Repository Analysis

xorbitsai/inference

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

15.7 Moderate AI signal View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of xorbitsai/inference, a Python project with 9,430 GitHub stars. SynthScan v2.0 examined 344,871 lines of code across 1307 source files, recording 4284 pattern matches distributed across 24 syntactic categories. The overall adjusted score of 15.7 places this repository in the Moderate AI signal band.

The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).

15.7
Adjusted Score
15.7
Raw Score
100%
Time Factor
2026-07-14
Last Push
9.4K
Stars
Python
Language
344.9K
Lines of Code
1.3K
Files
4.3K
Pattern Hits
2026-07-14
Scan Date
0.16
HC Hit Rate

What These Metrics Mean

Adjusted Score
Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score
The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor
The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits
Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate
High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files
Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 1HIGH 202MEDIUM 189LOW 3892

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 4284 distinct pattern matches across 24 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. 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 diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers1279 hits · 1324 pts
SeverityFileLineSnippetContext
LOWversioneer.py652def git_versions_from_keywords(keywords, tag_prefix, verbose):CODE
LOWversioneer.py1174def git_versions_from_keywords(keywords, tag_prefix, verbose):STRING
LOWbenchmark/utils.py169def _num_special_tokens_to_add(tokenizer: "PreTrainedTokenizerBase") -> int:CODE
LOWbenchmark/utils.py234def _gen_prompt_decode_to_target_len(CODE
LOWbenchmark/utils.py300def _generate_prompt_with_target_len(CODE
LOWbenchmark/benchmark_serving.py30def _validate_random_range_ratio(value: float, name: str) -> float:CODE
LOW…register-model/[modelType]/[modelName]/page-client.tsx8export default function RegisterModelEditPageClient() {CODE
LOW…ntend/src/app/running-model/[modelUid]/page-client.tsx7export default function RunningModelDetailPageClient() {CODE
LOWfrontend/src/components/pages/launch-model/utils.tsx215export function getLaunchModelEndpointType(type: RequestModelType) {CODE
LOWfrontend/src/components/pages/launch-model/utils.tsx269function restoreNestedFormListObject(values: FormValues, parent: string, field: string) {CODE
LOWfrontend/src/components/pages/launch-model/utils.tsx284function transformOnlyValueFormListToArray(values: FormValues, field: string) {CODE
LOWfrontend/src/components/pages/launch-model/utils.tsx308function transformArrayToOnlyValueFormList(values: FormValues, field: string) {CODE
LOWfrontend/src/components/pages/launch-model/utils.tsx358function applyNestedFormListObject(values: FormValues, parent: string, field: string) {CODE
LOWfrontend/src/components/pages/launch-model/utils.tsx380function deleteNestedEmptyArrayField(values: FormValues, parent: string, field: string) {CODE
LOWfrontend/src/components/pages/launch-model/utils.tsx602export function generateCommandLineStatement(params: FormValues) {CODE
LOWfrontend/src/components/pages/launch-model/utils.tsx861export function isVisibleRequiredLaunchField(field: LaunchFieldConfig) {CODE
LOW…nents/pages/running-model-detail/capability-config.tsx124function appendCommonMediaFormData(formData: FormData, context: TransformContext) {CODE
LOW…nents/pages/running-model-detail/capability-config.tsx153function appendCommonVideoFormData(formData: FormData, context: TransformContext) {CODE
LOW…end/src/components/pages/running-model-detail/utils.ts142export function transformFileInfoForResult(message?: ChatChoicesMessage) {CODE
LOWxinference/conftest.py168def run_test_cluster_in_subprocess(CODE
LOWxinference/_version.py179def git_versions_from_keywords(keywords, tag_prefix, verbose):CODE
LOWxinference/constants.py114def _get_or_create_persisted_secret(env_name: str, file_name: str) -> str:CODE
LOWxinference/constants.py207def get_or_create_setup_token() -> str:CODE
LOWxinference/types.py314def get_pydantic_model_from_method(CODE
LOWxinference/device_utils.py53def _count_with_visible_devices(env_name: str, device_count: int) -> int:CODE
LOWxinference/device_utils.py273def _collect_gpu_info_with_env(CODE
LOWxinference/device_utils.py583def move_model_to_available_device(model):CODE
LOWxinference/device_utils.py590def get_device_preferred_dtype(device: str) -> Union[torch.dtype, None]:CODE
LOWxinference/device_utils.py599def is_hf_accelerate_supported(device: str) -> bool:CODE
LOWxinference/device_utils.py609def get_available_device_env_name():CODE
LOWxinference/device_utils.py635def get_per_process_gpu_memory() -> Dict[int, Dict[int, int]]:CODE
LOWxinference/core/worker.py214def _snapshot_gpu_occupying_pids(device_indices: list) -> set:CODE
LOWxinference/core/worker.py307def _process_or_ancestor_has_uid(proc: Any, uid_lower: str) -> bool:CODE
LOWxinference/core/worker.py1348 def _load_persisted_launch_args(self) -> dict:CODE
LOWxinference/core/worker.py122def _exclusive_venv_path_lock(env_path: str):CODE
LOWxinference/core/worker.py418async def _kill_gpu_orphans_by_ppid(CODE
LOWxinference/core/worker.py822 async def _evict_replica_from_supervisor(self, model_uid: str) -> None:CODE
LOWxinference/core/worker.py855 def _get_spec_dicts_with_cache_status(CODE
LOWxinference/core/worker.py897 async def _cleanup_gpu_orphans_on_startup(self) -> None:CODE
LOWxinference/core/worker.py1241 async def _refresh_supervisor_address(self):CODE
LOWxinference/core/worker.py1258 def _get_running_replica_states(self) -> List[Dict[str, Any]]:CODE
LOWxinference/core/worker.py1331 def _remove_persisted_launch_args(self, model_uid: str):CODE
LOWxinference/core/worker.py1492 async def allocate_devices_with_gpu_idx(CODE
LOWxinference/core/worker.py1530 async def get_gpu_allocation_status(self) -> Dict[str, Any]:CODE
LOWxinference/core/worker.py1572 async def _append_sub_pool_protected(CODE
LOWxinference/core/worker.py1898 async def _store_complete_model_configurations(self, model_type: str, model_data):CODE
LOWxinference/core/worker.py2349 async def query_engines_by_model_name(CODE
LOWxinference/core/worker.py2396 def _create_virtual_env_manager(CODE
LOWxinference/core/worker.py2701 def _upload_download_progress(CODE
LOWxinference/core/worker.py3572 async def _periodical_report_status(self):CODE
LOWxinference/core/worker.py3746 async def list_virtual_env_packages(self, model_name: str) -> Dict[str, Any]:CODE
LOWxinference/core/metrics.py666def launch_metrics_export_server(q, host=None, port=None):CODE
LOWxinference/core/supervisor.py198 def _refresh_replica_scheduler(replica_info: ReplicaInfo) -> None:CODE
LOWxinference/core/supervisor.py203 def _iter_active_replica_model_uids(self, model_uid: str) -> List[str]:CODE
LOWxinference/core/supervisor.py213 def _get_model_uid_and_replica_index(CODE
LOWxinference/core/supervisor.py428 def _clear_unexpected_down_replicas(self, model_uid: str) -> None:CODE
LOWxinference/core/supervisor.py438 def _rebuild_worker_replica_state(CODE
LOWxinference/core/supervisor.py93def callback_for_async_launch(model_uid: str):CODE
LOWxinference/core/supervisor.py235 def _normalize_replica_states(CODE
LOWxinference/core/supervisor.py246 def _remove_worker_from_replica_mappings(self, worker_address: str):CODE
1219 more matches not shown…
Cross-File Repetition165 hits · 825 pts
SeverityFileLineSnippetContext
HIGHxinference/model/video/__init__.py0load downloaded json configurations from the builtin directory.STRING
HIGHxinference/model/llm/__init__.py0load downloaded json configurations from the builtin directory.STRING
HIGHxinference/model/embedding/__init__.py0load downloaded json configurations from the builtin directory.STRING
HIGHxinference/model/image/__init__.py0load downloaded json configurations from the builtin directory.STRING
HIGHxinference/model/audio/__init__.py0load downloaded json configurations from the builtin directory.STRING
HIGHxinference/model/rerank/__init__.py0load downloaded json configurations from the builtin directory.STRING
HIGH…ence/model/llm/tool_parsers/deepseek_v3_tool_parser.py0extract tool calls from complete model output. parses the model output to find json code blocks containing tool calls anSTRING
HIGHxinference/model/llm/tool_parsers/glm5_tool_parser.py0extract tool calls from complete model output. parses the model output to find json code blocks containing tool calls anSTRING
HIGH…ce/model/llm/tool_parsers/deepseek_v3_1_tool_parser.py0extract tool calls from complete model output. parses the model output to find json code blocks containing tool calls anSTRING
HIGHxinference/model/llm/tool_parsers/glm4_tool_parser.py0extract tool calls from complete model output. parses the model output to find json code blocks containing tool calls anSTRING
HIGH…ference/thirdparty/cosyvoice/transformer/activation.py0implementation of a sine-based periodic activation function shape: - input: (b, c, t) - output: (b, c, t), same shape asSTRING
HIGHxinference/thirdparty/indextts/BigVGAN/activations.py0implementation of a sine-based periodic activation function shape: - input: (b, c, t) - output: (b, c, t), same shape asSTRING
HIGH…thirdparty/indextts/s2mel/modules/hifigan/generator.py0implementation of a sine-based periodic activation function shape: - input: (b, c, t) - output: (b, c, t), same shape asSTRING
HIGH…irdparty/indextts/s2mel/modules/bigvgan/activations.py0implementation of a sine-based periodic activation function shape: - input: (b, c, t) - output: (b, c, t), same shape asSTRING
HIGH…ference/thirdparty/cosyvoice/transformer/activation.py0initialization. input: - in_features: shape of the input - alpha: trainable parameter alpha is initialized to 1 by defauSTRING
HIGHxinference/thirdparty/indextts/BigVGAN/activations.py0initialization. input: - in_features: shape of the input - alpha: trainable parameter alpha is initialized to 1 by defauSTRING
HIGH…thirdparty/indextts/s2mel/modules/hifigan/generator.py0initialization. input: - in_features: shape of the input - alpha: trainable parameter alpha is initialized to 1 by defauSTRING
HIGH…irdparty/indextts/s2mel/modules/bigvgan/activations.py0initialization. input: - in_features: shape of the input - alpha: trainable parameter alpha is initialized to 1 by defauSTRING
HIGH…ference/thirdparty/cosyvoice/transformer/activation.py0forward pass of the function. applies the function to the input elementwise. snake ∶= x + 1/a * sin^2 (xa)STRING
HIGHxinference/thirdparty/indextts/BigVGAN/activations.py0forward pass of the function. applies the function to the input elementwise. snake ∶= x + 1/a * sin^2 (xa)STRING
HIGH…thirdparty/indextts/s2mel/modules/hifigan/generator.py0forward pass of the function. applies the function to the input elementwise. snake ∶= x + 1/a * sin^2 (xa)STRING
HIGH…irdparty/indextts/s2mel/modules/bigvgan/activations.py0forward pass of the function. applies the function to the input elementwise. snake ∶= x + 1/a * sin^2 (xa)STRING
HIGHxinference/thirdparty/cosyvoice/utils/mask.py0make mask tensor containing indices of padded part. see description of make_non_pad_mask. args: lengths (torch.tensor): STRING
HIGHxinference/thirdparty/indextts/utils/common.py0make mask tensor containing indices of padded part. see description of make_non_pad_mask. args: lengths (torch.tensor): STRING
HIGHxinference/thirdparty/indextts/utils/utils.py0make mask tensor containing indices of padded part. see description of make_non_pad_mask. args: lengths (torch.tensor): STRING
HIGH…ference/thirdparty/deepseek_vl2/models/conversation.py0a class that manages prompt templates and keeps all conversation history.STRING
HIGHxinference/thirdparty/deepseek_vl/utils/conversation.py0a class that manages prompt templates and keeps all conversation history.STRING
HIGHxinference/thirdparty/internvl/conversation.py0a class that manages prompt templates and keeps all conversation history.STRING
HIGH…ference/thirdparty/deepseek_vl2/models/conversation.py0update the last output. the last message is typically set to be none when constructing the prompt, so we need to update STRING
HIGHxinference/thirdparty/deepseek_vl/utils/conversation.py0update the last output. the last message is typically set to be none when constructing the prompt, so we need to update STRING
HIGHxinference/thirdparty/internvl/conversation.py0update the last output. the last message is typically set to be none when constructing the prompt, so we need to update STRING
HIGH…ference/thirdparty/deepseek_vl2/models/conversation.py0convert the conversation to openai chat completion format.STRING
HIGHxinference/thirdparty/deepseek_vl/utils/conversation.py0convert the conversation to openai chat completion format.STRING
HIGHxinference/thirdparty/internvl/conversation.py0convert the conversation to openai chat completion format.STRING
HIGH…ish_speech/fish_speech/models/vqgan/modules/firefly.py0remove padding from x, handling properly zero padding. only for 1d!STRING
HIGH…s/maskgct/models/codec/speechtokenizer/modules/conv.py0remove padding from x, handling properly zero padding. only for 1d!STRING
HIGH…ference/thirdparty/indextts/s2mel/dac/model/encodec.py0remove padding from x, handling properly zero padding. only for 1d!STRING
HIGHxinference/thirdparty/indextts/s2mel/modules/encodec.py0remove padding from x, handling properly zero padding. only for 1d!STRING
HIGH…ish_speech/fish_speech/models/vqgan/modules/firefly.py0tiny wrapper around f.pad, just to allow for reflect padding on small input. if this is the case, we insert extra 0 paddSTRING
HIGH…s/maskgct/models/codec/speechtokenizer/modules/conv.py0tiny wrapper around f.pad, just to allow for reflect padding on small input. if this is the case, we insert extra 0 paddSTRING
HIGH…ference/thirdparty/indextts/s2mel/dac/model/encodec.py0tiny wrapper around f.pad, just to allow for reflect padding on small input. if this is the case, we insert extra 0 paddSTRING
HIGHxinference/thirdparty/indextts/s2mel/modules/encodec.py0tiny wrapper around f.pad, just to allow for reflect padding on small input. if this is the case, we insert extra 0 paddSTRING
HIGHxinference/thirdparty/melo/attentions.py0x: [b, h, l, d] y: [h or 1, m, d] ret: [b, h, l, m]STRING
HIGH…megatts3/tts/modules/ar_dur/commons/rel_transformer.py0x: [b, h, l, d] y: [h or 1, m, d] ret: [b, h, l, m]STRING
HIGH…ils/maskgct/models/codec/facodec/modules/attentions.py0x: [b, h, l, d] y: [h or 1, m, d] ret: [b, h, l, m]STRING
HIGH…rdparty/indextts/s2mel/modules/openvoice/attentions.py0x: [b, h, l, d] y: [h or 1, m, d] ret: [b, h, l, m]STRING
HIGHxinference/thirdparty/melo/attentions.py0bias for self-attention to encourage attention to close positions. args: length: an integer scalar. returns: a tensor wiSTRING
HIGH…megatts3/tts/modules/ar_dur/commons/rel_transformer.py0bias for self-attention to encourage attention to close positions. args: length: an integer scalar. returns: a tensor wiSTRING
HIGH…ils/maskgct/models/codec/facodec/modules/attentions.py0bias for self-attention to encourage attention to close positions. args: length: an integer scalar. returns: a tensor wiSTRING
HIGH…rdparty/indextts/s2mel/modules/openvoice/attentions.py0bias for self-attention to encourage attention to close positions. args: length: an integer scalar. returns: a tensor wiSTRING
HIGHxinference/thirdparty/melo/commons.py0sample from the gumbel distribution, protect from overflows.STRING
HIGH…/utils/maskgct/models/codec/facodec/modules/commons.py0sample from the gumbel distribution, protect from overflows.STRING
HIGHxinference/thirdparty/indextts/s2mel/modules/commons.py0sample from the gumbel distribution, protect from overflows.STRING
HIGH…thirdparty/indextts/s2mel/modules/openvoice/commons.py0sample from the gumbel distribution, protect from overflows.STRING
HIGHxinference/thirdparty/melo/text/cleaner_multiling.py0replace symbols based on the lenguage tag. args: text: input text. lang: lenguage identifier. ex: "en", "fr", "pt", "ca"STRING
HIGH…nference/thirdparty/melo/text/es_phonemizer/cleaner.py0replace symbols based on the lenguage tag. args: text: input text. lang: lenguage identifier. ex: "en", "fr", "pt", "ca"STRING
HIGH…nference/thirdparty/melo/text/fr_phonemizer/cleaner.py0replace symbols based on the lenguage tag. args: text: input text. lang: lenguage identifier. ex: "en", "fr", "pt", "ca"STRING
HIGH…ce/thirdparty/melo/text/es_phonemizer/gruut_wrapper.py0returns true if `language` is supported by the backendSTRING
HIGHxinference/thirdparty/melo/text/es_phonemizer/base.py0returns true if `language` is supported by the backendSTRING
HIGH…ce/thirdparty/melo/text/fr_phonemizer/gruut_wrapper.py0returns true if `language` is supported by the backendSTRING
105 more matches not shown…
Unused Imports709 hits · 692 pts
SeverityFileLineSnippetContext
LOWbenchmark/utils.py29CODE
LOWxinference/__init__.py29CODE
LOWxinference/device_utils.py131CODE
LOWxinference/device_utils.py140CODE
LOWxinference/device_utils.py149CODE
LOWxinference/device_utils.py158CODE
LOWxinference/device_utils.py159CODE
LOWxinference/device_utils.py168CODE
LOWxinference/_compat.py22CODE
LOWxinference/_compat.py22CODE
LOWxinference/_compat.py22CODE
LOWxinference/_compat.py22CODE
LOWxinference/_compat.py22CODE
LOWxinference/_compat.py22CODE
LOWxinference/_compat.py22CODE
LOWxinference/_compat.py34CODE
LOWxinference/_compat.py35CODE
LOWxinference/_compat.py36CODE
LOWxinference/_compat.py37CODE
LOWxinference/_compat.py39CODE
LOWxinference/_compat.py39CODE
LOWxinference/_compat.py39CODE
LOWxinference/_compat.py39CODE
LOWxinference/_compat.py39CODE
LOWxinference/_compat.py39CODE
LOWxinference/_compat.py39CODE
LOWxinference/_compat.py51CODE
LOWxinference/_compat.py52CODE
LOWxinference/_compat.py53CODE
LOWxinference/_compat.py54CODE
LOWxinference/core/supervisor.py53CODE
LOWxinference/core/supervisor.py77CODE
LOWxinference/core/supervisor.py78CODE
LOWxinference/core/supervisor.py80CODE
LOWxinference/core/supervisor.py81CODE
LOWxinference/core/supervisor.py82CODE
LOWxinference/core/supervisor.py83CODE
LOWxinference/core/launch_strategy.py22CODE
LOWxinference/core/model.py48CODE
LOWxinference/core/model.py49CODE
LOWxinference/deploy/cmdline.py54CODE
LOWxinference/deploy/utils.py42CODE
LOWxinference/model/custom.py24CODE
LOWxinference/model/cache_manager.py6CODE
LOWxinference/model/utils.py58CODE
LOWxinference/model/utils.py59CODE
LOWxinference/model/video/__init__.py22CODE
LOWxinference/model/video/diffusers.py36CODE
LOWxinference/model/llm/custom.py21CODE
LOWxinference/model/llm/cache_manager.py22CODE
LOWxinference/model/llm/__init__.py20CODE
LOWxinference/model/llm/__init__.py20CODE
LOWxinference/model/llm/__init__.py26CODE
LOWxinference/model/llm/__init__.py27CODE
LOWxinference/model/llm/__init__.py27CODE
LOWxinference/model/llm/__init__.py27CODE
LOWxinference/model/llm/__init__.py27CODE
LOWxinference/model/llm/__init__.py27CODE
LOWxinference/model/llm/core.py33CODE
LOWxinference/model/llm/core.py33CODE
649 more matches not shown…
Excessive Try-Catch Wrapping522 hits · 504 pts
SeverityFileLineSnippetContext
LOWbenchmark/benchmark_runner.py198 except Exception:CODE
MEDIUMxinference/conftest.py117 print(f"Error while checking endpoint: {e}")CODE
LOWxinference/conftest.py321 except Exception:CODE
LOWxinference/__init__.py30except Exception:CODE
MEDIUMxinference/device_utils.py61def _mps_empty_cache():CODE
MEDIUMxinference/device_utils.py313def get_nvidia_gpu_info() -> Dict[str, Any]:CODE
MEDIUMxinference/device_utils.py345def get_metax_gpu_info() -> Dict:CODE
MEDIUMxinference/device_utils.py360def get_rocm_gpu_info() -> Dict:CODE
LOWxinference/device_utils.py302 except Exception as e:CODE
LOWxinference/device_utils.py309 except Exception:CODE
LOWxinference/device_utils.py326 except Exception as e:CODE
LOWxinference/device_utils.py340 except Exception as e:CODE
LOWxinference/device_utils.py355 except Exception as e:CODE
LOWxinference/device_utils.py369 except Exception:CODE
LOWxinference/device_utils.py655 except Exception:CODE
LOWxinference/device_utils.py678 except Exception:CODE
MEDIUMxinference/core/worker.py1112def signal_handler():CODE
MEDIUMxinference/core/worker.py1129def trigger_exit(self) -> bool:CODE
LOWxinference/core/worker.py209 except Exception as e:CODE
LOWxinference/core/worker.py224 except Exception:CODE
LOWxinference/core/worker.py234 except Exception:CODE
LOWxinference/core/worker.py239 except Exception:CODE
LOWxinference/core/worker.py300 except Exception:CODE
LOWxinference/core/worker.py316 except Exception:CODE
LOWxinference/core/worker.py1345 except Exception:CODE
LOWxinference/core/worker.py1356 except Exception:CODE
LOWxinference/core/worker.py3534 except Exception:CODE
LOWxinference/core/worker.py3538 except Exception:CODE
LOWxinference/core/worker.py3543 except Exception:CODE
LOWxinference/core/worker.py253 except Exception:CODE
LOWxinference/core/worker.py264 except Exception:CODE
LOWxinference/core/worker.py269 except Exception:CODE
LOWxinference/core/worker.py366 except Exception:CODE
LOWxinference/core/worker.py395 except Exception:CODE
LOWxinference/core/worker.py410 except Exception:CODE
LOWxinference/core/worker.py492 except Exception:CODE
LOWxinference/core/worker.py629 except Exception:CODE
LOWxinference/core/worker.py658 except Exception as e:CODE
LOWxinference/core/worker.py683 except Exception:CODE
LOWxinference/core/worker.py702 except Exception:CODE
LOWxinference/core/worker.py704 except Exception:CODE
LOWxinference/core/worker.py745 except Exception:CODE
LOWxinference/core/worker.py770 except Exception as e:CODE
LOWxinference/core/worker.py788 except Exception:CODE
LOWxinference/core/worker.py812 except Exception:CODE
LOWxinference/core/worker.py844 except Exception:CODE
LOWxinference/core/worker.py928 except Exception:CODE
LOWxinference/core/worker.py930 except Exception:CODE
LOWxinference/core/worker.py971 except Exception:CODE
LOWxinference/core/worker.py1068 except Exception:CODE
LOWxinference/core/worker.py1076 except Exception:CODE
LOWxinference/core/worker.py1116 except Exception as e:CODE
LOWxinference/core/worker.py1132 except Exception as e:CODE
LOWxinference/core/worker.py1156 except Exception:CODE
LOWxinference/core/worker.py1190 except Exception:CODE
LOWxinference/core/worker.py1222 except Exception:CODE
LOWxinference/core/worker.py1325 except Exception:CODE
LOWxinference/core/worker.py1391 except Exception:CODE
LOWxinference/core/worker.py1420 except Exception:CODE
LOWxinference/core/worker.py1629 except Exception:CODE
462 more matches not shown…
Over-Commented Block482 hits · 470 pts
SeverityFileLineSnippetContext
LOWsetup.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWversioneer.py1201 if not tags:COMMENT
LOWbenchmark/benchmark_long.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWbenchmark/utils.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWbenchmark/benchmark_embedding.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWbenchmark/benchmark_runner.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWbenchmark/benchmark_latency.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWbenchmark/benchmark_rerank.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWbenchmark/benchmark_serving.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWfrontend/next.config.ts1// Output mode (build only):COMMENT
LOWxinference/isolation.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/conftest.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/fields.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/constants.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/__init__.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/types.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/utils.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/device_utils.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/_compat.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/ui/__init__.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/worker.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/worker.py1661 model_uid, model_type, gpu_idx # type: ignoreCOMMENT
LOWxinference/core/worker.py3821 @no_type_checkCOMMENT
LOWxinference/core/metrics.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/event.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/progress_tracker.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/log.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/monitor_config_store.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/supervisor.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/virtual_env_manager.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/launch_strategy.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/resource.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/__init__.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/cache_tracker.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/autostart.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/model.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/utils.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/status_guard.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/exceptions.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/launch_history_store.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/otel.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_virtual_env_manager.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_model.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_continuous_batching.py1# Copyright 2022-2026 XProbe Inc.COMMENT
LOWxinference/core/tests/test_utils.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_launch_orphan_cleanup.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_metrics.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_restful_api.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_subpool_hardening.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/__init__.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_heartbeat.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_worker.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_progressor.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_launch_strategy.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_strip_test_envs.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_autostart.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_monitor_config_store.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_types.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
LOWxinference/core/tests/test_types.py101 # messages = [COMMENT
LOWxinference/deploy/worker.py1# Copyright 2022-2026 Xinference Holdings Pte. LtdCOMMENT
422 more matches not shown…
Deep Nesting453 hits · 392 pts
SeverityFileLineSnippetContext
LOWversioneer.py1146CODE
LOWversioneer.py1385CODE
LOWversioneer.py1712CODE
LOWversioneer.py2160CODE
LOWbenchmark/benchmark_runner.py88CODE
LOWbenchmark/benchmark_runner.py206CODE
LOWxinference/_version.py151CODE
LOWxinference/_version.py602CODE
LOWxinference/constants.py114CODE
LOWxinference/utils.py42CODE
LOWxinference/device_utils.py273CODE
LOWxinference/device_utils.py385CODE
LOWxinference/device_utils.py635CODE
LOWxinference/core/worker.py214CODE
LOWxinference/core/worker.py244CODE
LOWxinference/core/worker.py287CODE
LOWxinference/core/worker.py321CODE
LOWxinference/core/worker.py515CODE
LOWxinference/core/worker.py624CODE
LOWxinference/core/worker.py897CODE
LOWxinference/core/worker.py1302CODE
LOWxinference/core/worker.py1572CODE
LOWxinference/core/worker.py1636CODE
LOWxinference/core/worker.py1803CODE
LOWxinference/core/worker.py1937CODE
LOWxinference/core/worker.py2258CODE
LOWxinference/core/worker.py2396CODE
LOWxinference/core/worker.py2514CODE
LOWxinference/core/worker.py2712CODE
LOWxinference/core/worker.py3209CODE
LOWxinference/core/worker.py3482CODE
LOWxinference/core/worker.py3694CODE
LOWxinference/core/metrics.py316CODE
LOWxinference/core/metrics.py613CODE
LOWxinference/core/monitor_config_store.py140CODE
LOWxinference/core/supervisor.py438CODE
LOWxinference/core/supervisor.py1157CODE
LOWxinference/core/supervisor.py1818CODE
LOWxinference/core/supervisor.py1914CODE
LOWxinference/core/supervisor.py2393CODE
LOWxinference/core/supervisor.py2654CODE
LOWxinference/core/supervisor.py2165CODE
LOWxinference/core/supervisor.py2468CODE
LOWxinference/core/virtual_env_manager.py228CODE
LOWxinference/core/virtual_env_manager.py285CODE
LOWxinference/core/virtual_env_manager.py475CODE
LOWxinference/core/launch_strategy.py57CODE
LOWxinference/core/cache_tracker.py51CODE
LOWxinference/core/cache_tracker.py79CODE
LOWxinference/core/cache_tracker.py111CODE
LOWxinference/core/cache_tracker.py133CODE
LOWxinference/core/cache_tracker.py147CODE
LOWxinference/core/model.py702CODE
LOWxinference/core/model.py750CODE
LOWxinference/core/utils.py225CODE
LOWxinference/core/utils.py342CODE
LOWxinference/core/tests/test_progressor.py25CODE
LOWxinference/deploy/cmdline.py485CODE
LOWxinference/deploy/cmdline.py903CODE
LOWxinference/deploy/cmdline.py1084CODE
393 more matches not shown…
Decorative Section Separators66 hits · 246 pts
SeverityFileLineSnippetContext
MEDIUMxinference/device_utils.py29# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py31# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py48# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py50# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py268# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py270# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py90# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py92# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py175# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py177# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py449# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py451# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py558# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/device_utils.py560# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/metrics.py31# ===========================================================================COMMENT
MEDIUMxinference/core/metrics.py33# ===========================================================================COMMENT
MEDIUMxinference/core/metrics.py52# ===========================================================================COMMENT
MEDIUMxinference/core/metrics.py54# ===========================================================================COMMENT
MEDIUMxinference/core/metrics.py96# ===========================================================================COMMENT
MEDIUMxinference/core/metrics.py98# ===========================================================================COMMENT
MEDIUMxinference/core/metrics.py164# ===========================================================================COMMENT
MEDIUMxinference/core/metrics.py166# ===========================================================================COMMENT
MEDIUMxinference/core/metrics.py193# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/metrics.py195# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/metrics.py219# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/metrics.py221# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/metrics.py235# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/metrics.py237# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/otel.py161# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/otel.py163# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/otel.py316# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/otel.py318# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py112# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py114# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py151# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py153# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py185# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py187# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py209# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py211# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py251# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py256# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py354# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py356# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py415# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py417# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py481# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/core/tests/test_subpool_hardening.py483# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/deploy/docker/docker-compose.yml20# # ── OpenTelemetry (OTEL) ──────────────────────────────────────────────COMMENT
MEDIUM…odel/llm/tool_parsers/tests/test_llama3_tool_parser.py12 # ── Normal parsing (JSON format) ──────────────────────────────────COMMENT
MEDIUM…odel/llm/tool_parsers/tests/test_llama3_tool_parser.py65 # ── Normal parsing (Python literal format) ────────────────────────COMMENT
MEDIUM…odel/llm/tool_parsers/tests/test_llama3_tool_parser.py79 # ── Security: RCE prevention ──────────────────────────────────────COMMENT
MEDIUM…odel/llm/tool_parsers/tests/test_llama3_tool_parser.py123 # ── Edge cases: malformed input ───────────────────────────────────COMMENT
MEDIUM…m/tool_parsers/tests/test_deepseek_v3_2_tool_parser.py296# ── Tests for plain (non-DSML) format ──────────────────────────────────────COMMENT
MEDIUMxinference/model/llm/tests/test_utils.py2027# ── Security tests for Llama3ToolParser ────────────────────COMMENT
MEDIUM…/sentence_transformers/tests/test_jina_task_mapping.py35# ---------------------------------------------------------------------------COMMENT
MEDIUM…/sentence_transformers/tests/test_jina_task_mapping.py37# ---------------------------------------------------------------------------COMMENT
MEDIUM…/sentence_transformers/tests/test_jina_task_mapping.py146# ---------------------------------------------------------------------------COMMENT
MEDIUM…/sentence_transformers/tests/test_jina_task_mapping.py148# ---------------------------------------------------------------------------COMMENT
MEDIUMxinference/api/utils.py31# ---------------------------------------------------------------------------COMMENT
6 more matches not shown…
AI Structural Patterns230 hits · 221 pts
SeverityFileLineSnippetContext
LOWxinference/core/worker.py2712CODE
LOWxinference/core/worker.py3766CODE
LOWxinference/core/metrics.py679CODE
LOWxinference/core/supervisor.py1914CODE
LOWxinference/core/supervisor.py2393CODE
LOWxinference/core/supervisor.py3649CODE
LOWxinference/core/supervisor.py3665CODE
LOWxinference/deploy/utils.py217CODE
LOWxinference/model/llm/memory.py299CODE
LOWxinference/model/llm/lmdeploy/core.py306CODE
LOWxinference/model/llm/vllm/distributed_executor_v1.py100CODE
LOW…nference/model/embedding/sentence_transformers/core.py320CODE
LOWxinference/model/embedding/vllm/core.py280CODE
LOWxinference/model/image/core.py208CODE
LOWxinference/model/image/ocr/paddleocr_vl.py222CODE
LOWxinference/model/image/stable_diffusion/core.py88CODE
LOWxinference/model/rerank/sentence_transformers/core.py359CODE
LOWxinference/api/restful_api.py1799CODE
LOWxinference/api/restful_api.py1858CODE
LOWxinference/api/restful_api.py1956CODE
LOWxinference/api/restful_api.py440CODE
LOWxinference/api/routers/admin.py385CODE
LOWxinference/api/routers/admin.py836CODE
LOWxinference/client/restful/restful_client.py1180CODE
LOWxinference/client/restful/async_restful_client.py1294CODE
LOWxinference/thirdparty/cosyvoice/dataset/dataset.py104CODE
LOWxinference/thirdparty/cosyvoice/hifigan/generator.py397CODE
LOWxinference/thirdparty/cosyvoice/transformer/decoder.py58CODE
LOWxinference/thirdparty/cosyvoice/transformer/decoder.py276CODE
LOW…e/thirdparty/cosyvoice/transformer/upsample_encoder.py107CODE
LOWxinference/thirdparty/cosyvoice/transformer/encoder.py39CODE
LOWxinference/thirdparty/cosyvoice/transformer/encoder.py341CODE
LOWxinference/thirdparty/cosyvoice/transformer/encoder.py390CODE
LOWxinference/thirdparty/cosyvoice/utils/mask.py158CODE
LOWxinference/thirdparty/cosyvoice/cli/model.py170CODE
LOWxinference/thirdparty/cosyvoice/cli/model.py321CODE
LOWxinference/thirdparty/cosyvoice/flow/decoder.py295CODE
LOWxinference/thirdparty/cosyvoice/flow/flow.py25CODE
LOWxinference/thirdparty/cosyvoice/flow/flow.py152CODE
LOWxinference/thirdparty/deepseek_vl2/models/siglip_vit.py194CODE
LOWxinference/thirdparty/deepseek_vl2/models/siglip_vit.py249CODE
LOW…party/deepseek_vl2/models/processing_deepseek_vl_v2.py132CODE
LOW…ce/thirdparty/deepseek_vl2/models/modeling_deepseek.py264CODE
LOW…ce/thirdparty/deepseek_vl2/models/modeling_deepseek.py1472CODE
LOW…ce/thirdparty/deepseek_vl2/models/modeling_deepseek.py1657CODE
LOW…ce/thirdparty/deepseek_vl2/models/modeling_deepseek.py1878CODE
LOW…irdparty/deepseek_vl2/models/configuration_deepseek.py117CODE
LOW…rdparty/deepseek_vl2/models/modeling_deepseek_vl_v2.py134CODE
LOW…rdparty/deepseek_vl2/models/modeling_deepseek_vl_v2.py559CODE
LOW…rdparty/deepseek_vl2/models/modeling_deepseek_vl_v2.py642CODE
LOWxinference/thirdparty/audiotools/post.py90CODE
LOWxinference/thirdparty/audiotools/metrics/spectral.py41CODE
LOWxinference/thirdparty/audiotools/metrics/spectral.py124CODE
LOWxinference/thirdparty/audiotools/core/loudness.py100CODE
LOWxinference/thirdparty/audiotools/data/transforms.py755CODE
LOWxinference/thirdparty/audiotools/data/transforms.py892CODE
LOWxinference/thirdparty/audiotools/data/transforms.py1453CODE
LOWxinference/thirdparty/audiotools/data/transforms.py1565CODE
LOWxinference/thirdparty/audiotools/data/datasets.py358CODE
LOW…/thirdparty/fish_speech/tools/sensevoice/auto_model.py279CODE
170 more matches not shown…
Modern Structural Boilerplate176 hits · 178 pts
SeverityFileLineSnippetContext
LOWbenchmark/benchmark_long.py27logger = logging.getLogger(__name__)CODE
LOWbenchmark/utils.py25logger = logging.getLogger(__name__)CODE
LOWbenchmark/benchmark_embedding.py28logger = logging.getLogger(__name__)CODE
LOWbenchmark/benchmark_runner.py28logger = logging.getLogger(__name__)CODE
LOWbenchmark/benchmark_latency.py26logger = logging.getLogger(__name__)CODE
LOWbenchmark/benchmark_rerank.py28logger = logging.getLogger(__name__)CODE
LOWbenchmark/benchmark_serving.py27logger = logging.getLogger(__name__)CODE
LOWxinference/device_utils.py22logger = logging.getLogger(__name__)CODE
LOWxinference/core/metrics.py27logger = logging.getLogger(__name__)CODE
LOWxinference/core/metrics.py613def update_security_gauges(auth_service) -> None:CODE
LOWxinference/core/progress_tracker.py35logger = logging.getLogger(__name__)CODE
LOWxinference/core/monitor_config_store.py22logger = logging.getLogger(__name__)CODE
LOWxinference/core/virtual_env_manager.py24logger = logging.getLogger(__name__)CODE
LOWxinference/core/model.py53logger = logging.getLogger(__name__)CODE
LOWxinference/core/utils.py36logger = logging.getLogger(__name__)CODE
LOWxinference/core/launch_history_store.py28logger = logging.getLogger(__name__)CODE
LOWxinference/core/otel.py44logger = logging.getLogger(__name__)CODE
LOWxinference/deploy/worker.py27logger = logging.getLogger(__name__)CODE
LOWxinference/deploy/supervisor.py32logger = logging.getLogger(__name__)CODE
LOWxinference/deploy/local.py36logger = logging.getLogger(__name__)CODE
LOWxinference/deploy/utils.py44logger = logging.getLogger(__name__)CODE
LOWxinference/model/custom.py26logger = logging.getLogger(__name__)CODE
LOWxinference/model/cache_manager.py9logger = logging.getLogger(__name__)CODE
LOWxinference/model/batch.py24logger = logging.getLogger(__name__)CODE
LOWxinference/model/utils.py61logger = logging.getLogger(__name__)CODE
LOWxinference/model/video/core.py22logger = logging.getLogger(__name__)CODE
LOWxinference/model/video/diffusers.py39logger = logging.getLogger(__name__)CODE
LOWxinference/model/video/tests/test_diffusers_video.py22logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/reasoning_parser.py12logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/custom.py24logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/cache_manager.py25logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/llm_family.py43logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/core.py35logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/utils.py59logger = logging.getLogger(__name__)CODE
LOW…ence/model/llm/tool_parsers/deepseek_v4_tool_parser.py8logger = logging.getLogger(__name__)CODE
LOW…ence/model/llm/tool_parsers/deepseek_v3_tool_parser.py9logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/tool_parsers/gemma_tool_parser.py9logger = logging.getLogger(__name__)CODE
LOW…nference/model/llm/tool_parsers/minimax_tool_parser.py9logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/tool_parsers/glm5_tool_parser.py9logger = logging.getLogger(__name__)CODE
LOW…ce/model/llm/tool_parsers/deepseek_v3_1_tool_parser.py9logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/tool_parsers/qwen_tool_parser.py9logger = logging.getLogger(__name__)CODE
LOW…ence/model/llm/tool_parsers/deepseek_r1_tool_parser.py9logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/tool_parsers/glm4_tool_parser.py8logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/tool_parsers/llama3_tool_parser.py9logger = logging.getLogger(__name__)CODE
LOW…ce/model/llm/tool_parsers/deepseek_v3_2_tool_parser.py8logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/lmdeploy/core.py35logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/distributed_executor_v1.py44logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/distributed_executor.py40logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/core.py73logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/core.py267def _update_vllm_supported_lists() -> None:CODE
LOWxinference/model/llm/vllm/utils.py19logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/xavier/collective.py17logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/xavier/block_manager.py25logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/xavier/transfer.py28logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/xavier/engine.py31logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/xavier/scheduler.py37logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/xavier/block.py27logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/xavier/collective_manager.py27logger = logging.getLogger(__name__)CODE
LOW…ce/model/llm/vllm/patches/hybrid_kv_cache_page_size.py20logger = logging.getLogger(__name__)CODE
LOWxinference/model/llm/vllm/patches/__init__.py15logger = logging.getLogger(__name__)CODE
116 more matches not shown…
Self-Referential Comments43 hits · 130 pts
SeverityFileLineSnippetContext
MEDIUMversioneer.py491# This file is released into the public domain.COMMENT
MEDIUMxinference/_version.py7# This file is released into the public domain.COMMENT
MEDIUMxinference/core/virtual_env_manager.py467 # This method is deprecated and no longer neededCOMMENT
MEDIUMxinference/core/tests/test_restful_api.py1467 # Create a mock handler with the conversion methodCOMMENT
MEDIUMxinference/core/tests/test_restful_api.py1474 # Create a temporary RESTfulAPI instance to access the methodCOMMENT
MEDIUMxinference/deploy/test/test_log_rotation.py211 # Create a file dated 100 days agoCOMMENT
MEDIUMxinference/model/utils.py1975 # Create a mapping of updated_at to model for comparisonCOMMENT
MEDIUMxinference/model/utils.py2044 # Create a copy of built-in models for mergingCOMMENT
MEDIUMxinference/model/llm/__init__.py294 # Create a copy of built-in models for mergingCOMMENT
MEDIUMxinference/model/llm/vllm/distributed_executor_v1.py157 # Create the parallel GPU workers.COMMENT
MEDIUMxinference/model/llm/vllm/distributed_executor.py146 # Create the parallel GPU workers.COMMENT
MEDIUMxinference/model/llm/transformers/chatglm.py126 # This method is adapted from https://github.com/THUDM/GLM-4/blob/main/basic_demo/openai_api_server.pyCOMMENT
MEDIUMxinference/model/llm/transformers/core.py64# Define the decorator to support multiple names registrationCOMMENT
MEDIUM…erence/model/llm/transformers/tests/test_tensorizer.py100 # Create a dummy cache file to simulate cache existenceCOMMENT
MEDIUM…ence/model/embedding/vllm/tests/test_vllm_embedding.py104 # Create a long text that exceeds 512 tokensCOMMENT
MEDIUMxinference/model/rerank/sentence_transformers/core.py230 # Create a simple wrapper for return value conversion onlyCOMMENT
MEDIUMxinference/thirdparty/audiotools/ml/accelerator.py14 """This class is used to prepare models and dataloaders forSTRING
MEDIUMxinference/thirdparty/fish_speech/tools/run_webui.py73 # Create the inference engineCOMMENT
MEDIUM…rence/thirdparty/fish_speech/tools/vqgan/extract_vq.py24# This file is used to convert the audio files to text files using the Whisper model.COMMENT
MEDIUM…fish_speech/tools/server/agent/pre_generation_utils.py39 # Create a conversation object and encode it for inferenceCOMMENT
MEDIUM…fish_speech/tools/inference_engine/reference_loader.py29 # Define the torchaudio backendCOMMENT
MEDIUM…rdparty/fish_speech/tools/inference_engine/__init__.py166 # Create a queue to get the responseCOMMENT
MEDIUM…erence/thirdparty/fish_speech/fish_speech/i18n/scan.py55# Define the standard file nameCOMMENT
MEDIUM…erence/thirdparty/fish_speech/fish_speech/i18n/scan.py78# Define the standard file nameCOMMENT
MEDIUMxinference/thirdparty/melo/text/japanese.py540# Initialize kakasi objectCOMMENT
MEDIUMxinference/thirdparty/melo/text/japanese.py636# # Initialize kakasi objectCOMMENT
MEDIUMxinference/thirdparty/melo/text/korean.py181# # Initialize kakasi objectCOMMENT
MEDIUMxinference/thirdparty/f5_tts/infer/utils_infer.py509 # Create a combined spectrogramCOMMENT
MEDIUMxinference/thirdparty/deepseek_vl/serve/app_deepseek.py96 # Create a copy of the conversation to avoid history truncation in the UICOMMENT
MEDIUMxinference/thirdparty/megatts3/tts/infer_cli.py49 # Define the output path with a .wav extensionCOMMENT
MEDIUM…erence/thirdparty/megatts3/tts/utils/audio_utils/io.py63 # Define the output path with a .wav extensionCOMMENT
MEDIUMxinference/thirdparty/mlx/flux/flux.py142 # Create the latent variablesCOMMENT
MEDIUMxinference/thirdparty/matcha/onnx/export.py164 # Create the output directory (if not exists)COMMENT
MEDIUMxinference/thirdparty/indextts/infer_v2.py926 # Create a temporary file for the complete audioCOMMENT
MEDIUM…irdparty/indextts/gpt/transformers_generation_utils.py496 # Create the causal mask with fixed shape in advance, to reduce recompilations. If the function to createCOMMENT
MEDIUMxinference/thirdparty/indextts/BigVGAN/ECAPA_TDNN.py246 """This class implements an attentive statistic pooling layer for each channel.STRING
MEDIUMxinference/thirdparty/indextts/BigVGAN/ECAPA_TDNN.py585 """This class implements the cosine similarity on the top of features.STRING
MEDIUMxinference/thirdparty/indextts/BigVGAN/nnet/CNN.py24 """This function implements SincConv (SincNet).STRING
MEDIUMxinference/thirdparty/indextts/BigVGAN/nnet/CNN.py306 """This function implements 1d convolution.STRING
MEDIUM…/utils/maskgct/models/codec/facodec/facodec_trainer.py521 # Create the normalized F0 sequence with unvoiced framesCOMMENT
MEDIUMxinference/thirdparty/indextts/s2mel/modules/commons.py380 # Create the normalized F0 sequence with unvoiced framesCOMMENT
MEDIUMdoc/source/gen_docs.py67 # Create a proper ModuleSpec that importlib.util.find_spec can findCOMMENT
MEDIUMdoc/source/norm_zh.py15# This file is derived from https://github.com/mars-project/mars/blob/master/docs/source/norm_zh.pyCOMMENT
Docstring Block Structure21 hits · 105 pts
SeverityFileLineSnippetContext
HIGHxinference/utils.py87 Recursively convert an object into a hashable form. This function is useful for creating deterministic cache kSTRING
HIGHxinference/deploy/utils.py996Convert CLI string arguments to appropriate Python types. Handles type conversion for Click command arguments with STRING
HIGH…ence/model/llm/tool_parsers/deepseek_v4_tool_parser.py95 Extract tool calls from complete model output. Args: model_output: The complete output strSTRING
HIGH…ce/model/llm/tool_parsers/deepseek_v3_2_tool_parser.py95 Extract tool calls from complete model output. Args: model_output: The complete output strSTRING
HIGHxinference/model/embedding/core.py352 Extract the 'sentences' argument and remaining kwargs from (*args, **kwargs) for a given function. STRING
HIGHxinference/model/rerank/sentence_transformers/core.py640 Extract the 'documents' and 'query' argument and remaining kwargs from (*args, **kwargs) for a given fuSTRING
HIGHxinference/model/rerank/vllm/core.py303 Extract the 'documents' and 'query' argument and remaining kwargs from (*args, **kwargs) for a given fuSTRING
HIGHxinference/api/utils.py93 Get a model with standardized error handling. Replaces the repeated pattern: ```python try: moSTRING
HIGHxinference/thirdparty/cosyvoice/utils/mask.py18 def subsequent_mask( size: int, device: torch.device = torch.device("cpu"), ) -> torch.Tensor: """CSTRING
HIGHxinference/thirdparty/cosyvoice/utils/mask.py57Create mask for subsequent steps (size, size). This mask is used only in decoder which works in an auto-regressive STRING
HIGHxinference/thirdparty/cosyvoice/utils/mask.py95Create mask for subsequent steps (size, size) with chunk size, this is for streaming encoder Args: sSTRING
HIGHxinference/thirdparty/cosyvoice/utils/mask.py133Create mask for subsequent steps (size, size) with chunk size, this is for streaming encoder Args: sSTRING
HIGHxinference/thirdparty/cosyvoice/utils/mask.py240Make mask tensor containing indices of padded part. See description of make_non_pad_mask. Args: lengthSTRING
HIGHxinference/thirdparty/cosyvoice/utils/common.py30Perform padding for the list of tensors. Args: xs (List): List of Tensors [(T_1, `*`), (T_2, `*`), ..., (T_STRING
HIGHxinference/thirdparty/cosyvoice/flow/decoder.py211Forward pass of the UNet1DConditional model. Args: x (torch.Tensor): shape (batch_size, in_channelsSTRING
HIGHxinference/thirdparty/cosyvoice/flow/decoder.py406Forward pass of the UNet1DConditional model. Args: x (torch.Tensor): shape (batch_size, in_channelsSTRING
HIGH…party/megatts3/tts/modules/ar_dur/commons/seq_utils.py113Make mask tensor containing indices of padded part. Args: lengths (LongTensor or List): Batch of lengths (B,STRING
HIGH…party/megatts3/tts/modules/ar_dur/commons/seq_utils.py219Make mask tensor containing indices of non-padded part. Args: lengths (LongTensor or List): Batch of lengthsSTRING
HIGH…ference/thirdparty/matcha/models/components/decoder.py364Forward pass of the UNet1DConditional model. Args: x (torch.Tensor): shape (batch_size, in_channelsSTRING
HIGHxinference/thirdparty/indextts/utils/common.py85Make mask tensor containing indices of padded part. See description of make_non_pad_mask. Args: lengthSTRING
HIGHxinference/thirdparty/indextts/utils/utils.py54Make mask tensor containing indices of padded part. See description of make_non_pad_mask. Args: lengthSTRING
Cross-Language Confusion15 hits · 85 pts
SeverityFileLineSnippetContext
HIGHbenchmark/benchmark_runner.py142 # "finish_reason": null,COMMENT
HIGHxinference/deploy/test/test_utils.py113 arg = '{"int_val": 10, "float_val": 1.5, "bool_val": false, "null_val": null}'CODE
HIGHxinference/deploy/test/test_utils.py219 result = handle_click_args_type('[1, "two", null, true, {"key": "value"}]')CODE
HIGHxinference/model/llm/tool_parsers/llama3_tool_parser.py53 # (e.g., True/False/None instead of true/false/null).COMMENT
HIGH…odel/llm/tool_parsers/tests/test_llama3_tool_parser.py41 model_output = '{"name": "test_func", "parameters": {"value": null}}'CODE
HIGHxinference/model/llm/tests/test_utils.py2116 "arguments": None, # null, left as-isCODE
HIGHxinference/model/llm/tests/test_utils.py2134 "arguments": "null", # valid JSON null, left as-isCODE
HIGHxinference/api/restful_api.py608 "npm ci && npm run build" (this stages the export at the directoryCODE
HIGH…nference/api/tests/test_frontend_static_real_export.py18(``cd frontend && npm run build``) and runs this module againstSTRING
HIGHxinference/thirdparty/audiotools/preference.py179 if (region != null) {CODE
HIGH…ference/thirdparty/fish_speech/tools/webui/__init__.py18 js="() => {const params = new URLSearchParams(window.location.search);if (!params.has('__theme')) {params.seCODE
HIGH…odels/codec/speechtokenizer/modules/quantization/ac.py138 self.packer.push(b1)CODE
HIGH…odels/codec/speechtokenizer/modules/quantization/ac.py185 self.packer.push(b1)CODE
HIGH…odels/codec/speechtokenizer/modules/quantization/ac.py304 encoder.push(symbol, q_cdf)CODE
HIGH…nce/thirdparty/indextts/s2mel/modules/flow_matching.py88 # Stack original and CFG (null) inputs for batched processingCOMMENT
Redundant / Tautological Comments49 hits · 73 pts
SeverityFileLineSnippetContext
LOWxinference/core/worker.py2565 # Check if packages contain PyTorch system markers (#system_torch#, etc.)COMMENT
LOWxinference/core/worker.py2841 # Check if cancelled while waiting in queueCOMMENT
LOWxinference/model/utils.py1843 # Check if flash_attn is installedCOMMENT
LOWxinference/model/utils.py1851 # Check if CUDA is availableCOMMENT
LOWxinference/model/llm/reasoning_parser.py55 # Check if <think> is present in previous or delta.COMMENT
LOWxinference/model/llm/llm_family.py387 # Append the class to the list of transformer classesCOMMENT
LOWxinference/model/llm/harmony.py60 # Check if buffer ends with partial 'assistantfinal'COMMENT
LOWxinference/model/llm/harmony.py76 # Check if this is actually a new message starting with 'analysis'COMMENT
LOWxinference/model/llm/harmony.py102 # Check if buffer ends with partial 'assistantfinal'COMMENT
LOWxinference/model/llm/tool_parsers/qwen_tool_parser.py329 # Check if current output contains tool_call start tokenCOMMENT
LOW…ence/model/llm/tool_parsers/deepseek_r1_tool_parser.py86 # Check if this block is a tool callCOMMENT
LOWxinference/model/llm/tests/test_llm_model.py311 # Check if tool_calls is present and is a listCOMMENT
LOWxinference/model/llm/tests/test_llm_model.py325 # Check if arguments is a valid JSON stringCOMMENT
LOWxinference/model/llm/vllm/xavier/engine.py125 # Check if we have a cached last_output from the previous iteration.COMMENT
LOW…ce/model/llm/vllm/patches/hybrid_kv_cache_page_size.py107 # Check if the original problematic code existsCOMMENT
LOW…ce/model/llm/vllm/patches/hybrid_kv_cache_page_size.py119 # Check if all smaller pages divide max evenlyCOMMENT
LOWxinference/model/llm/transformers/core.py469 # Check if streamingCOMMENT
LOWxinference/model/llm/transformers/core.py1055 # Check if streamingCOMMENT
LOW…erence/model/llm/transformers/tests/test_tensorizer.py118 # Check if the logger.info was called with the expected message, indicating early return due to cache existenceCOMMENT
LOWxinference/model/llm/mlx/core.py127 # Check if next_generated method exists (new API)COMMENT
LOWxinference/model/llm/mlx/core.py274 # Check if there are any pending results (early results that arrived before queue was ready)COMMENT
LOWxinference/model/llm/mlx/core.py322 # Check if generation is finishedCOMMENT
LOWxinference/model/llm/mlx/core.py343 # Check if request is still in active setCOMMENT
LOWxinference/model/llm/mlx/core.py1534 # Check if processor supports audio to avoid feature_extractor errorsCOMMENT
LOWxinference/model/embedding/core.py215 # Check if sentences is a two-dimensional list of integersCOMMENT
LOWxinference/model/image/stable_diffusion/core.py875 # Check if we have a cancel callback for this requestCOMMENT
LOWxinference/api/restful_api.py1352 # Check if iterator is actually an async iteratorCOMMENT
LOWxinference/thirdparty/fish_speech/tools/run_webui.py48 # Check if MPS or CUDA is availableCOMMENT
LOW…e/thirdparty/fish_speech/tools/server/model_manager.py37 # Check if MPS or CUDA is availableCOMMENT
LOWxinference/thirdparty/fish_speech/tools/server/views.py159 # Check if the text is too longCOMMENT
LOWxinference/thirdparty/fish_speech/tools/server/views.py166 # Check if streaming is enabledCOMMENT
LOW…/thirdparty/fish_speech/tools/server/agent/generate.py64 # Check if all samples are finishedCOMMENT
LOW…rty/fish_speech/tools/server/agent/generation_utils.py102 # Check if the token is semanticCOMMENT
LOWxinference/thirdparty/f5_tts/socket_server.py85 # Check if it's the final chunkCOMMENT
LOWxinference/thirdparty/f5_tts/train/finetune_gradio.py417 # Check if a training process is already runningCOMMENT
LOWxinference/thirdparty/f5_tts/infer/infer_gradio.py504 # Check if all speech types in text are availableSTRING
LOWxinference/thirdparty/megatts3/tts/infer_cli.py42 # Check if the file existsCOMMENT
LOWxinference/thirdparty/megatts3/tts/infer_cli.py47 # Check if the file already has a .wav extensionCOMMENT
LOW…erence/thirdparty/megatts3/tts/utils/audio_utils/io.py56 # Check if the file existsCOMMENT
LOW…erence/thirdparty/megatts3/tts/utils/audio_utils/io.py61 # Check if the file already has a .wav extensionCOMMENT
LOWxinference/thirdparty/indextts/infer_v2.py110 # Check if it's a HuggingFace cache structure with snapshotsCOMMENT
LOWxinference/thirdparty/indextts/gpt/perceiver.py87 # Check if mask exists and expand to compatible shapeCOMMENT
LOWxinference/thirdparty/indextts/gpt/perceiver.py94 # Check if there is a compatible device for flash attentionCOMMENT
LOW…ce/thirdparty/indextts/gpt/transformers_beam_search.py307 # Check if we are done so that we can save a pad step if all(done)STRING
LOW…ce/thirdparty/indextts/gpt/transformers_beam_search.py659 # Check if we are done so that we can save a pad step if all(done)STRING
LOW…thirdparty/indextts/gpt/transformers_modeling_utils.py2477 # Check if the covariance is positive definite.COMMENT
LOW…thirdparty/indextts/gpt/transformers_modeling_utils.py4060 # Check if `_keep_in_fp32_modules` is not NoneSTRING
LOW…ty/indextts/BigVGAN/alias_free_activation/cuda/load.py49 # Check if cuda 11 is installed for compute capability 8.0COMMENT
LOW…mel/modules/bigvgan/alias_free_activation/cuda/load.py18 # Check if cuda 11 is installed for compute capability 8.0COMMENT
Modern AI Meta-Vocabulary14 hits · 50 pts
SeverityFileLineSnippetContext
MEDIUMxinference/core/tests/test_model.py250 # rerank/embedding model must run del + empty_cache so its VRAM isCOMMENT
MEDIUMxinference/core/tests/test_worker.py926 # test terminate LLM model, then launch embedding modelCOMMENT
MEDIUMxinference/model/embedding/embed_family.py113# { embedding model name -> { engine name -> engine params } }COMMENT
MEDIUMxinference/model/embedding/core.py90# this class define the basic info of embedding modelCOMMENT
MEDIUM…nference/model/embedding/sentence_transformers/core.py509 # seems already support prompt in embedding modelCOMMENT
MEDIUMxinference/api/restful_api.py499 # Attach API instance for dependency injection (Depends(get_api), etc.)COMMENT
MEDIUMxinference/api/schemas/requests.py33 # <0 = cap at the model's max_tokens. Honored by the embedding model baseCOMMENT
MEDIUM…ference/thirdparty/deepseek_vl2/models/conversation.py33 # The number of few shot examplesCOMMENT
MEDIUMxinference/thirdparty/deepseek_vl/utils/conversation.py65 # The number of few shot examplesCOMMENT
MEDIUMxinference/thirdparty/internvl/conversation.py50 # The number of few shot examplesCOMMENT
MEDIUMxinference/thirdparty/whisper/transcribe.py402 # skip silence before possible hallucinationsCOMMENT
MEDIUMxinference/thirdparty/whisper/transcribe.py414 # if first segment might be a hallucination, skip leading silenceCOMMENT
MEDIUMxinference/thirdparty/whisper/transcribe.py422 # skip silence before any possible hallucination that is surroundedCOMMENT
MEDIUMxinference/thirdparty/whisper/transcribe.py423 # by silence or more hallucinationsCOMMENT
AI Slop Vocabulary19 hits · 36 pts
SeverityFileLineSnippetContext
LOWversioneer.py510 # each be defined on a line of their own. _version.py will just callCOMMENT
LOWxinference/_version.py26 # each be defined on a line of their own. _version.py will just callCOMMENT
LOWxinference/core/supervisor.py2591 # Not launched perhaps, just return 0.0 to prevent errorCOMMENT
LOWxinference/model/utils.py1969 # New model from user, just add itCOMMENT
LOWxinference/model/llm/llm_family.py613 # TODO: If user does not specify quantization, just use the first oneCOMMENT
MEDIUMxinference/model/llm/core.py245 # Use model_specs from huggingface, as HuggingFace is the most comprehensive.COMMENT
LOWxinference/model/embedding/embed_family.py103 # TODO: If user does not specify quantization, just use the first oneCOMMENT
LOWxinference/model/rerank/rerank_family.py102 # TODO: If user does not specify quantization, just use the first oneCOMMENT
LOW…erence/thirdparty/cosyvoice/transformer/convolution.py124 # It's better we just return None if no cache is required,COMMENT
MEDIUMxinference/thirdparty/cosyvoice/utils/executor.py45 # A context manager to be used in conjunction with an instance ofCOMMENT
MEDIUMxinference/thirdparty/cosyvoice/utils/executor.py97 # A context manager to be used in conjunction with an instance ofCOMMENT
LOWxinference/thirdparty/f5_tts/model/cfm.py136 duration = torch.maximum(lens + 1, duration) # just add one token so something is generatedCODE
LOWxinference/thirdparty/f5_tts/model/dataset.py214 # if want to have different batches between epochs, may just set a seed and log it in ckptCOMMENT
MEDIUMxinference/thirdparty/f5_tts/infer/speech_edit.py54# [leverage https://github.com/MahmoudAshraf97/ctc-forced-aligner to get char level alignment]COMMENT
MEDIUM…irdparty/indextts/gpt/transformers_generation_utils.py437 # (this alternative is not as robust as calling `generate` and letting it create `cache_position`)COMMENT
MEDIUM…irdparty/indextts/gpt/transformers_generation_utils.py713 # 1. Check whether the user has defined `decoder_input_ids` manually. To facilitate in terms of input naming,COMMENT
LOW…ce/thirdparty/indextts/gpt/transformers_beam_search.py854 # generation. In these cases we simply return the highest scoring outputs.STRING
LOW…thirdparty/indextts/gpt/transformers_modeling_utils.py5402 # We can probably just use the multi-head attention module of PyTorch >=1.1.0STRING
LOWxinference/thirdparty/indextts/gpt/conformer_encoder.py146 # It's better we just return None if no cache is required,COMMENT
Dead Code9 hits · 18 pts
SeverityFileLineSnippetContext
MEDIUM…tts/BigVGAN/alias_free_activation/cuda/activation1d.py31CODE
MEDIUM…nce/thirdparty/indextts/s2mel/modules/openvoice/api.py149CODE
MEDIUM…nce/thirdparty/indextts/s2mel/modules/openvoice/api.py150CODE
MEDIUM…nce/thirdparty/indextts/s2mel/modules/openvoice/api.py151CODE
MEDIUM…nce/thirdparty/indextts/s2mel/modules/openvoice/api.py153CODE
MEDIUM…nce/thirdparty/indextts/s2mel/modules/openvoice/api.py154CODE
MEDIUM…nce/thirdparty/indextts/s2mel/modules/openvoice/api.py155CODE
MEDIUM…nce/thirdparty/indextts/s2mel/modules/openvoice/api.py168CODE
MEDIUM…les/bigvgan/alias_free_activation/cuda/activation1d.py32CODE
Structural Annotation Overuse12 hits · 16 pts
SeverityFileLineSnippetContext
LOW…m/tool_parsers/tests/test_deepseek_v3_1_tool_parser.py281 # Step 1: Part 1 of end tokenCOMMENT
LOW…m/tool_parsers/tests/test_deepseek_v3_1_tool_parser.py288 # Step 2: Part 2 of end tokenCOMMENT
LOWxinference/model/llm/tests/test_stream_options.py1016 # Step 1: Get the initial response with stream=TrueCOMMENT
LOWxinference/model/llm/tests/test_stream_options.py1034 # Step 2: Get the final response after tool calls with stream=TrueCOMMENT
LOWxinference/model/llm/tests/test_stream_options.py1052 # Step 3: Get the initial response with stream=FalseCOMMENT
LOWxinference/model/llm/tests/test_stream_options.py1069 # Step 4: Get the final response after tool calls with stream=FalseCOMMENT
LOWxinference/thirdparty/fish_speech/tools/fish_e2e.py106 # Step 1: Encode audio using VQGANCOMMENT
LOWxinference/thirdparty/fish_speech/tools/fish_e2e.py135 # Step 2: Prepare LLM requestCOMMENT
LOWxinference/thirdparty/fish_speech/tools/fish_e2e.py182 # Step 3: Stream LLM response and decode audioCOMMENT
LOW…irdparty/indextts/gpt/transformers_generation_utils.py3615 # IMPORTANT: Note that this should appear BEFORE the call to _reorder_cache() to save the maximum memorySTRING
LOW…irdparty/indextts/gpt/transformers_generation_utils.py3908 # IMPORTANT: Note that this should appear BEFORE the call to _reorder_cache() to save the maximum memorySTRING
LOW…irdparty/indextts/gpt/transformers_generation_utils.py4146 # IMPORTANT: Note that this should appear BEFORE the call to _reorder_cache() to save the maximum memorySTRING
Verbosity Indicators9 hits · 15 pts
SeverityFileLineSnippetContext
LOW…m/tool_parsers/tests/test_deepseek_v3_1_tool_parser.py281 # Step 1: Part 1 of end tokenCOMMENT
LOW…m/tool_parsers/tests/test_deepseek_v3_1_tool_parser.py288 # Step 2: Part 2 of end tokenCOMMENT
LOWxinference/model/llm/tests/test_stream_options.py1016 # Step 1: Get the initial response with stream=TrueCOMMENT
LOWxinference/model/llm/tests/test_stream_options.py1034 # Step 2: Get the final response after tool calls with stream=TrueCOMMENT
LOWxinference/model/llm/tests/test_stream_options.py1052 # Step 3: Get the initial response with stream=FalseCOMMENT
LOWxinference/model/llm/tests/test_stream_options.py1069 # Step 4: Get the final response after tool calls with stream=FalseCOMMENT
LOWxinference/thirdparty/fish_speech/tools/fish_e2e.py106 # Step 1: Encode audio using VQGANCOMMENT
LOWxinference/thirdparty/fish_speech/tools/fish_e2e.py135 # Step 2: Prepare LLM requestCOMMENT
LOWxinference/thirdparty/fish_speech/tools/fish_e2e.py182 # Step 3: Stream LLM response and decode audioCOMMENT
Hallucination Indicators1 hit · 10 pts
SeverityFileLineSnippetContext
CRITICALxinference/thirdparty/audiotools/core/util.py475 batch[k] = torch.utils.data._utils.collate.default_collate(v)CODE
Slop Phrases3 hits · 8 pts
SeverityFileLineSnippetContext
MEDIUMxinference/thirdparty/melo/text/chinese.py73 assert len(word2ph) == len(text) # Sometimes it will crash,you can add a try-catch.CODE
MEDIUMxinference/thirdparty/melo/text/chinese_mix.py80 # assert len(word2ph) == len(text) # Sometimes it will crash,you can add a try-catch.COMMENT
MEDIUM…nce/thirdparty/f5_tts/train/datasets/prepare_emilia.py2# if use updated new version, i.e. WebDataset, feel free to modify / draft your own scriptCOMMENT
Magic Placeholder Names1 hit · 5 pts
SeverityFileLineSnippetContext
HIGHxinference/thirdparty/fish_speech/tools/api_client.py176 "authorization": "Bearer YOUR_API_KEY",CODE
Fake / Example Data3 hits · 4 pts
SeverityFileLineSnippetContext
LOWdoc/source/norm_zh.py62 ... "Lorem ipsum dolor sit amet, consectetur adipisicing elit, "CODE
LOWdoc/source/norm_zh.py62 ... "Lorem ipsum dolor sit amet, consectetur adipisicing elit, "CODE
LOWdoc/source/norm_zh.py66 " \"Lorem ipsum dolor sit "CODE
Example Usage Blocks2 hits · 2 pts
SeverityFileLineSnippetContext
LOWxinference/thirdparty/fish_speech/tools/fish_e2e.py263# Example usage:COMMENT
LOW…party/matcha/utils/get_durations_from_trained_model.py192 # Example usage:STRING
Overly Generic Function Names1 hit · 1 pts
SeverityFileLineSnippetContext
LOW…ce/thirdparty/fish_speech/tools/llama/build_dataset.py65def run_task(task):CODE