connector.py	0	validate that image pixels match expected reference values. args: image: the pil image to validate. reference_pixels: li	STRING
HIGH	…line_inference/test_sensenova_u1_text2img_expansion.py	0	validate that image pixels match expected reference values. args: image: the pil image to validate. reference_pixels: li	STRING
HIGH	…fline_inference/test_sensenova_u1_img2img_expansion.py	0	validate that image pixels match expected reference values. args: image: the pil image to validate. reference_pixels: li	STRING
HIGH	…l_executor/models/voxcpm2/test_talker_output_marker.py	0	defer talker import (pulls vllm model_executor) until first use.	STRING
HIGH	…_executor/models/voxcpm2/test_talker_state_eviction.py	0	defer talker import (pulls vllm model_executor) until first use.	STRING
HIGH	…executor/models/voxcpm2/test_request_seed_cfm_noise.py	0	defer talker import (pulls vllm model_executor) until first use.	STRING
HIGH	…del_executor/models/moss_tts/test_per_request_codes.py	0	defer talker import (pulls vllm model_executor) until first use.	STRING
HIGH	…ecutor/models/cosyvoice3/test_cosyvoice3_components.py	0	pin torch_sdpa so cpu shape tests do not pick cuda-only backends (fa3).	STRING
HIGH	tests/diffusion/cache/test_cache_dit.py	0	pin torch_sdpa so cpu shape tests do not pick cuda-only backends (fa3).	STRING
HIGH	…ion/models/boogu_image/test_boogu_image_transformer.py	0	pin torch_sdpa so cpu shape tests do not pick cuda-only backends (fa3).	STRING
HIGH	…models/mammoth_moda2/test_pipeline_mammothmoda2_dit.py	0	pin torch_sdpa so cpu shape tests do not pick cuda-only backends (fa3).	STRING
HIGH	…s/e2e/offline_inference/test_qwen2_5_omni_expansion.py	0	test audio and text input processing and text/audio output generation via openai api. deploy setting: default yaml input	STRING
HIGH	tests/e2e/online_serving/test_qwen3_tts_customvoice.py	0	test audio and text input processing and text/audio output generation via openai api. deploy setting: default yaml input	STRING
HIGH	tests/e2e/online_serving/test_qwen3_tts_base.py	0	test audio and text input processing and text/audio output generation via openai api. deploy setting: default yaml input	STRING
HIGH	tests/e2e/online_serving/test_qwen2_5_omni_expansion.py	0	test audio and text input processing and text/audio output generation via openai api. deploy setting: default yaml input	STRING
HIGH	tests/e2e/online_serving/test_qwen3_omni.py	0	test audio and text input processing and text/audio output generation via openai api. deploy setting: default yaml input	STRING
HIGH	docs/contributing/ci/test_writing_guide.md	0	test audio and text input processing and text/audio output generation via openai api. deploy setting: default yaml input	STRING
HIGH	tests/e2e/online_serving/test_mimo_audio_expansion.py	0	test audio and text input processing and text/audio output generation via openai api. deploy setting: default yaml input	STRING
HIGH	…ts/e2e/online_serving/test_qwen3_tts_base_expansion.py	0	e2e online tests for qwen3-tts model with text input and audio output. these tests verify the /v1/audio/speech endpoint	STRING
HIGH	…online_serving/test_qwen3_tts_customvoice_expansion.py	0	e2e online tests for qwen3-tts model with text input and audio output. these tests verify the /v1/audio/speech endpoint	STRING
HIGH	tests/e2e/online_serving/test_qwen3_tts_customvoice.py	0	e2e online tests for qwen3-tts model with text input and audio output. these tests verify the /v1/audio/speech endpoint	STRING
HIGH	tests/e2e/online_serving/test_qwen3_tts_base.py	0	e2e online tests for qwen3-tts model with text input and audio output. these tests verify the /v1/audio/speech endpoint	STRING
HIGH	…ts/e2e/online_serving/test_qwen3_tts_base_expansion.py	0	text prompt for text-to-audio tests (same as test_qwen3_omni - beijing test case).	STRING
HIGH	…online_serving/test_qwen3_tts_customvoice_expansion.py	0	text prompt for text-to-audio tests (same as test_qwen3_omni - beijing test case).	STRING
HIGH	tests/e2e/online_serving/test_qwen3_tts_customvoice.py	0	text prompt for text-to-audio tests (same as test_qwen3_omni - beijing test case).	STRING
HIGH	tests/e2e/online_serving/test_qwen3_tts_base.py	0	text prompt for text-to-audio tests (same as test_qwen3_omni - beijing test case).	STRING
HIGH	…ts/e2e/online_serving/test_qwen3_tts_base_expansion.py	0	batch size for concurrent requests (same as test_qwen3_omni).	STRING
HIGH	…online_serving/test_qwen3_tts_customvoice_expansion.py	0	batch size for concurrent requests (same as test_qwen3_omni).	STRING
HIGH	tests/e2e/online_serving/test_qwen3_tts_customvoice.py	0	batch size for concurrent requests (same as test_qwen3_omni).	STRING
HIGH	tests/e2e/online_serving/test_qwen3_tts_base.py	0	batch size for concurrent requests (same as test_qwen3_omni).	STRING
HIGH	…ts/e2e/online_serving/test_qwen3_tts_base_expansion.py	0	test text input processing and audio output via openai api. deploy setting: default yaml input modal: text output modal:	STRING
HIGH	…online_serving/test_qwen3_tts_customvoice_expansion.py	0	test text input processing and audio output via openai api. deploy setting: default yaml input modal: text output modal:	STRING
HIGH	tests/e2e/online_serving/test_qwen3_tts_customvoice.py	0	test text input processing and audio output via openai api. deploy setting: default yaml input modal: text output modal:	STRING
HIGH	tests/e2e/online_serving/test_qwen3_tts_base.py	0	test text input processing and audio output via openai api. deploy setting: default yaml input modal: text output modal:	STRING
HIGH	tests/e2e/online_serving/test_qwen_image.py	0	return a single default ``omniserverparams`` row (no extra ``server_args``).	STRING
HIGH	tests/e2e/online_serving/test_qwen_image_layered.py	0	return a single default ``omniserverparams`` row (no extra ``server_args``).	STRING
HIGH	tests/e2e/online_serving/test_boogu_image.py	0	return a single default ``omniserverparams`` row (no extra ``server_args``).	STRING
HIGH	tests/e2e/online_serving/test_qwen2_5_omni_expansion.py	0	test text input processing and text-only output generation via openai api. deploy setting: default yaml input modal: tex	STRING
HIGH	tests/e2e/online_serving/test_qwen3_omni.py	0	test text input processing and text-only output generation via openai api. deploy setting: default yaml input modal: tex	STRING
HIGH	tests/e2e/online_serving/test_mimo_audio_expansion.py	0	test text input processing and text-only output generation via openai api. deploy setting: default yaml input modal: tex	STRING
HIGH	…mples/offline_inference/text_to_image/text_to_image.py	0	parse a cli value as a json object, attributing errors to ``flag_name``.	STRING
HIGH	examples/offline_inference/qwen2_5_omni/end2end.py	0	parse a cli value as a json object, attributing errors to ``flag_name``.	STRING
HIGH	…offline_inference/text_to_speech/cosyvoice3/end2end.py	0	parse a cli value as a json object, attributing errors to ``flag_name``.	STRING
HIGH	…les/offline_inference/image_to_video/image_to_video.py	0	parse a cli value as a json object, attributing errors to ``flag_name``.	STRING
HIGH	…ne_serving/text_to_speech/moss_tts_nano/gradio_demo.py	0	<div id="tts-player"> <div style="display:flex; align-items:center; gap:10px;"> <div id="tts-status-dot" style="width:10	STRING
HIGH	…online_serving/text_to_speech/qwen3_tts/gradio_demo.py	0	<div id="tts-player"> <div style="display:flex; align-items:center; gap:10px;"> <div id="tts-status-dot" style="width:10	STRING
HIGH	…s/online_serving/text_to_speech/voxcpm2/gradio_demo.py	0	<div id="tts-player"> <div style="display:flex; align-items:center; gap:10px;"> <div id="tts-status-dot" style="width:10	STRING
HIGH	…ne_serving/text_to_speech/moss_tts_nano/gradio_demo.py	0	<script> const sr = {sample_rate}; const wc = {json.dumps(worklet_js)}; let ctx = null, node = null, abort = null, gen =	STRING
HIGH	…s/online_serving/text_to_speech/voxcpm2/gradio_demo.py	0	<script> const sr = {sample_rate}; const wc = {json.dumps(worklet_js)}; let ctx = null, node = null, abort = null, gen =	STRING
HIGH	…online_serving/text_to_speech/qwen3_tts/gradio_demo.py	0	<script> const sr = {sample_rate}; const wc = {json.dumps(worklet_js)}; let ctx = null, node = null, abort = null, gen =	STRING
HIGH	…ne_serving/text_to_speech/moss_tts_nano/gradio_demo.py	0	encode gradio audio input (sample_rate, numpy_array) to base64 data url.	STRING
HIGH	…s/online_serving/text_to_speech/glm_tts/gradio_demo.py	0	encode gradio audio input (sample_rate, numpy_array) to base64 data url.	STRING
HIGH	…line_serving/text_to_speech/fish_speech/gradio_demo.py	0	encode gradio audio input (sample_rate, numpy_array) to base64 data url.	STRING
HIGH	…/online_serving/text_to_speech/qwen3_tts/tts_common.py	0	encode gradio audio input (sample_rate, numpy_array) to base64 data url.	STRING
HIGH	…ne_serving/text_to_speech/moss_tts_nano/gradio_demo.py	0	#generate-btn button { width: 100%; } #streaming-player { border: 1px solid var(--border-color-primary) !important; bord	STRING
HIGH	…s/online_serving/text_to_speech/voxcpm2/gradio_demo.py	0	#generate-btn button { width: 100%; } #streaming-player { border: 1px solid var(--border-color-primary) !important; bord	STRING
HIGH	…online_serving/text_to_speech/qwen3_tts/gradio_demo.py	0	#generate-btn button { width: 100%; } #streaming-player { border: 1px solid var(--border-color-primary) !important; bord	STRING
HIGH	…ne_serving/text_to_speech/moss_tts_nano/gradio_demo.py	0	<div style="text-align:center; padding:8px 0; margin-top:4px;"> <a href="https://github.com/vllm-project/vllm-omni" targ	STRING
HIGH	…s/online_serving/text_to_speech/voxcpm2/gradio_demo.py	0	<div style="text-align:center; padding:8px 0; margin-top:4px;"> <a href="https://github.com/vllm-project/vllm-omni" targ	STRING
94 more matches not shown…

Modern Structural Boilerplate753 hits · 750 pts

Severity	File	Line	Snippet	Context
LOW	tools/nightly/generate_nightly_perf_excel.py	768	def _set_column_width(ws, columns: Sequence[str], col_name: str, width: int) -> None:	CODE
LOW⚡	tests/config/test_config_factory.py	3848	def set_files(self, files: list[tuple[str, str]]) -> None:	CODE
LOW	…del_executor/models/moss_tts/test_reference_encoder.py	42	def set_fail_values(self, values) -> None:	CODE
LOW	…utor/stage_input_processors/test_nemotron_voicechat.py	423	def set_init_inputs(self, speaker_name: str) -> None:	CODE
LOW	tests/model_tests/diffusion/utils.py	14	logger = logging.getLogger(__name__)	CODE
LOW⚡	tests/diffusion/test_diffusion_step_pipeline.py	67	def _update_environment_variables(envs_dict: dict[str, str]) -> None:	CODE
LOW	tests/diffusion/test_diffusion_step_pipeline.py	1208	def set_active_adapter(self, adapter, scale: float = 1.0) -> None:	CODE
LOW	tests/diffusion/distributed/test_comm.py	34	def _update_environment_variables(envs_dict: dict[str, str]) -> None:	CODE
LOW	tests/diffusion/distributed/test_boogu_image_sp.py	48	def _set_dist_env(rank: int, world_size: int, port: int) -> None:	CODE
LOW⚡	tests/diffusion/distributed/test_pipeline_parallel.py	340	def _set_rank(monkeypatch, world_size: int, first_stage: bool) -> None:	CODE
LOW	tests/diffusion/distributed/test_cfg_parallel.py	39	def _set_random_seeds(seed: int) -> None:	CODE
LOW	tests/diffusion/distributed/test_cfg_parallel.py	70	def _update_environment_variables(envs_dict: dict[str, str]) -> None:	CODE
LOW	…n/models/lingbot_world/test_lingbot_world_attention.py	117	def set_weight_attrs(weight: torch.Tensor, attrs: dict) -> None:	CODE
LOW	…n/models/lingbot_world/test_lingbot_world_attention.py	327	def _set_identity_attention(attention: nn.Module) -> None:	CODE
LOW	tests/diffusion/models/helios/test_helios_usp_2rank.py	82	def _update_env(envs_dict: dict[str, str]) -> None:	CODE
LOW	tests/diffusion/models/wan2_2/conftest.py	39	def set_timesteps(self, num_steps: int, device: torch.device, shift: float \| None = None) -> None:	CODE
LOW	…diffusion/models/wan2_2/test_wan22_pipeline_diffuse.py	64	def set_timesteps(self, num_steps: int, device: torch.device, shift: float \| None = None) -> None:	CODE
LOW	tests/diffusion/models/sdxl/test_sdxl_request_batch.py	33	def set_timesteps(self, num_steps: int) -> None:	CODE
LOW	…ts/diffusion/models/auk/test_auk_transformer_parity.py	269	def _set_mask_flag(reference, port, enabled: bool) -> None:	CODE
LOW	tests/diffusion/diffusion_kv/test_initialization.py	35	def set_kv_cache_configs(self, configs, resolved_max_model_len) -> None:	CODE
LOW	tests/dfx/reliability/helpers.py	34	logger = logging.getLogger(__name__)	CODE
LOW	…/entrypoints/openai_api/test_serving_audio_generate.py	30	logger = logging.getLogger(__name__)	CODE
LOW	tests/entrypoints/openai_api/test_serving_speech.py	85	logger = logging.getLogger(__name__)	CODE
LOW⚡	tests/e2e/features/helpers/custom_pipeline.py	37	logger = logging.getLogger(__name__)	CODE
LOW⚡	tests/e2e/features/helpers/custom_pipeline.py	262	def set_death_signal() -> None:	CODE
LOW	tests/e2e/features/helpers/verl_omni_server.py	31	logger = logging.getLogger(__name__)	CODE
LOW	…sts/e2e/accuracy/test_hunyuan_image3_pixel_accuracy.py	34	logger = logging.getLogger(__name__)	CODE
LOW⚡	tests/e2e/accuracy/test_diffusers_backend_similarity.py	69	def _set_matched_attention_backend(pipe: DiffusionPipeline) -> None:	CODE
LOW	…ts/e2e/online_serving/test_cosyvoice3_tts_expansion.py	53	def _set_rocm_request_timeout(request_config: dict) -> None:	CODE
LOW	tests/e2e/online_serving/minimax_h3/_common.py	348	__all__ = [	CODE
LOW	tests/engine/test_orchestrator_stage_input_bridge.py	69	def set_engine_outputs(self, _outputs) -> None:	CODE
LOW	tests/engine/test_orchestrator.py	154	def set_engine_outputs(self, outputs) -> None:	CODE
LOW	tests/engine/test_orchestrator.py	274	def update_scheduler_stats(self, _scheduler_stats) -> None:	CODE
LOW	tests/engine/test_duplex_orchestrator.py	134	async def _settle(orchestrator: DuplexOrchestrator, *, timeout_s: float = 3.0) -> None:	CODE
LOW	tests/engine/duplex/test_session_manager.py	443	async def _settle() -> None:	CODE
LOW	tests/helpers/media.py	32	logger = logging.getLogger(__name__)	CODE
LOW	tests/helpers/media.py	971	__all__ = [	CODE
LOW	tests/helpers/clean.py	20	logger = logging.getLogger(__name__)	CODE
LOW	tests/helpers/clean.py	276	__all__ = [	CODE
LOW	tests/helpers/monitor.py	55	__all__ = ["DeviceMemoryMonitor"]	CODE
LOW	tests/helpers/client.py	2270	__all__ = [	CODE
LOW	tests/helpers/assertions.py	1245	__all__ = [	CODE
LOW	tests/helpers/runtime.py	1308	__all__ = [	CODE
LOW	tests/helpers/distributed.py	52	def set_device(cls, device: torch.device) -> None:	CODE
LOW	tests/helpers/stage_config.py	780	__all__ = [	CODE
LOW	tests/helpers/kv_layout.py	21	__all__ = ["build_kv_cache_tensor", "layout_for_backend"]	CODE
LOW	tests/helpers/tests/test_cpu_threads.py	24	def set_num_threads(self, num_threads: int) -> None:	CODE
LOW	…ence/custom_pipeline/image_to_image/custom_pipeline.py	12	logger = logging.getLogger(__name__)	CODE
LOW⚡	…es/offline_inference/qwen3_omni/end2end_async_chunk.py	46	logger = logging.getLogger(__name__)	CODE
LOW	…es/offline_inference/text_to_speech/glm_tts/end2end.py	48	logger = logging.getLogger(__name__)	CODE
LOW	…ffline_inference/text_to_speech/fish_speech/end2end.py	38	logger = logging.getLogger(__name__)	CODE
LOW	…/offline_inference/text_to_speech/qwen3_tts/end2end.py	24	logger = logging.getLogger(__name__)	CODE
LOW	…ffline_inference/text_to_speech/voxtral_tts/end2end.py	35	logger = logging.getLogger(__name__)	CODE
LOW	examples/online_serving/minicpmo/realtime_web/server.py	16	__all__ = ["APP_DIR", "STATIC_DIR", "_join_ws_url", "build_app", "main"]	CODE
LOW	…mples/online_serving/minicpmo/realtime_web/__init__.py	5	__all__ = ["build_app"]	CODE
LOW	examples/online_serving/realtime_web/server.py	24	logger = logging.getLogger(__name__)	CODE
LOW	…e_serving/step_audio2/openai_chat_completion_client.py	34	logger = logging.getLogger(__name__)	CODE
LOW⚡	…ne_serving/text_to_speech/moss_tts_nano/gradio_demo.py	38	logger = logging.getLogger(__name__)	CODE
LOW⚡	…s/online_serving/text_to_speech/voxcpm2/gradio_demo.py	32	logger = logging.getLogger(__name__)	CODE
LOW	…rving/text_to_speech/qwen3_tts/word_timestamps_demo.py	47	logger = logging.getLogger(__name__)	CODE
693 more matches not shown…

Over-Commented Block462 hits · 428 pts

Severity	File	Line	Snippet	Context
LOW	tools/run_merge_jobs.sh	1	#!/usr/bin/env bash	COMMENT
LOW	tools/run_merge_jobs.sh	21	# Usage:	COMMENT
LOW	tools/run_ready_jobs.sh	1	#!/usr/bin/env bash	COMMENT
LOW	tools/run_ready_jobs.sh	21	# Usage:	COMMENT
LOW	tools/run_jobs_common.sh	1	#!/usr/bin/env bash	COMMENT
LOW	tools/nightly/run_nightly_jobs.sh	1	#!/usr/bin/env bash	COMMENT
LOW	tools/nightly/run_nightly_jobs.sh	21	# function — label has neither "Perf Test" nor "Accuracy Test" (incl. Doc, Multi-Replica, etc.)	COMMENT
LOW	tools/nightly/run_nightly_jobs.sh	41	# From repo root: pytest -sv -m "<markers> and local_model" (markers from MODEL_TYPE: omni, tts,	COMMENT
LOW	tools/nightly/run_nightly_jobs.sh	61	# YML=/path/to/vllm-omni/.buildkite/cuda/test-nightly.yml bash path/to/run_nightly_jobs.sh	COMMENT
LOW	tests/clients/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/attention/test_fish_kvcache_attn.py	281	assert captured["value"] == expected	COMMENT
LOW	tests/model_executor/models/voxcpm2/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	…s/model_executor/models/nemotron_voicechat/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	…_executor/models/nemotron_voicechat/duplex/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	…l_executor/models/common/test_fused_group_norm_silu.py	41	H, W = spatial_size	COMMENT
LOW	tests/model_executor/models/personaplex/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	…s/model_executor/models/personaplex/duplex/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/model_executor/models/minicpmo_4_5/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/model_executor/executor_common/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/model_executor/executor_common/duplex/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/model_executor/executor_common/audio/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	…executor/quantization/test_modelopt_nvfp4_nan_clamp.py	181	def test_install_is_self_asserting():	COMMENT
LOW	tests/model_tests/diffusion/config_types.py	81	# as core models to always run in the CI.	COMMENT
LOW	tests/model_tests/diffusion/model_settings.py	21	# The model will only be loaded once per test group, and will execute each of its	COMMENT
LOW	tests/model_tests/diffusion/test_alignment.py	21	# initializing the server).	COMMENT
LOW	tests/protocol/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/protocol/duplex/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/protocol/realtime/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/diffusion/attention/test_flash_attn.py	541	# NPU mask-free packed attention (PR #5891).	COMMENT
LOW	tests/diffusion/models/pi0/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/diffusion/models/pi0/test_pi0_units.py	481	masks = [bool(m.item()) for m in image_masks]	COMMENT
LOW	tests/diffusion/models/pi05/test_pi05_units.py	681	observation = {	COMMENT
LOW	tests/diffusion/models/pi05/test_pi05_units.py	701	# shape-driven. Full-scale numerical correctness is ``test_pi05_parity.py``'s	COMMENT
LOW	tests/diffusion/models/pi05/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	…s/hunyuan_image3/test_hunyuan_image3_it2i_ar_format.py	61	# it kept skipping because instantiating	COMMENT
LOW	tests/diffusion/models/anima/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/diffusion/models/lingbot_video/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/diffusion/models/hunyuan_video/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	…dels/boogu_image/test_pipeline_boogu_image_batching.py	741	# Negative control: force an all-ones mask (ignore real padding). A's row	COMMENT
LOW	…ion/models/boogu_image/test_boogu_image_transformer.py	801	# softmax weight on a correctly-excluded position exactly zero regardless	COMMENT
LOW	tests/diffusion/models/minimax_h3/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/diffusion/models/cosmos3/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/diffusion/quantization/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/rl_rollout/__init__.py	1	# SPDX-License-Identifier: Apache-2.0	COMMENT
LOW	tests/dfx/stability/scripts/resource_monitor.sh	1	#!/bin/bash	COMMENT
LOW	tests/entrypoints/test_pd_disaggregation.py	1161	_ = omni._prepare_prefill_sampling_params("req-1", sp)	COMMENT
LOW	tests/e2e/offline_inference/run_quantization_e2e.sh	1	#!/bin/bash	COMMENT
LOW	…racy/omni_duplex_eval/test_omni_duplex_eval_ci_mock.py	441	def test_summarize_scores_empty(score_root: Path) -> None:	COMMENT
LOW	tests/helpers/runtime.py	1141		COMMENT
LOW	requirements/common.txt	1	# Common dependencies for all platforms	COMMENT
LOW	recipes/cosmos3/Cosmos3-Nano.md	361		COMMENT
LOW	examples/offline_inference/lance/gradio_demo.py	41	# canonical (W, H) via:	COMMENT
LOW	examples/offline_inference/lance/gradio_demo.py	1021	)	COMMENT
LOW	examples/offline_inference/audex/speech_to_speech.py	41	from vllm_omni.model_executor.models.audex.prompt import build_cond_prompt	COMMENT
LOW	…_inference/qwen3_omni/run_single_prompt_async_chunk.sh	1	#!/bin/bash	COMMENT
LOW	…ine_inference/qwen2_5_omni/strategy_stage_replica.yaml	1	# Composable-parallel strategy for Qwen2.5-Omni.	COMMENT
LOW	…mples/offline_inference/qwen2_5_omni/strategy_tp2.yaml	1	# Composable-parallel strategy for Qwen2.5-Omni: tensor-parallel the thinker.	COMMENT
LOW	…s/offline_inference/text_to_speech/moss_tts/end2end.py	161	gc.collect()	COMMENT
LOW	examples/online_serving/minicpmo/barge_in_serve.sh	1	#!/bin/bash	COMMENT
LOW	…line_serving/replica_data_parallel/wan2_2_ti2v_dp.yaml	1	# Replica data-parallel recipe for Wan2.2 TI2V-5B (video DiT).	COMMENT
402 more matches not shown…

AI Structural Patterns386 hits · 352 pts

Severity	File	Line	Context
LOW	…ributed/omni_connectors/test_chunk_transfer_adapter.py	565	CODE
LOW	tests/distributed/omni_connectors/test_tp_rank_aware.py	41	CODE
LOW	…stage_input_processors/test_fish_speech_async_chunk.py	17	CODE
LOW	…r/stage_input_processors/test_qwen3_tts_async_chunk.py	99	CODE
LOW	tests/diffusion/attention/test_attention_sp.py	146	CODE
LOW	tests/diffusion/ar_diffusion/test_paged_attention.py	41	CODE
LOW	…on/models/lingbot_world/test_pipeline_lingbot_world.py	307	CODE
LOW	…n/models/hunyuan_image3/test_hunyuan_image3_sampler.py	293	CODE
LOW	…ffusion/models/hunyuan_image3/test_multi_resolution.py	564	CODE
LOW	…iffusion/models/sana_video/test_sana_video_topology.py	25	CODE
LOW	tests/diffusion/quantization/test_quantization_fp8.py	112	CODE
LOW	…/diffusion/diffusion_backend/test_diffusers_backend.py	479	CODE
LOW	tests/profile/test_omni_torch_profiler.py	42	CODE
LOW	tests/entrypoints/openai_api/test_serving_speech.py	3611	CODE
LOW	tests/e2e/features/helpers/custom_pipeline.py	74	CODE
LOW	tests/e2e/features/helpers/custom_pipeline.py	514	CODE
LOW	tests/engine/test_orchestrator.py	106	CODE
LOW	…les/offline_inference/mimo_audio/process_speechdata.py	131	CODE
LOW	…line_inference/text_to_speech/moss_tts_nano/end2end.py	52	CODE
LOW	…/offline_inference/text_to_speech/indextts2/end2end.py	43	CODE
LOW	examples/online_serving/lance/openai_chat_client.py	17	CODE
LOW	…es/online_serving/image_to_image/openai_chat_client.py	31	CODE
LOW	…les/online_serving/text_to_image/openai_chat_client.py	17	CODE
LOW	benchmarks/lingbot_world/workload.py	261	CODE
LOW	benchmarks/accuracy/common.py	144	CODE
LOW	benchmarks/accuracy/image_to_image/gedit_bench.py	419	CODE
LOW	vllm_omni/tokenizers/mammoth_moda2_tokenizer.py	103	CODE
LOW	vllm_omni/experimental/fullduplex/client.py	503	CODE
LOW	…mni/experimental/fullduplex/mage_vl/serving/backend.py	31	CODE
LOW	vllm_omni/experimental/fullduplex/joyvl/memory/brain.py	21	CODE
LOW	…_omni/experimental/fullduplex/joyvl/decision/policy.py	26	CODE
LOW	vllm_omni/platforms/npu/worker/npu_model_runner.py	118	CODE
LOW	…ni/platforms/npu/worker/npu_generation_model_runner.py	658	CODE
LOW	vllm_omni/core/sched/omni_scheduler_mixin.py	733	CODE
LOW	vllm_omni/worker_v2/omni_ar_model_runner.py	721	CODE
LOW	…m_omni/model_executor/models/voxcpm2/minicpm4_paged.py	123	CODE
LOW	…executor/models/audio8_tts/configuration_audio8_tts.py	34	CODE
LOW	…executor/models/audio8_tts/configuration_audio8_tts.py	96	CODE
LOW	…executor/models/audio8_tts/configuration_audio8_tts.py	144	CODE
LOW	…l_executor/models/breeze_tts_2/configuration_breeze.py	12	CODE
LOW	vllm_omni/model_executor/models/breeze_tts_2/prompt.py	20	CODE
LOW	…model_executor/models/hunyuan_image3/hunyuan_image3.py	2236	CODE
LOW	vllm_omni/model_executor/models/cosyvoice3/utils.py	23	CODE
LOW	…/model_executor/models/cosyvoice3/code2wav_core/cfm.py	275	CODE
LOW	…el_executor/models/cosyvoice3/code2wav_core/hifigan.py	570	CODE
LOW	…el_executor/models/cosyvoice3/code2wav_core/hifigan.py	864	CODE
LOW	…el_executor/models/cosyvoice3/code2wav_core/hifigan.py	1163	CODE
LOW	vllm_omni/model_executor/models/glm_tts/glm_tts_dit.py	475	CODE
LOW	vllm_omni/model_executor/models/glm_tts/glm_tts_dit.py	698	CODE
LOW	…i/model_executor/models/glm_tts/glm_tts_dit_wrapper.py	565	CODE
LOW	…m_omni/model_executor/models/glm_image/glm_image_ar.py	1437	CODE
LOW	…i/model_executor/models/gepard/configuration_gepard.py	40	CODE
LOW	…ecutor/models/fish_speech/configuration_fish_speech.py	23	CODE
LOW	…ecutor/models/fish_speech/configuration_fish_speech.py	77	CODE
LOW	…executor/models/fish_speech/dac_modules/transformer.py	168	CODE
LOW	…model_executor/models/fish_speech/dac_modules/codec.py	239	CODE
LOW	…i/model_executor/models/fish_speech/dac_modules/rvq.py	35	CODE
LOW	…odel_executor/models/mimo_audio/mimo_audio_code2wav.py	1016	CODE
LOW	…executor/models/mimo_audio/modeling_audio_tokenizer.py	1135	CODE
LOW	…executor/models/mimo_audio/modeling_audio_tokenizer.py	1176	CODE
326 more matches not shown…

Docstring Block Structure62 hits · 310 pts

Severity	File	Line	Snippet	Context
HIGH	…buted/omni_connectors/test_bagel_mooncake_connector.py	122	Generate an image using Bagel model with configured parameters. Args: omni: The Omni instance to use for ge	STRING
HIGH	…/omni_connectors/test_bagel_shared_memory_connector.py	163	Generate an image using Bagel model with img2img pipeline. Args: omni: The Omni instance to use for generat	STRING
HIGH	…line_inference/test_sensenova_u1_text2img_expansion.py	120	Generate an image using SenseNova-U1 model with configured parameters. Args: omni: The Omni instance to use	STRING
HIGH	…fline_inference/test_sensenova_u1_img2img_expansion.py	127	Generate an edited image using SenseNova-U1 model with img2img pipeline. Args: omni: The Omni instance to u	STRING
HIGH	vllm_omni/distributed/omni_coordinator/load_balancer.py	47	Route a task to one of the available replicas. Args: task: The task to route. Not used by the rando	STRING
HIGH	vllm_omni/config/composable_parallel/apply.py	250	Overlay per-role strategy specs onto a merged stage list. Args: stages: the ``list[StageConfig]`` returned	STRING
HIGH	vllm_omni/model_executor/models/cosyvoice3/utils.py	253	Make mask tensor containing indices of padded part. See description of make_non_pad_mask. Args: length	STRING
HIGH	…/nemotron_voicechat/nemo_vendored/ear_tts_vae_codec.py	177	Converts a spectrogram back into a waveform using the overlap-add method. This function is an approximate inver	STRING
HIGH	…els/nemotron_voicechat/nemo_vendored/duplex_ear_tts.py	444	Retrieve a cached audio prompt latent and adapt it to the requested batch size. This fetches a latent	STRING
HIGH	…els/nemotron_voicechat/nemo_vendored/duplex_ear_tts.py	651	Returns a dictionary of initial inputs for inference, using registered buffers. Args: B (i	STRING
HIGH	…r/models/nemotron_voicechat/nemo_vendored/tokenizer.py	303	Adds a dictionary of special tokens (eos, pad, cls...). If special tokens are NOT in the vocabulary, they are	STRING
HIGH	…utor/models/nemotron_voicechat/nemo_vendored/fusion.py	346	Factory function to create the appropriate fusion module. Args: fuse_method: One of None, "add", "conc	STRING
HIGH	…ls/nemotron_voicechat/nemo_vendored/ear_tts_commons.py	50	Loads a configuration from a JSON or Python file. - For JSON files (`*.json`), it parses the file directly.	STRING
HIGH	…ls/nemotron_voicechat/nemo_vendored/ear_tts_commons.py	230	Finds the path of the latest checkpoint file or directory in a directory. The latest checkpoint is determined	STRING
HIGH	…m_omni/model_executor/models/minimax_music3/weights.py	262	Load the audio embedding table and the RVQ depth decoder in place. Args: vllm_config: The stage's config, u	STRING
HIGH	…m_omni/model_executor/models/minimax_music3/staging.py	46	Stage ``count`` entries of each row and return the device view. Args: values: One sequence of Pytho	STRING
HIGH	vllm_omni/model_executor/models/minimax_music3/dit.py	431	Solve an aligned condition into a vocoder latent ``[1, 128, T_mel]``. The previous window's latent is re-impose	STRING
HIGH	vllm_omni/model_executor/models/minimax_music3/dav.py	173	Decode a latent to interleaved stereo. Args: latent: ``[B, 128, T]`` vocoder latent. Retur	STRING
HIGH	…m_omni/model_executor/models/indextts2/utils/common.py	66	Make mask tensor containing indices of padded part. See description of make_non_pad_mask. Args: length	STRING
HIGH	…model_executor/models/qwen3_tts/qwen3_tts_tokenizer.py	68	Initialize tokenizer with HuggingFace `from_pretrained` style. Args: pretrained_model_name	STRING
HIGH	…odel_executor/stage_input_processors/minimax_music3.py	166	Emit the unconditioned companion for a guided MiniMax Music 3 request. Classifier-free guidance is not optional for	STRING
HIGH	vllm_omni/diffusion/registry.py	470	Initialize a diffusion model from the registry. This function: 1. Loads the model class from the registry 2	STRING
HIGH	vllm_omni/diffusion/data.py	1189	Find an available port with retry logic. Args: port: Initial port to check por	STRING
HIGH	vllm_omni/diffusion/attention/backends/registry.py	125	Register or override a diffusion backend implementation. Args: backend: The DiffusionAttentionBackendEnum m	STRING
HIGH	vllm_omni/diffusion/cache/selector.py	16	Get cache backend instance based on cache_backend string. This is a selector function that routes to the appropriat	STRING
HIGH	vllm_omni/diffusion/cache/teacache/extractors.py	1721	Get extractor function for given transformer class. String lookups match an exact registered name. Type lookup	STRING
HIGH	…omni/diffusion/cache/teacache/coefficient_estimator.py	224	Estimate polynomial coefficients from collected data. Args: poly_order: Order of polynomial fit (de	STRING
HIGH	vllm_omni/diffusion/cache/magcache/strategy.py	473	Get strategy function for given transformer class. This function looks up the strategy based on the exact transform	STRING
HIGH	vllm_omni/diffusion/distributed/sp_sharding.py	32	Shard a tensor along the specified dimension for sequence parallelism. The tensor is split into world_size chunks a	STRING
HIGH	vllm_omni/diffusion/distributed/parallel_state.py	617	Initialize Ulysses, Ring, and AllGather-KV process groups. AllGather-KV may be composed with Ulysses (the orth	STRING
HIGH	…ffusion/models/qwen_image_21/pipeline_qwen_image_21.py	498	Reconcile each contiguous ``<\|image_pad\|>`` run with one slot per 2x2 latent group. The transformer's joint seq	STRING
HIGH	…on/models/hunyuan_image3/hunyuan_image3_transformer.py	3122	The call function to the pipeline for generation. Args: prompt (`str` or `List[str]`):	STRING
HIGH	…ni/diffusion/models/glm_image/glm_image_transformer.py	64	Validate GLM-Image TP constraints without requiring a distributed context. Args: dim: Model hidden dimensio	STRING
HIGH	…ni/diffusion/models/glm_image/glm_image_transformer.py	419	Get cache for a specific layer. Args: layer_idx: Index of the layer (0-indexed). Returns:	STRING
HIGH	…mni/diffusion/models/sana_video/pipeline_sana_video.py	969	Function invoked when calling the pipeline for generation. Args: prompt (`str` or `list[st	STRING
HIGH	…lm_omni/diffusion/models/omnigen2/pipeline_omnigen2.py	817	Get prompt embeddings from the Qwen2 text encoder. Args: prompt: The prompt or list of pro	STRING
HIGH	…on/models/gr00t/dataio/state_action/action_chunking.py	131	Convert a relative action chunking to an absolute action chunking by applying the relative poses on top	STRING
HIGH	…on/models/gr00t/dataio/state_action/action_chunking.py	168	Convert action chunking to the specified action format. Must be implemented by subclasses. Arg	STRING
HIGH	…on/models/gr00t/dataio/state_action/action_chunking.py	259	Interpolate the joint action chunking to generate intermediate configurations. Uses linear interpolati	STRING
HIGH	…on/models/gr00t/dataio/state_action/action_chunking.py	338	Convert a relative joint action chunking to an absolute action chunking by adding the relative joint po	STRING
HIGH	…on/models/gr00t/dataio/state_action/action_chunking.py	373	Convert trajectory to the desired format. Args: action_format: The desired output format	STRING
HIGH	…on/models/gr00t/dataio/state_action/action_chunking.py	479	Interpolate the action chunking to generate intermediate poses. Uses linear interpolation for translat	STRING
HIGH	…on/models/gr00t/dataio/state_action/action_chunking.py	635	Convert trajectory to the desired format. Args: action_format: The desired output format	STRING
HIGH	…mni/diffusion/models/gr00t/dataio/state_action/pose.py	101	Compute relative transformation between two poses. For EndEffectorPose: Computes the relative transfor	STRING
HIGH	…mni/diffusion/models/gr00t/dataio/state_action/pose.py	243	Compute relative joint displacement. Args: other: Reference joint pose Returns:	STRING
HIGH	…ls/gr00t/dataio/state_action/state_action_processor.py	227	Reverse state processing (denormalization). Args: state: Dict mapping joint_group -> proce	STRING
HIGH	…ls/gr00t/dataio/state_action/state_action_processor.py	286	Apply action processing (absolute->relative conversion, normalization). Processing order: 1. C	STRING
HIGH	…ls/gr00t/dataio/state_action/state_action_processor.py	373	Reverse action processing (denormalization, relative->absolute conversion). Processing order:	STRING
HIGH	…iffusion/models/ernie_image/ernie_image_transformer.py	63	Validate ErnieImage TP constraints without requiring a distributed context. Args: heads: Number of attentio	STRING
HIGH	vllm_omni/diffusion/hooks/sequence_parallel.py	84	Get a parameter value from args or kwargs by name. Args: identifier: The parameter name to look up,	STRING
HIGH	vllm_omni/diffusion/hooks/sequence_parallel.py	621	Get a submodule by dotted name, supporting wildcards. Args: model: The root module. name: Dotted pa	STRING
HIGH	vllm_omni/diffusion/worker/diffusion_worker.py	1867	Execute a method on the worker. Args: method: Method name (str) or serialized callable (by	STRING
HIGH	vllm_omni/entrypoints/async_omni.py	135	Generate outputs for the given prompt(s) asynchronously. Coordinates multi-stage pipeline execution. Processes	STRING
HIGH	vllm_omni/entrypoints/openai/image_api_utils.py	34	Parse size string to width and height tuple. Args: size_str: Size in format "WIDTHxHEIGHT" (e.g., "1024x102	STRING
HIGH	vllm_omni/entrypoints/openai/api_server.py	1372	Generate speech audio from text using the loaded TTS model. Args: request: Speech synthesis request in Open	STRING
HIGH	vllm_omni/entrypoints/openai/api_server.py	2069	Generate images from text prompts using diffusion models. OpenAI DALL-E compatible endpoint for text-to-image gener	STRING
HIGH	vllm_omni/entrypoints/openai/api_server.py	2847	Retrieve metadata for a previously created video job. Args: video_id: Identifier returned by ``POST /v1/vid	STRING
HIGH	vllm_omni/entrypoints/openai/api_server.py	2875	Delete a stored video job and any generated output. In-flight jobs get a bounded engine abort, then frontend cancel	STRING
HIGH	vllm_omni/entrypoints/openai/api_server.py	2945	Download the generated file for a completed video job. Args: video_id: Identifier of the video job whose ou	STRING
HIGH	…ps/ComfyUI-vLLM-Omni/comfyui_vllm_omni/utils/format.py	32	Convert base64-encoded image to ComfyUI image tensor. Args: base64_str: Base64-encoded image string	STRING
2 more matches not shown…

Structural Annotation Overuse140 hits · 226 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/core/sched/test_generation_scheduler_restore.py	249	# Step 1: process_pending_chunks moves req-B out	COMMENT
LOW⚡	tests/core/sched/test_generation_scheduler_restore.py	254	# Step 2: simulate the try/except/finally pattern	COMMENT
LOW⚡	tests/core/sched/test_generation_scheduler_restore.py	263	# Step 3: verify request is restored	COMMENT
LOW⚡	…cutor/models/minicpmo_4_5/duplex/test_window_wiring.py	1463	# Step 1: worker reanchor runs	COMMENT
LOW⚡	…cutor/models/minicpmo_4_5/duplex/test_window_wiring.py	1473	# Step 2: Simulate second call with the same reanchor_id (e.g. reinjection or duplicate metadata)	COMMENT
LOW	tests/diffusion/attention/test_attention_sp.py	1028	# Step 1: Run without SP (baseline with ulysses_degree=1, ring_degree=1)	COMMENT
LOW	tests/diffusion/attention/test_attention_sp.py	1057	# Step 2: Run with SP enabled	COMMENT
LOW	tests/diffusion/attention/test_attention_sp.py	1089	# Step 3: Verify input consistency and compare outputs	COMMENT
LOW	…dels/boogu_image/test_pipeline_boogu_image_batching.py	502	# Step 1: run the real sequential (single-rank) forward once, capturing	COMMENT
LOW	…dels/boogu_image/test_pipeline_boogu_image_batching.py	531	# Step 2: replay the identical branches through the real dispatch/gather	COMMENT
LOW⚡	tests/e2e/offline_inference/test_moss_tts_realtime.py	166	# Step 1: locate the realtime processor module in the snapshot.	COMMENT
LOW⚡	tests/e2e/offline_inference/test_moss_tts_realtime.py	191	# Step 2: encode the reference audio clip via MOSS-Audio-Tokenizer.	COMMENT
LOW	tests/e2e/offline_inference/test_moss_tts_realtime.py	209	# Step 3: build the (L, 17) prefill grid.	COMMENT
LOW⚡	…ures/custom_pipeline/test_async_omni_collective_rpc.py	126	# Step 1: list_loras (the call that was crashing)	COMMENT
LOW⚡	…ures/custom_pipeline/test_async_omni_collective_rpc.py	130	# Step 2: generate (should still work after list_loras)	COMMENT
LOW⚡	.claude/skills/vllm-omni-test/SKILL.md	31	### Step 1: Classify Test Goal	COMMENT
LOW⚡	.claude/skills/vllm-omni-test/SKILL.md	37	### Step 2: Select Test Level	COMMENT
LOW⚡	.claude/skills/vllm-omni-test/SKILL.md	45	### Step 3: Pick Markers	COMMENT
LOW	.claude/skills/vllm-omni-test/SKILL.md	91	### Step 4: Generate Test Case Skeleton	COMMENT
LOW	.claude/skills/vllm-omni-test/SKILL.md	627	### Step 5: Wire Buildkite (when CI must run the new test)	COMMENT
LOW	.claude/skills/vllm-omni-test/SKILL.md	829	### Step 6: Run Tests	COMMENT
LOW	.claude/skills/vllm-omni-test/SKILL.md	856	### Step 7: Validate Result Quality	COMMENT
LOW	.claude/skills/precheck-pr/SKILL.md	21	### Step 1: Detect Base Branch	COMMENT
LOW	.claude/skills/precheck-pr/SKILL.md	31	### Step 2: Validate PR Title	COMMENT
LOW	.claude/skills/precheck-pr/SKILL.md	50	### Step 3: Categorize the PR	COMMENT
LOW	.claude/skills/precheck-pr/SKILL.md	62	### Step 4: Run Checklist	COMMENT
LOW	.claude/skills/precheck-pr/SKILL.md	74	### Step 5: Print Report	COMMENT
LOW	.claude/skills/add-diffusion-model/SKILL.md	21	## Step 0: Classify the Migration Path	COMMENT
LOW	.claude/skills/add-diffusion-model/SKILL.md	291	### Step 4: Register Model in registry.py	COMMENT
LOW	.claude/skills/add-diffusion-model/SKILL.md	311	### Step 5: Run, Test, Debug	COMMENT
LOW	.claude/skills/add-diffusion-model/SKILL.md	331	### Step 6: Add Example Scripts	COMMENT
LOW	.claude/skills/add-diffusion-model/SKILL.md	338	### Step 7: Update Documentation	COMMENT
LOW	.claude/skills/add-diffusion-model/SKILL.md	352	### Step 8: Add E2E Tests	COMMENT
LOW	.claude/skills/add-diffusion-model/SKILL.md	387	### Step 9: Add Cache-DiT Acceleration	COMMENT
LOW	.claude/skills/add-diffusion-model/SKILL.md	400	### Step 10: Add Parallelism Support	COMMENT
LOW	.claude/skills/add-diffusion-model/SKILL.md	441	### Step 11: Add CPU Offload Support	COMMENT
LOW	.claude/skills/add-diffusion-model/SKILL.md	478	### Step 12: Performance Profiling	COMMENT
LOW	…add-diffusion-model/references/parallelism-patterns.md	186	#### Step 1: Identify module boundaries	COMMENT
LOW	…add-diffusion-model/references/parallelism-patterns.md	208	#### Step 2: Handle inline operations	COMMENT
LOW	…add-diffusion-model/references/parallelism-patterns.md	227	#### Step 3: Write `_sp_plan`	COMMENT
LOW	.claude/skills/vllm-omni-npu-upgrade/SKILL.md	120	### Step 1: Preparation	COMMENT
LOW	.claude/skills/vllm-omni-npu-upgrade/SKILL.md	137	### Step 2: Analyze Omni-Specific Logic	COMMENT
LOW	.claude/skills/vllm-omni-npu-upgrade/SKILL.md	151	### Step 3: Update Base Class (OmniNPUModelRunner)	COMMENT
LOW	.claude/skills/vllm-omni-npu-upgrade/SKILL.md	173	### Step 4: Update AR Model Runner	COMMENT
LOW	.claude/skills/vllm-omni-npu-upgrade/SKILL.md	188	### Step 5: Update Generation Model Runner	COMMENT
LOW	.claude/skills/vllm-omni-npu-upgrade/SKILL.md	205	### Step 6: Update Imports	COMMENT
LOW	.claude/skills/vllm-omni-npu-upgrade/SKILL.md	226	### Step 7: Sync GPU-Side Omni Changes	COMMENT
LOW	.claude/skills/vllm-omni-npu-upgrade/SKILL.md	238	### Step 8: Validation	COMMENT
LOW	docs/design/feature/cfg_parallel.md	84	### Step 1: Inherit `CFGParallelMixin`	COMMENT
LOW	docs/design/feature/cfg_parallel.md	123	### Step 2: Call `diffuse`	COMMENT
LOW	docs/design/feature/tensor_parallel.md	46	### Step 1: Identify Linear Layers	COMMENT
LOW	docs/design/feature/tensor_parallel.md	54	### Step 2: Replace Linear Layers with Parallel Equivalents	COMMENT
LOW	docs/design/feature/tensor_parallel.md	148	### Step 3: Validate TP Constraints	COMMENT
LOW	docs/design/feature/pipeline_parallel.md	97	### Step 1: Inherit `PipelineParallelMixin` and `CFGParallelMixin`	COMMENT
LOW	docs/design/feature/pipeline_parallel.md	123	### Step 2: Make model forward and `predict_noise()` PP-aware	COMMENT
LOW	docs/design/feature/pipeline_parallel.md	159	### Step 3: Partition the transformer layers	COMMENT
LOW	docs/design/feature/pipeline_parallel.md	235	### Step 4: Use the standard denoising contract	COMMENT
LOW	docs/design/feature/hsdp.md	44	### Step 1: Identify Modules to Shard	COMMENT
LOW	docs/design/feature/hsdp.md	55	### Step 2: Define Shard Conditions	COMMENT
LOW	docs/design/feature/sequence_parallel.md	124	### Step 1: Understand Module Boundaries	COMMENT
80 more matches not shown…

Modern AI Meta-Vocabulary67 hits · 205 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/config/test_config_factory.py	811	# yaml ``pipeline:`` key selects cosmos3_omni_deploy and merges guardrails.	COMMENT
MEDIUM⚡	…n/models/hunyuan_image3/test_hunyuan_image3_sampler.py	307	# DiT scaffold token is masked.	COMMENT
MEDIUM	tests/e2e/offline_inference/test_audex_s2s.py	43	# the official temp-1.0 seed-0 draw hallucinates off-language text (yet closes	COMMENT
MEDIUM	…uracy/sana_video/test_sana_video_pipeline_alignment.py	413	# Isolate scheduler orchestration from native-attention error by	COMMENT
MEDIUM	…ts/e2e/online_serving/test_cosyvoice3_tts_expansion.py	33	# Official CosyVoice zero-shot prompt audio and its transcript. Vendored under	COMMENT
MEDIUM⚡	tests/engine/test_orchestrator_event_driven.py	74	# Parity: the legacy scenario matrix, re-run through the event-driven loop	COMMENT
MEDIUM	tests/engine/test_orchestrator_event_driven.py	92	# KV/queue gauges under the event-driven loop.	COMMENT
MEDIUM	tests/helpers/assertions.py	901	# may hallucinate extra context around the short utterance. Use	COMMENT
MEDIUM	requirements/common.txt	43	# Required for running the Cosmos3 model with guardrails enabled (default behavior).	COMMENT
MEDIUM	docs/design/module/entrypoints.md	140	### ENTRY-INV-001: Entrypoints adapt but do not orchestrate	COMMENT
MEDIUM	docs/design/module/engine_orchestration.md	69	# Engine orchestration	COMMENT
MEDIUM	docs/serving/speech_api.md	45	# Gepard-1.0 (zero-shot default voice; packaged gepard.yaml)	COMMENT
MEDIUM	docs/contributing/profiling.md	377	[Speech API](../serving/speech_api.md#orchestration-loop-experimental)) an idle	CODE
MEDIUM	docs/contributing/model/adding_tts_model.md	600	# Build context window: left_context + chunk	COMMENT
MEDIUM	…s/user_guide/examples/online_serving/text_to_speech.md	113	AuK accepts the complete instruction after you fill in the [local recipe template](../../../../recipes/Tencent/AuK-H100.	CODE
MEDIUM	recipes/cosmos3/Cosmos3-Nano.md	367	# guardrails off (policy serving emits robot actions; the guardrail stack is	COMMENT
MEDIUM	recipes/cosmos3/Cosmos3-Nano.md	368	# not part of it, so --no-guardrails is implied).	COMMENT
MEDIUM	examples/offline_inference/audex/speech_to_speech.py	54	# the official temp-1.0 seed-0 draw hallucinates off-language text (yet	COMMENT
MEDIUM	…mples/offline_inference/text_to_image/text_to_image.py	616	# Cosmos3 loads its (gated) guardrail models at build time, so the guardrails	COMMENT
MEDIUM	…mples/offline_inference/text_to_image/text_to_image.py	617	# gate is an engine-level config (offline analog of the server's --no-guardrails).	COMMENT
MEDIUM	…mples/offline_inference/text_to_video/text_to_video.py	599	# Cosmos3 loads its (gated) guardrail models at build time, so the guardrails	COMMENT
MEDIUM	…mples/offline_inference/text_to_video/text_to_video.py	600	# gate is an engine-level config (offline analog of the server's --no-guardrails).	COMMENT
MEDIUM	examples/offline_inference/text_to_speech/README.md	536	### Quick start (zero-shot, default voice)	COMMENT
MEDIUM	…offline_inference/text_to_speech/cosyvoice3/end2end.py	20	# Upstream zero-shot reference clip	COMMENT
MEDIUM	…les/offline_inference/image_to_video/image_to_video.py	617	# Cosmos3 loads its (gated) guardrail models at build time, so the guardrails	COMMENT
MEDIUM	…les/offline_inference/image_to_video/image_to_video.py	618	# gate is an engine-level config (offline analog of the server's --no-guardrails).	COMMENT
MEDIUM	examples/online_serving/audex/client.py	46	# official temp-1.0 seed-0 draw measurably hallucinates off-language text on	COMMENT
MEDIUM	examples/online_serving/audex/client.py	299	# hallucinate off-language answers (see the module-level comment).	COMMENT
MEDIUM	…ine_serving/text_to_speech/cosyvoice3/speech_client.py	30	# Official CosyVoice zero-shot prompt and its transcript.	COMMENT
MEDIUM	…les/online_serving/text_to_speech/gepard/run_server.sh	5	# Launch vLLM-Omni server for Gepard-1.0 TTS (zero-shot default voice).	COMMENT
MEDIUM	vllm_omni/data_entry_keys.py	22	# Internal output routing markers shared by first-frame producers and orchestration.	COMMENT
MEDIUM	…ctors/connectors/mooncake_transfer_engine_connector.py	172	# The orchestration layer (get_connectors_config_for_stage /	COMMENT
MEDIUM	vllm_omni/config/stage_config.py	1363	# overrides are deep-merged so a partial CLI dict (e.g. --no-guardrails	COMMENT
MEDIUM	vllm_omni/deploy/qwen3_tts_high_concurrency.yaml	12	# For CPU-bound frontend or orchestration workloads, this profile can be used	COMMENT
MEDIUM	vllm_omni/deploy/lance.yaml	6	# stage orchestration.	COMMENT
MEDIUM	vllm_omni/deploy/cosmos3_policy_droid.yaml	38	# of it. Equivalent to launching with --no-guardrails.	COMMENT
MEDIUM	vllm_omni/deploy/cosmos3_omni.yaml	14	# behaviour is unchanged (CLI single-stage fallback). --no-guardrails remains	COMMENT
MEDIUM	vllm_omni/deploy/cosmos3_omni.yaml	15	# the CLI-only equivalent of model_config.guardrails below. Per-checkpoint	COMMENT
MEDIUM	vllm_omni/deploy/cosmos3_omni.yaml	29	# recommended layout off. Equivalent to launching with --no-guardrails.	COMMENT
MEDIUM	…model_executor/models/audio8_tts/audio8_tts_slow_ar.py	667	# chat-template scaffolding.	COMMENT
MEDIUM	…model_executor/models/hunyuan_image3/hunyuan_image3.py	1593	# <cfg>, <img>, <timestep> and <joint_img_sep> are DiT-side scaffold	COMMENT
MEDIUM	…model_executor/models/hunyuan_image3/hunyuan_image3.py	1992	# The <timestep> slot at the head of each per-image scaffold is NOT	COMMENT
MEDIUM	…m_omni/model_executor/models/glm_image/glm_image_ar.py	401	# Append HF's target-shape scaffold without decoding/re-tokenizing the	COMMENT
MEDIUM	…i/model_executor/models/gepard/configuration_gepard.py	102	# Carried for the cloning follow-up; zero-shot uses null_prefix only.	COMMENT
MEDIUM	…el_executor/models/personaplex/personaplex_temporal.py	269	# Capacity = context window (the mask truncates at `context` anyway).	COMMENT
MEDIUM	…_omni/diffusion/models/hunyuan_image3/system_prompt.py	195	# Think task: use chain-of-thought recaption prompt	STRING
MEDIUM	vllm_omni/diffusion/models/lance/pipeline_lance.py	1863	# the chat scaffolding.	COMMENT
MEDIUM	…iffusion/models/qwen_image/pipeline_qwen_image_edit.py	399	# The edit template contains fixed multimodal scaffolding around the	COMMENT
MEDIUM	vllm_omni/diffusion/models/auk/pipeline_auk.py	65	# reference (instruct TTS) and a 3 s one (zero-shot). The first call compiles	COMMENT
MEDIUM	…/models/longcat_video/pipeline_longcat_video_avatar.py	53	# Whisper uses a 30-second context window: 30s * 16kHz raw samples,	COMMENT
MEDIUM	vllm_omni/diffusion/models/cosmos3/guardrails.py	65	# ``model_config["guardrails"]`` is False.	COMMENT
MEDIUM⚡	vllm_omni/diffusion/models/cosmos3/guardrails.py	133	# caller has opted in to guardrails.	COMMENT
MEDIUM	…quantization/tools/merge_mxfp4_dualscale_checkpoint.py	331	# BF16 base: provides the scaffold for non-MXFP4 tensors (norms, embeddings,	COMMENT
MEDIUM	…quantization/tools/merge_mxfp4_dualscale_checkpoint.py	378	# Merge: base_state provides BF16 scaffold; MXFP4 tensors override their BF16 counterparts	COMMENT
MEDIUM	vllm_omni/entrypoints/async_omni_base.py	37	# Blocking-wait interval for the event-driven final-output drain	COMMENT
MEDIUM	vllm_omni/entrypoints/async_omni_base.py	320	# event-driven loop (vllm_omni/engine/orchestrator.py).	COMMENT
MEDIUM	vllm_omni/entrypoints/cli/serve.py	152	# --no-guardrails is a CLI-only alias, not a diffusion engine arg.	COMMENT
MEDIUM	vllm_omni/entrypoints/cli/serve.py	1074	# Disable safety guardrails for this server (currently only applicable for Cosmos3)	COMMENT
MEDIUM	vllm_omni/entrypoints/openai/README.md	12	\| Shared media / serving utils \| root `image_api_utils.py`, `video_api_utils.py`, `audio_utils_mixin.py`, `utils.py` \| *	CODE
MEDIUM	vllm_omni/entrypoints/openai/serving_chat.py	792	# scaffold.	COMMENT
7 more matches not shown…

Self-Referential Comments63 hits · 182 pts

Severity	File	Line	Snippet	Context
MEDIUM	…ributed/omni_connectors/test_omni_connector_configs.py	23	# This file is 4 levels deep from root if we count from tests?	COMMENT
MEDIUM	tests/config/test_config_factory.py	1210	# Create the model	COMMENT
MEDIUM	tests/config/test_config_factory.py	1254	# Create the model	COMMENT
MEDIUM	tests/config/test_config_factory.py	1402	# Create a config with the autodetected type, and write the	COMMENT
MEDIUM	…s/model_executor/models/glm_image/test_glm_image_ar.py	172	# Create a mock for the parent parse_mm_data	COMMENT
MEDIUM	tests/diffusion/test_worker_wrapper_base.py	669	# Create a mock worker class with re_init_pipeline	COMMENT
MEDIUM	tests/diffusion/cache/test_cache_backends.py	431	# Create a cache config with an scm policy & enable it	COMMENT
MEDIUM	…iffusion/distributed/test_autoencoder_kl_wan_encode.py	220	# Create a simple task with 2 temporal chunks	COMMENT
MEDIUM⚡	tests/diffusion/distributed/test_sp_plan_hooks.py	560	# Create a test tensor	COMMENT
MEDIUM	tests/diffusion/distributed/test_sp_plan_hooks.py	577	# Create a test tensor with [text, image] concatenated	COMMENT
MEDIUM⚡	…n/models/wan2_2/test_wan22_quant_config_propagation.py	213	# Create a fake module that has WanRMS_norm	COMMENT
MEDIUM	tests/diffusion/models/ltx2/test_ltx2_pipeline.py	2259	# Create a minimal od_config mock	COMMENT
MEDIUM	…fusion/models/glm_image/test_glm_image_quantization.py	591	# Create a minimal mock od_config	COMMENT
MEDIUM	…els/sensenova_u1/test_sensenova_u1_logits_processor.py	52	# Create a vLLM config with a wrapped diffusion config	COMMENT
MEDIUM	tests/diffusion/quantization/test_hsdp_fp8.py	53	# Create the quant-method instance without calling __init__ (avoids	COMMENT
MEDIUM⚡	tests/benchmarks/duplex/test_omni_duplex_eval_media.py	180	# Create a long-GOP video: 3s @ 10fps = 30 frames, gop_size=30 (1 keyframe)	COMMENT
MEDIUM	tests/entrypoints/test_omni_entrypoints.py	1458	# Create a generator and start to evaluate it to make sure the request isn't aborted yet	COMMENT
MEDIUM	tests/entrypoints/openai_api/test_serving_speech.py	676	# Create a file larger than 10MB	COMMENT
MEDIUM	tests/entrypoints/openai_api/test_serving_speech.py	1183	# Create a TTS stage	COMMENT
MEDIUM	tests/entrypoints/openai_api/test_image_server.py	99	# Create a simple test image	COMMENT
MEDIUM	tests/worker/test_omni_gpu_model_runner.py	280	# Create an instance without calling OmniGPUModelRunner.__init__	COMMENT
MEDIUM	tests/engine/test_arg_utils.py	254	# Create a vLLM ModelConfig	COMMENT
MEDIUM	tests/engine/test_arg_utils.py	257	# Create a mock talking config with a dummy value for position_id_per_seconds	COMMENT
MEDIUM	docs/mkdocs/hooks/generate_examples.py	398	# Create the EXAMPLE_DOC_DIR if it doesn't exist	COMMENT
MEDIUM⚡	…ctors/connectors/mooncake_transfer_engine_connector.py	313	# Create a socket to determine the local IP used for external communication	COMMENT
MEDIUM	…del_executor/models/fish_speech/fish_speech_fast_ar.py	532	# Create a seeded generator for deterministic residual codebook sampling.	COMMENT
MEDIUM	…odel_executor/models/mimo_audio/mimo_audio_code2wav.py	1038	# Create an all-zero logits tensor (sampler will choose the first token, usually pad token)	COMMENT
MEDIUM⚡	…/nemotron_voicechat/nemo_vendored/ear_tts_vae_codec.py	98	# Create a range tensor from 0 to max_length - 1	COMMENT
MEDIUM	…/nemotron_voicechat/nemo_vendored/ear_tts_vae_codec.py	150	# Create the window tensor on the same device as the waveform.	COMMENT
MEDIUM	…els/nemotron_voicechat/nemo_vendored/duplex_ear_tts.py	375	# Create a random dropout decision for each BOS instance	COMMENT
MEDIUM	…els/nemotron_voicechat/nemo_vendored/duplex_ear_tts.py	386	# Create a mask of the same shape as target_text_tokens	COMMENT
MEDIUM	…dels/nemotron_voicechat/nemo_vendored/ear_tts_model.py	258	# Create a range tensor from 0 to max_length - 1	COMMENT
MEDIUM	…dels/nemotron_voicechat/nemo_vendored/ear_tts_model.py	431	# Create a new, dense character vocabulary sorted by the original token ID	COMMENT
MEDIUM	…dels/nemotron_voicechat/nemo_vendored/ear_tts_model.py	860	# Create a padded tensor for the character IDs	COMMENT
MEDIUM	…odels/nemotron_voicechat/nemo_vendored/asr/features.py	33	# This file contains code artifacts adapted from https://github.com/ryanleary/patter	COMMENT
MEDIUM	…otron_voicechat/nemo_vendored/asr/conformer_encoder.py	490	# Create the self-attention and padding masks	COMMENT
MEDIUM	…on_voicechat/nemo_vendored/asr/multi_head_attention.py	596	# Create a helper tensor to find the local indices of global attention	COMMENT
MEDIUM	…_tts/tokenizer_25hz/modeling_qwen3_tts_tokenizer_v1.py	210	"""This class implements an attentive statistic pooling layer for each channel.	STRING
MEDIUM	…lm_omni/model_executor/models/qwen3_omni/qwen3_omni.py	244	# Create a new vllm_config with thinker_config as the hf_config	COMMENT
MEDIUM	…lm_omni/model_executor/models/qwen3_omni/qwen3_omni.py	286	# Create a new vllm_config with talker_config as the hf_config	COMMENT
MEDIUM	…lm_omni/model_executor/models/qwen3_omni/qwen3_omni.py	337	# Create a new vllm_config with code2wav_config as the hf_config	COMMENT
MEDIUM	…l_executor/models/qwen3_omni/qwen3_omni_moe_thinker.py	1150	# Create the buffers on the target device explicitly. They are	COMMENT
MEDIUM	…el_executor/models/qwen3_omni/qwen3_omni_moe_talker.py	367	# Create a vllm_config for the talker's text model	COMMENT
MEDIUM	…executor/models/qwen2_5_omni/qwen2_5_omni_token2wav.py	170	"""This class implements an attentive statistic pooling layer for each channel.	STRING
MEDIUM	…_executor/models/minicpmo_4_5/minicpmo_4_5_omni_llm.py	4755	# Create a sequence tensor of shape (batch_size, max_seq_len)	COMMENT
MEDIUM	vllm_omni/diffusion/distributed/comm.py	251	# Create a contiguous buffer for receiving	COMMENT
MEDIUM	vllm_omni/diffusion/utils/kv_utils.py	45	# Create the boolean mask for the input sequences	COMMENT
MEDIUM	…ion/models/qwen_image_21/autoencoder_kl_qwenimage21.py	480	# Create the components	STRING
MEDIUM	…on/models/hunyuan_image3/hunyuan_image3_transformer.py	694	# This class is just for type hinting purposes. Attribute `i` should be defined	COMMENT
MEDIUM	vllm_omni/diffusion/models/bagel/mot/ops/mot_gemm.py	231	# Initialize VAE variables first and overwrite for Text	COMMENT
MEDIUM	…iffusion/models/qwen_image/autoencoder_kl_qwenimage.py	347	# Create the components	STRING
MEDIUM	…/scheduling_flow_match_euler_discrete_time_shifting.py	12	# This file is adapted by Boogu Team from prior open-source scheduler work.	COMMENT
MEDIUM	…mni/diffusion/models/nextstep_1_1/modeling_flux_vae.py	295	# Create a config-like object for compatibility	COMMENT
MEDIUM	…on/models/gr00t/dataio/state_action/action_chunking.py	203	# Create a joint action chunking	STRING
MEDIUM	…on/models/gr00t/dataio/state_action/action_chunking.py	399	# Create an end-effector action chunking	STRING
MEDIUM	…mni/diffusion/models/gr00t/dataio/state_action/pose.py	172	# Create a 6-DOF joint configuration	STRING
MEDIUM	vllm_omni/diffusion/hooks/sequence_parallel.py	6	# This module is adapted from HuggingFace diffusers library:	COMMENT
MEDIUM	vllm_omni/diffusion/worker/diffusion_worker.py	1720	# Create the actual worker instance. Only dynamic custom pipelines skip	COMMENT
MEDIUM	vllm_omni/benchmarks/data_modules/daily_omni_dataset.py	672	# Create an iterator-like wrapper for compatibility	COMMENT
MEDIUM	vllm_omni/entrypoints/utils.py	262	# The following code detects if the process is running in a container and if	COMMENT
3 more matches not shown…

Redundant / Tautological Comments85 hits · 128 pts

Severity	File	Line	Snippet	Context
LOW	tools/pre_commit/check_test_marks.py	50	# Check if a file is located under tests/ and matches test_<something>.py	COMMENT
LOW	tools/pre_commit/check_forbidden_imports.py	210	# Check if it's allowed	COMMENT
LOW	tests/distributed/omni_connectors/test_kv_flow.py	126	# Check if data was put into connector	COMMENT
LOW	…r/models/cosyvoice3/test_cosyvoice3_components_cuda.py	170	# Set TF32 to True initially to verify `finally` restoration	COMMENT
LOW	…_executor/models/higgs_audio_v3/test_higgs_audio_v3.py	142	# Set weights to identity-like pattern so we can verify offsets	COMMENT
LOW	…ts/diffusion/models/flux2/test_flux2_transformer_tp.py	246	# Check if to_out related weights are loaded	COMMENT
LOW⚡	tests/benchmarks/patch/test_patch.py	831	# Check if attribute exists and has a value (should be 0.0 or similar default)	COMMENT
LOW	tests/e2e/offline_inference/compute_lpips.py	95	# Print results table	COMMENT
LOW	tests/e2e/features/helpers/custom_pipeline.py	342	# Check if model is a local path	COMMENT
LOW	tests/helpers/stage_config.py	90	# Check if next key is a digit (list index) or string (dict key)	COMMENT
LOW	tests/helpers/stage_config.py	224	# Check if this is a simple key (not dot-separated)	COMMENT
LOW	examples/offline_inference/step_audio2/end2end.py	203	# Check if it's a local path	COMMENT
LOW	examples/offline_inference/image_to_image/image_edit.py	788	# Check if this is a layered output (list of images)	COMMENT
LOW	examples/offline_inference/image_to_image/image_edit.py	799	# Check if this is a layered output (list of images)	COMMENT
LOW	…ai_chat_completion_client_for_multimodal_generation.py	60	# Check if it's a URL (starts with http:// or https://)	COMMENT
LOW	…ai_chat_completion_client_for_multimodal_generation.py	99	# Check if it's a URL (starts with http:// or https://)	COMMENT
LOW	…ai_chat_completion_client_for_multimodal_generation.py	136	# Check if it's a URL (starts with http:// or https://)	COMMENT
LOW	…ai_chat_completion_client_for_multimodal_generation.py	64	# Check if it's a URL (starts with http:// or https://)	COMMENT
LOW	…ai_chat_completion_client_for_multimodal_generation.py	103	# Check if it's a URL (starts with http:// or https://)	COMMENT
LOW	…ai_chat_completion_client_for_multimodal_generation.py	141	# Check if it's already a base64 data URL	COMMENT
LOW	…ai_chat_completion_client_for_multimodal_generation.py	145	# Check if it's a URL (starts with http:// or https://)	COMMENT
LOW	examples/online_serving/lance/openai_chat_client.py	49	# Check if local file	COMMENT
LOW	examples/online_serving/qwen3_omni/run_gradio_demo.sh	154	# Check if startup flag file exists (startup complete)	COMMENT
LOW	examples/online_serving/qwen3_omni/run_gradio_demo.sh	163	# Check if server process is still running	COMMENT
LOW	examples/online_serving/qwen2_5_omni/run_gradio_demo.sh	154	# Check if startup flag file exists (startup complete)	COMMENT
LOW	examples/online_serving/qwen2_5_omni/run_gradio_demo.sh	163	# Check if server process is still running	COMMENT
LOW	…online_serving/text_to_speech/qwen3_tts/gradio_demo.py	368	# Check if this is a request ID referencing a stored payload	COMMENT
LOW	benchmarks/build_dataset/extract_tts_prompts.py	45	# Print result stats	COMMENT
LOW	benchmarks/build_dataset/extract_tts_prompts.py	64	# Check if input file exists	COMMENT
LOW	vllm_omni/platforms/cuda/platform.py	106	# Check if FA packages are available	COMMENT
LOW	vllm_omni/platforms/musa/platform.py	72	# Check if FA packages are available	COMMENT
LOW	vllm_omni/platforms/rocm/platform.py	95	# Check if aiter is available for Flash Attention support	COMMENT
LOW⚡	…ctors/connectors/mooncake_transfer_engine_connector.py	1104	# Check if this is a query request	COMMENT
LOW⚡	…mni/distributed/omni_connectors/utils/serialization.py	210	# Check if this looks like an OmniRequestOutput (check before RequestOutput	COMMENT
LOW⚡	…mni/distributed/omni_connectors/utils/serialization.py	215	# Check if this looks like a RequestOutput	COMMENT
LOW⚡	…mni/distributed/omni_connectors/utils/serialization.py	219	# Check if this looks like a CompletionOutput	COMMENT
LOW	vllm_omni/plugins/__init__.py	34	# Check if the only discovered plugin is the default one.	COMMENT
LOW	…model_executor/models/hunyuan_image3/hunyuan_image3.py	1833	# Check if T dimension is 1, then squeeze it	COMMENT
LOW	…m_omni/model_executor/models/glm_image/glm_image_ar.py	178	# Check if we're in a subdirectory (vision_language_encoder)	COMMENT
LOW	…m_omni/model_executor/models/glm_image/glm_image_ar.py	582	# Check if there are any images to process	COMMENT
LOW	…m_omni/model_executor/models/glm_image/glm_image_ar.py	2445	# Check if this is a text-to-image request:	COMMENT
LOW	…m_omni/model_executor/models/glm_image/glm_image_ar.py	2477	# Check if there's a token after this start and it's an image token	COMMENT
LOW	…odel_executor/models/mimo_audio/mimo_audio_code2wav.py	974	# Check if in CUDA graph capture phase	COMMENT
LOW	…lm_omni/model_executor/models/mimo_audio/mimo_audio.py	881	# Check if in CUDA graph capture phase	COMMENT
LOW	…_executor/models/minicpmo_4_5/minicpmo_4_5_omni_llm.py	477	# Check if the args are a device or a dtype	STRING
LOW	…mni/model_executor/stage_input_processors/glm_image.py	338	# Check if elements are tensors or Python lists	COMMENT
LOW	…_omni/model_executor/stage_input_processors/glm_tts.py	340	# Check if enough tokens accumulated for next chunk	COMMENT
LOW	…i/diffusion/offloader/distributed_layerwise_backend.py	1230	# Check if this buffer is non-persistent on its OWNING module	COMMENT
LOW	vllm_omni/diffusion/attention/parallel/ulysses.py	578	# Check if Ring Attention is also active (Hybrid mode)	COMMENT
LOW	vllm_omni/diffusion/cache/cachedit/model_specific.py	58	# Set timesteps to calculate the split	COMMENT
LOW	vllm_omni/diffusion/distributed/sp_plan.py	452	# Check if it's an output specification (SequenceParallelOutput or list/tuple thereof)	COMMENT
LOW	vllm_omni/diffusion/distributed/cfg_parallel.py	320	# Assign branches to ranks via round-robin	COMMENT
LOW	…lm_omni/diffusion/models/wan2_2/pipeline_wan2_2_i2v.py	241	# Check if this is a two-stage model (MoE with transformer_2)	COMMENT
LOW	vllm_omni/diffusion/models/wan2_2/pipeline_wan2_2.py	406	# Check if this is a two-stage model (MoE with transformer_2)	COMMENT
LOW	…ffusion/models/qwen_image_21/pipeline_qwen_image_21.py	350	# Check if model is a local path	COMMENT
LOW	vllm_omni/diffusion/models/flux/pipeline_flux.py	106	# Check if model is a local path	COMMENT
LOW	…_omni/diffusion/models/glm_image/pipeline_glm_image.py	757	# Check if prior_token_ids are provided externally (from AR stage in multistage mode)	COMMENT
LOW	…ni/diffusion/models/glm_image/glm_image_transformer.py	573	# Check if SP is enabled	COMMENT
LOW	vllm_omni/diffusion/models/flux2/pipeline_flux2.py	239	# Check if it's a list of lists or a list of images	COMMENT
LOW	vllm_omni/diffusion/models/flux2/pipeline_flux2.py	385	# Check if model is a local path	COMMENT
25 more matches not shown…

Hallucination Indicators10 hits · 102 pts

Severity	File	Line	Snippet	Context
CRITICAL	…executor/models/minicpmo_4_5/test_code2wav_batching.py	768	token2wav.flow.decoder.estimator.cfg_batches.clear()	CODE
CRITICAL	tests/diffusion/test_ray_executor.py	441	actor.check_alive.options.return_value.remote.assert_called_once_with()	CODE
CRITICAL	…diffusion/distributed/test_wan_vae_fastpath_install.py	316	grad_strides = vae.decoder.conv_out.weight.grad.stride()	CODE
CRITICAL	…diffusion/distributed/test_wan_vae_fastpath_install.py	336	assert vae.decoder.conv_out.weight.grad.stride() == grad_strides	CODE
CRITICAL	…diffusion/models/sensenova_u1/test_sensenova_u1_moe.py	150	layer.mlp.experts.routed_experts.w13_weight.zero_()	CODE
CRITICAL	tests/helpers/client.py	1503	with self.client.audio.speech.with_streaming_response.create(	CODE
CRITICAL	tests/helpers/client.py	1543	with self.client.audio.speech.with_streaming_response.create(	CODE
CRITICAL⚡	…executor/models/qwen2_5_omni/qwen2_5_omni_token2wav.py	1298	self.codec_embed_size = self.code2wav_dit_model.text_embed.codec_embed.weight.size(0)	STRING
CRITICAL⚡	vllm_omni/diffusion/models/gr00t/modeling/gr00t_n1d7.py	321	self.model.model.language_model.layers.pop(-1)	CODE
CRITICAL	vllm_omni/engine/duplex/session/control.py	65	turn_detection = self._ctx.session.config.extra_body.get("realtime_turn_detection")	CODE

AI Slop Vocabulary36 hits · 95 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/platforms/npu/test_a5_patches.py	104	# imports (e.g. ``qwen3_tts_code2wav``) resolve inside the harness.	COMMENT
MEDIUM	…executor/models/qwen3_tts/test_code_predictor_dtype.py	981	# The test harness mocks ``default_weight_loader`` as a no-op; install a	COMMENT
MEDIUM	…executor/models/qwen3_tts/test_code_predictor_dtype.py	1042	# The test harness mocks ``default_weight_loader`` as a no-op; install a	COMMENT
MEDIUM	…executor/models/qwen3_tts/test_code_predictor_dtype.py	1348	# Find any actual self_attn layer prefix, to make the test robust	COMMENT
MEDIUM	…executor/models/qwen3_omni/test_qwen3_omni_moe_lora.py	117	# This CPU harness tests weight mapping, not CUDA pinned-memory allocation.	COMMENT
MEDIUM	tests/diffusion/kernels/mot/test_mot_linear.py	320	# Cosine similarity is the primary correctness gate: robust to scale	COMMENT
LOW	…iffusion/distributed/test_autoencoder_kl_wan_encode.py	47	# Simple mock: just return the input	COMMENT
MEDIUM⚡	tests/diffusion/models/pi0/test_pi0_units.py	494	# vision_tower / embed_scale version-robust paths against regressions.	COMMENT
MEDIUM	…usion/diffusion_kv/test_paged_attention_adapter_gpu.py	101	# control plane pins it, so this standalone harness must too.	COMMENT
MEDIUM	tests/e2e/offline_inference/test_audio8_tts.py	54	# At ``core_model`` (L1/L2) the harness patches every stage to	COMMENT
MEDIUM⚡	…s/e2e/offline_inference/test_sensenova_u1_expansion.py	48	# regardless of GQA, so this is the robust LoRA target. Verify against config.json.	COMMENT
MEDIUM	tests/e2e/online_serving/test_audio8_tts.py	101	# Raw PCM has no header: without this the harness assumes 24 kHz and the	COMMENT
MEDIUM	…line_serving/text_to_speech/voxtral_tts/gradio_demo.py	43	# Default fallback voices - comprehensive list	COMMENT
LOW	vllm_omni/metrics/stat_logger.py	120	# rewritten label set already, so just pass through.	COMMENT
LOW	vllm_omni/platforms/cuda/platform.py	451	# users can just use IR op priority directly	COMMENT
MEDIUM	…ni/platforms/npu/worker/npu_generation_model_runner.py	295	# We simply utilize the implementation in vLLM.	COMMENT
MEDIUM	vllm_omni/platforms/npu/worker/npu_ar_model_runner.py	526	# We simply utilize the implementation in vLLM.	COMMENT
LOW⚡	…ctors/connectors/mooncake_transfer_engine_connector.py	314	# We don't actually connect, just use the socket to get routing info	COMMENT
LOW	vllm_omni/config/model.py	70	# would just use itself as prefix — safe but worth	COMMENT
MEDIUM	vllm_omni/model_executor/models/utils.py	59	"""Make ``trust_remote_code`` weight loading robust to the transformers 5.9	STRING
LOW	…m_omni/model_executor/models/glm_image/glm_image_ar.py	2777	# For intermediate tensors (PP), just return hidden states	COMMENT
LOW	…lm_omni/model_executor/models/mimo_audio/mimo_audio.py	477	# If no bos/eos tokens, just use audio tokens	COMMENT
MEDIUM	…els/nemotron_voicechat/nemo_vendored/duplex_ear_tts.py	325	# EOS dropout to make the model more robust	COMMENT
MEDIUM	…els/nemotron_voicechat/nemo_vendored/duplex_ear_tts.py	342	# BOS dropout to make the model more robust	COMMENT
MEDIUM	…els/nemotron_voicechat/nemo_vendored/duplex_ear_tts.py	361	# BOS dropout to make the model more robust	COMMENT
LOW	…del_executor/models/indextts2/gpt/conformer_encoder.py	141	# It's better we just return None if no cache is required,	COMMENT
MEDIUM	…el_executor/models/minicpmo_4_5/duplex/capabilities.py	10	#: the benchmark harness uses for the same purpose.	COMMENT
MEDIUM	vllm_omni/diffusion/models/pi0/modeling_pi0.py	635	# embedding (version-robust: self-scaled at transformers ≥ 5.4, manually	COMMENT
MEDIUM	vllm_omni/diffusion/models/anima/anima_transformer.py	260	# We use diffusers' apply_rotary_emb to leverage its internal float32 rotation upcasting	COMMENT
MEDIUM	vllm_omni/diffusion/diffusion_kv/layout.py	126	# Older configs, or a standalone harness: fall back to the same default	COMMENT
LOW	vllm_omni/diffusion/hooks/base.py	313	# Otherwise just call the original forward.	COMMENT
MEDIUM	vllm_omni/diffusion/lora/layers/base_linear.py	54	# `__dict__` for robust lookups in `__getattr__`.	COMMENT
MEDIUM	vllm_omni/benchmarks/data_modules/daily_omni_eval.py	133	# ``\b`` after the letter avoids "Because"/"Definitely" false positives	COMMENT
MEDIUM	vllm_omni/entrypoints/openai/serving_chat.py	1594	# Always track previous_texts for comprehensive output logging	COMMENT
MEDIUM	vllm_omni/entrypoints/openai/serving_chat.py	2061	# Update for comprehensive logging even in simple case	COMMENT
LOW	vllm_omni/worker/gpu_ar_model_runner.py	2119	# just use zeros for the draft tokens.	COMMENT

Verbosity Indicators37 hits · 70 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/core/sched/test_generation_scheduler_restore.py	249	# Step 1: process_pending_chunks moves req-B out	COMMENT
LOW⚡	tests/core/sched/test_generation_scheduler_restore.py	254	# Step 2: simulate the try/except/finally pattern	COMMENT
LOW⚡	tests/core/sched/test_generation_scheduler_restore.py	263	# Step 3: verify request is restored	COMMENT
LOW⚡	…cutor/models/minicpmo_4_5/duplex/test_window_wiring.py	1463	# Step 1: worker reanchor runs	COMMENT
LOW⚡	…cutor/models/minicpmo_4_5/duplex/test_window_wiring.py	1473	# Step 2: Simulate second call with the same reanchor_id (e.g. reinjection or duplicate metadata)	COMMENT
LOW	tests/diffusion/attention/test_attention_sp.py	1028	# Step 1: Run without SP (baseline with ulysses_degree=1, ring_degree=1)	COMMENT
LOW	tests/diffusion/attention/test_attention_sp.py	1057	# Step 2: Run with SP enabled	COMMENT
LOW	tests/diffusion/attention/test_attention_sp.py	1089	# Step 3: Verify input consistency and compare outputs	COMMENT
LOW	…dels/boogu_image/test_pipeline_boogu_image_batching.py	502	# Step 1: run the real sequential (single-rank) forward once, capturing	COMMENT
LOW	…dels/boogu_image/test_pipeline_boogu_image_batching.py	531	# Step 2: replay the identical branches through the real dispatch/gather	COMMENT
LOW⚡	tests/e2e/offline_inference/test_moss_tts_realtime.py	166	# Step 1: locate the realtime processor module in the snapshot.	COMMENT
LOW⚡	tests/e2e/offline_inference/test_moss_tts_realtime.py	191	# Step 2: encode the reference audio clip via MOSS-Audio-Tokenizer.	COMMENT
LOW	tests/e2e/offline_inference/test_moss_tts_realtime.py	209	# Step 3: build the (L, 17) prefill grid.	COMMENT
LOW⚡	…ures/custom_pipeline/test_async_omni_collective_rpc.py	126	# Step 1: list_loras (the call that was crashing)	COMMENT
LOW⚡	…ures/custom_pipeline/test_async_omni_collective_rpc.py	130	# Step 2: generate (should still work after list_loras)	COMMENT
LOW	…utor/models/ming_flash_omni/ming_flash_omni_thinker.py	930	# Step 1: if vision/audio features were extracted, merge them into	COMMENT
LOW	…utor/models/ming_flash_omni/ming_flash_omni_thinker.py	941	# Step 2: image-gen query tokens are appended at the tail of the prompt	COMMENT
LOW	…lm_omni/diffusion/models/bagel/mot/ops/mot_rms_norm.py	28	# Step 0: MoT Routing	COMMENT
LOW	…lm_omni/diffusion/models/bagel/mot/ops/mot_rms_norm.py	48	# Step 1: Compute sum of squares in float32 to avoid overflow	COMMENT
LOW⚡	…lm_omni/diffusion/models/bagel/mot/ops/mot_rms_norm.py	60	# Step 2: Compute RMS (root mean square) in float32	COMMENT
LOW⚡	…lm_omni/diffusion/models/bagel/mot/ops/mot_rms_norm.py	65	# Step 3: Normalize and apply weight	COMMENT
LOW⚡	…/diffusion/models/joy_image/pipeline_joy_image_edit.py	904	# Step 4: build the scheduler timestep/sigma schedule.	COMMENT
LOW⚡	…/diffusion/models/joy_image/pipeline_joy_image_edit.py	912	# Step 5: run the DiT denoising loop. The reference image latents stay	COMMENT
LOW⚡	…/diffusion/models/joy_image/pipeline_joy_image_edit.py	930	# Step 6: decode only the target latent back to image space.	COMMENT
LOW	…/diffusion/models/joy_image/pipeline_joy_image_edit.py	827	# Step 1: read the preprocessed single-image edit request.	COMMENT
LOW	…/diffusion/models/joy_image/pipeline_joy_image_edit.py	862	# Step 2: encode text plus the reference image through Qwen3-VL	COMMENT
LOW	…/diffusion/models/joy_image/pipeline_joy_image_edit.py	891	# Step 3: VAE-encode the reference image and create the target noise	COMMENT
LOW⚡	vllm_omni/diffusion/models/gr00t/policy.py	337	# Step 1: Split batched observation into individual observations	COMMENT
LOW⚡	vllm_omni/diffusion/models/gr00t/policy.py	341	# Step 2: Process each observation through the VLA processor	COMMENT
LOW⚡	vllm_omni/diffusion/models/gr00t/policy.py	349	# Step 3: Collate processed inputs into a single batch for model	COMMENT
LOW⚡	vllm_omni/diffusion/models/gr00t/policy.py	353	# Step 4: Run model inference to predict actions	COMMENT
LOW⚡	vllm_omni/diffusion/models/gr00t/policy.py	358	# Step 5: Decode actions from normalized space back to physical units	COMMENT
LOW	…ls/gr00t/dataio/state_action/state_action_processor.py	310	# Step 1: Convert absolute actions to relative (if needed)	COMMENT
LOW	…ls/gr00t/dataio/state_action/state_action_processor.py	343	# Step 2: Normalize actions	COMMENT
LOW	…ls/gr00t/dataio/state_action/state_action_processor.py	395	# Step 1: Unnormalize actions	COMMENT
LOW	…ls/gr00t/dataio/state_action/state_action_processor.py	418	# Step 2: Convert relative actions to absolute (if needed)	COMMENT
LOW	vllm_omni/quantization/tools/merge_mxfp8_checkpoint.py	231	# Step 1: Copy original model, skipping transformer dirs (will be replaced).	COMMENT

Example Usage Blocks33 hits · 50 pts

Severity	File	Line	Snippet	Context
LOW	tools/run_merge_jobs.sh	21	# Usage:	COMMENT
LOW	tools/run_ready_jobs.sh	21	# Usage:	COMMENT
LOW	tools/nightly/run_nightly_jobs.sh	58	# Usage:	COMMENT
LOW	tests/e2e/offline_inference/run_quantization_e2e.sh	10	# Usage:	COMMENT
LOW	…_inference/qwen3_omni/run_single_prompt_async_chunk.sh	12	# Usage:	COMMENT
LOW	…ference/qwen3_omni/run_multiple_prompts_async_chunk.sh	8	# Usage:	COMMENT
LOW	…ine_inference/qwen2_5_omni/strategy_stage_replica.yaml	14	# Usage:	COMMENT
LOW	…mples/offline_inference/qwen2_5_omni/strategy_tp2.yaml	12	# Usage:	COMMENT
LOW	…les/online_serving/replica_data_parallel/run_server.sh	4	# Usage:	COMMENT
LOW	examples/online_serving/audex/run_server.sh	13	# Usage:	COMMENT
LOW	…amples/online_serving/text_to_video/run_server_ltx2.sh	7	# Usage:	COMMENT
LOW	examples/online_serving/qwen3_omni/run_gradio_demo.sh	4	# Usage:	COMMENT
LOW	examples/online_serving/qwen2_5_omni/run_gradio_demo.sh	4	# Usage:	COMMENT
LOW	…erving/text_to_speech/moss_tts_nano/run_gradio_demo.sh	4	# Usage:	COMMENT
LOW	…ine_serving/text_to_speech/moss_tts_nano/run_server.sh	4	# Usage:	COMMENT
LOW	…e_serving/text_to_speech/audio8_tts/run_gradio_demo.sh	7	# Usage:	COMMENT
LOW	…online_serving/text_to_speech/audio8_tts/run_server.sh	7	# Usage:	COMMENT
LOW	…rving/text_to_speech/ming_flash_omni_tts/run_server.sh	4	# Usage:	COMMENT
LOW	…online_serving/text_to_speech/cosyvoice3/run_server.sh	7	# Usage:	COMMENT
LOW	…line_serving/text_to_speech/glm_tts/run_gradio_demo.sh	4	# Usage:	COMMENT
LOW	…es/online_serving/text_to_speech/glm_tts/run_server.sh	4	# Usage:	COMMENT
LOW	…/online_serving/text_to_speech/omnivoice/run_server.sh	4	# Usage:	COMMENT
LOW	…les/online_serving/text_to_speech/gepard/run_server.sh	7	# Usage:	COMMENT
LOW	…_serving/text_to_speech/fish_speech/run_gradio_demo.sh	4	# Usage:	COMMENT
LOW	…nline_serving/text_to_speech/fish_speech/run_server.sh	4	# Usage:	COMMENT
LOW	…s/online_serving/text_to_speech/ming_tts/run_server.sh	4	# Usage:	COMMENT
LOW	…ne_serving/text_to_speech/higgs_audio_v2/run_server.sh	8	# Usage:	COMMENT
LOW	…ne_serving/text_to_speech/higgs_audio_v3/run_server.sh	6	# Usage:	COMMENT
LOW	…ne_serving/text_to_speech/qwen3_tts/run_gradio_demo.sh	7	# Usage:	COMMENT
LOW	…/online_serving/text_to_speech/qwen3_tts/run_server.sh	4	# Usage:	COMMENT
LOW	.buildkite/release/scripts/publish-release-images.sh	6	# Usage:	COMMENT
LOW	vllm_omni/deploy/qwen3_omni_moe_mori_intranode.yaml	26	# Usage:	COMMENT
LOW	vllm_omni/deploy/indextts2_low_latency.yaml	8	# Usage:	COMMENT

Dead Code12 hits · 24 pts

Severity	File	Line	Context
MEDIUM	tests/diffusion/test_inline_stage_diffusion_client.py	218	CODE
MEDIUM	tests/benchmarks/test_realtime_tts_probe.py	41	CODE
MEDIUM	…/entrypoints/openai_api/test_serving_audio_generate.py	422	CODE
MEDIUM	…/entrypoints/openai_api/test_serving_audio_generate.py	481	CODE
MEDIUM	…/entrypoints/openai_api/test_serving_audio_generate.py	496	CODE
MEDIUM	tests/entrypoints/openai_api/test_serving_speech.py	3755	CODE
MEDIUM	tests/entrypoints/openai_api/test_serving_speech.py	3916	CODE
MEDIUM	tests/entrypoints/openai_api/test_serving_speech.py	5952	CODE
MEDIUM	tests/entrypoints/openai_api/test_serving_speech.py	6021	CODE
MEDIUM	…s/entrypoints/openai_api/test_serving_speech_stream.py	394	CODE
MEDIUM	tests/entrypoints/openai_api/test_image_server.py	701	CODE
MEDIUM	tests/entrypoints/openai_api/test_image_server.py	1023	CODE

Magic Placeholder Names1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	.github/ISSUE_TEMPLATE/400-bug-report.yml	20	Consider redacting or replacing sensitive values with placeholders like `<YOUR_TOKEN_HERE>` when sharing configura	CODE

Slop Phrases2 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	…_executor/models/minicpmo_4_5/minicpmo_4_5_omni_llm.py	2205	# When lifting this restriction, don't forget to either	COMMENT
LOW	…_executor/models/minicpmo_4_5/minicpmo_4_5_omni_llm.py	2205	# When lifting this restriction, don't forget to either	COMMENT

Overly Generic Function Names3 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	tests/diffusion/test_stage_diffusion_proc.py	173	async def run_task(req_data):	CODE
LOW	tests/diffusion/test_diffusion_engine.py	952	async def run_task(rid):	CODE
LOW	examples/offline_inference/lance/gradio_demo.py	794	def run_task(	CODE

Fake / Example Data3 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	…or/models/higgs_audio_v3/test_ref_audio_diagnostics.py	57	assert "placeholder" in message	CODE
LOW	tests/diffusion/models/cosmos3/test_cosmos3_pipeline.py	1198	source.write_bytes(b"placeholder")	CODE
LOW	tests/diffusion/models/cosmos3/test_cosmos3_pipeline.py	1233	source.write_bytes(b"placeholder")	CODE

Maintenance and Governance Review

Risk Review · v3

What These Metrics Mean

Pattern-Signal History

Severity Breakdown

Directory Score Breakdown

Pattern Findings