A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.
This report summarizes scanner evidence for josStorer/RWKV-Runner, a TypeScript project with 6,482 GitHub stars. SynthScan examined 140,730 lines of code across 408 source files, recording 1134 pattern matches distributed across 20 syntactic categories. The legacy adjusted pattern signal is 9.6 (Moderate pattern signal); it is not an authorship estimate.
Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.
Use each vector to guide manual verification of the underlying findings.
Can maintainers explain intent, assumptions, and trade-offs? 668 finding(s).
Are imports declared and package/API names verified? 309 finding(s).
Are wrappers, guards, and repeated structures necessary? 558 finding(s).
Which changes need focused human review? 1134 finding(s).
This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.
Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.
This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.
The scanner identified 1134 distinct pattern matches across 20 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.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | frontend/wailsjs/go/backend_golang/App.d.ts | 25 | export function ConvertSafetensorsWithPython(arg1:string,arg2:string,arg3:string):Promise<string>; | CODE |
| LOW | frontend/wailsjs/go/backend_golang/App.d.ts | 51 | export function GetMaxCudaComputeCapability():Promise<string>; | CODE |
| LOW | frontend/wailsjs/go/backend_golang/App.js | 45 | export function ConvertSafetensorsWithPython(arg1, arg2, arg3) { | CODE |
| LOW | frontend/wailsjs/go/backend_golang/App.js | 97 | export function GetMaxCudaComputeCapability() { | CODE |
| LOW | frontend/wailsjs/runtime/runtime.d.ts | 103 | export function WindowSetSystemDefaultTheme(): void; | CODE |
| LOW | frontend/wailsjs/runtime/runtime.d.ts | 203 | export function WindowSetBackgroundColour(R: number, G: number, B: number, A: number): void; | CODE |
| LOW | frontend/wailsjs/runtime/runtime.js | 72 | export function WindowSetSystemDefaultTheme() { | CODE |
| LOW | frontend/wailsjs/runtime/runtime.js | 160 | export function WindowSetBackgroundColour(R, G, B, A) { | CODE |
| LOW | frontend/src/utils/index.tsx | 188 | function initLastUnfinishedModelDownloads() { | CODE |
| LOW | frontend/src/utils/index.tsx | 457 | export function forceDownloadProgramFiles() { | CODE |
| LOW | frontend/src/utils/index.tsx | 464 | export async function deleteDynamicProgramFiles() { | CODE |
| LOW | frontend/src/utils/index.tsx | 855 | export function getMidiRawContentMainInstrument(rawContent: MidiMessage[]) { | CODE |
| LOW | frontend/src/utils/index.tsx | 877 | export function flushMidiRecordingContent() { | CODE |
| LOW | frontend/src/utils/rwkv-task.ts | 267 | export async function convertSafetensorsWithPython( | CODE |
| LOW | frontend/src/utils/get-available-torch-cu-version.ts | 5 | export function getAvailableTorchCuVersion( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cache.py | 228 | def _find_longest_prefix_node( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_speculative.py | 136 | def find_candidate_pred_tokens( | CODE |
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_ggml.py | 1094 | def ggml_backend_buffer_clear(buffer: ggml_backend_buffer_t, value: ctypes.c_uint8): | CODE |
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_ggml.py | 1103 | def ggml_backend_buffer_is_host(buffer: ggml_backend_buffer_t) -> ctypes.c_bool: | CODE |
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_ggml.py | 1112 | def ggml_backend_buffer_set_usage(buffer: ggml_backend_buffer_t, usage: ctypes.c_int32): | CODE |
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_ggml.py | 1121 | def ggml_backend_buffer_get_usage(buffer: ggml_backend_buffer_t) -> ctypes.c_int32: | CODE |
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_ggml.py | 1130 | def ggml_backend_buffer_get_type(buffer: ggml_backend_buffer_t) -> ggml_backend_buffer_t: | CODE |
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_ggml.py | 1139 | def ggml_backend_buffer_reset(buffer: ggml_backend_buffer_t): | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 933 | def ggml_backend_buft_alloc_buffer( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 945 | def ggml_backend_buft_get_alignment(buft: ggml_backend_buffer_type_t) -> ctypes.c_size_t: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 954 | def ggml_backend_buft_get_max_size(buft: ggml_backend_buffer_type_t) -> ctypes.c_size_t: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 966 | def ggml_backend_buft_get_alloc_size( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 978 | def ggml_backend_buft_is_host(buft: ggml_backend_buffer_type_t) -> ctypes.c_bool: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 987 | def ggml_backend_buft_get_device(buft: ggml_backend_buffer_type_t) -> ggml_backend_dev_t: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1028 | def ggml_backend_buffer_get_base(buffer: ggml_backend_buffer_t): | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1037 | def ggml_backend_buffer_get_size(buffer: ggml_backend_buffer_t) -> ctypes.c_size_t: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1049 | def ggml_backend_buffer_init_tensor( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1061 | def ggml_backend_buffer_get_alignment(buffer: ggml_backend_buffer_t) -> ctypes.c_size_t: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1070 | def ggml_backend_buffer_get_max_size(buffer: ggml_backend_buffer_t) -> ctypes.c_size_t: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1082 | def ggml_backend_buffer_get_alloc_size( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1188 | def ggml_backend_device_register(device: ctypes.c_void_p): | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1259 | def ggml_backend_init_by_name(name: ctypes.c_char_p, params: ctypes.c_char_p) -> ggml_backend_t: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1319 | def ggml_backend_load_all_from_path(dir_path: ctypes.c_char_p): | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1334 | def ggml_backend_cpu_buffer_from_ptr( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1350 | def ggml_backend_cpu_buffer_type() -> ggml_backend_buffer_type_t: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 147 | def register_chat_completion_handler( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 165 | def get_chat_completion_handler_by_name( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 177 | def get_chat_completion_handler(name: str) -> LlamaChatCompletionHandler: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 183 | def register_chat_completion_handler(name: str): | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 299 | def _convert_text_completion_logprobs_to_chat( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 324 | def _convert_text_completion_to_chat( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 348 | def _convert_text_completion_chunks_to_chat( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 391 | def _convert_completion_to_chat( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 408 | def _convert_completion_to_chat_function( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 457 | def _stream_response_to_function_stream( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 585 | def chat_formatter_to_chat_completion_handler( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 778 | def hf_autotokenizer_to_chat_formatter( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 803 | def hf_autotokenizer_to_chat_completion_handler( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 810 | def hf_tokenizer_config_to_chat_formatter( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 858 | def hf_tokenizer_config_to_chat_completion_handler( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 868 | def guess_chat_format_from_gguf_metadata(metadata: Dict[str, str]) -> Optional[str]: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 974 | def _format_add_colon_space_single( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1033 | def _grammar_for_response_format( | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1568 | def generate_shared_definitions(shared_defs, indent_level: int) -> str: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1585 | def generate_schema_from_functions(functions, namespace="functions") -> str: | CODE |
| 283 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | py310/Lib/site-packages/llama_cpp/llama_cache.py | 9 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cache.py | 20 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_tokenizer.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 10 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 16 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 16 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 42 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/__init__.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/__init__.py | 2 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 23 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 30 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 30 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 30 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 30 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 26 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 27 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 33 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 35 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 37 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 37 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 37 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 37 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/mtmd_cpp.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/mtmd_cpp.py | 5 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/mtmd_cpp.py | 21 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_ctypes_extensions.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_embedding.py | 7 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_embedding.py | 7 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_embedding.py | 7 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/types.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/model.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/cli.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/settings.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/app.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/errors.py | 1 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/errors.py | 6 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/errors.py | 6 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/__main__.py | 25 | CODE | |
| LOW | finetune/json2binidx_tool/tools/rwkv_tokenizer.py | 6 | CODE | |
| LOW | finetune/json2binidx_tool/tools/rwkv_tokenizer.py | 6 | CODE | |
| LOW | finetune/json2binidx_tool/tools/rwkv_tokenizer.py | 6 | CODE | |
| LOW | finetune/json2binidx_tool/tools/rwkv_tokenizer.py | 6 | CODE | |
| LOW | finetune/json2binidx_tool/tools/tokenizer.py | 24 | CODE | |
| LOW | finetune/lora/merge_lora.py | 2 | CODE | |
| LOW | finetune/lora/v6/train.py | 13 | CODE | |
| LOW | finetune/lora/v6/train.py | 163 | CODE | |
| LOW | finetune/lora/v6/train.py | 163 | CODE | |
| LOW | finetune/lora/v6/train.py | 163 | CODE | |
| LOW | finetune/lora/v6/train.py | 347 | CODE | |
| LOW | finetune/lora/v6/merge/merge_state.py | 1 | CODE | |
| LOW | finetune/lora/v6/merge/merge_state.py | 2 | CODE | |
| LOW | finetune/lora/v6/merge/merge_state.py | 3 | CODE | |
| LOW | finetune/lora/v6/merge/merge_state.py | 5 | CODE | |
| LOW | finetune/lora/v6/merge/merge_state.py | 7 | CODE | |
| LOW | finetune/lora/v6/merge/merge.py | 2 | CODE | |
| LOW | finetune/lora/v6/merge/merge.py | 3 | CODE | |
| 248 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 2959 | except Exception: | CODE |
| HIGH | py310/Lib/site-packages/llama_cpp/_internals.py | 1148 | except Exception: | CODE |
| HIGH | py310/Lib/site-packages/llama_cpp/_internals.py | 1326 | except Exception: | CODE |
| HIGH | py310/Lib/site-packages/llama_cpp/_internals.py | 1679 | except Exception: | CODE |
| HIGH | py310/Lib/site-packages/llama_cpp/_internals.py | 85 | except Exception: | CODE |
| HIGH | py310/Lib/site-packages/llama_cpp/_internals.py | 510 | except Exception: | CODE |
| HIGH | py310/Lib/site-packages/llama_cpp/_internals.py | 935 | except Exception: | CODE |
| HIGH | py310/Lib/site-packages/llama_cpp/_internals.py | 1316 | except Exception: | CODE |
| HIGH | py310/Lib/site-packages/llama_cpp/_internals.py | 1659 | except Exception: | CODE |
| HIGH | py310/Lib/site-packages/llama_cpp/_internals.py | 1799 | except Exception: | CODE |
| HIGH | py310/Lib/site-packages/llama_cpp/llama.py | 2175 | except UnicodeError: | CODE |
| HIGH | finetune/json2binidx_tool/tools/rwkv_tokenizer.py | 120 | except: | CODE |
| HIGH | finetune/json2binidx_tool/tools/rwkv_tokenizer.py | 229 | except: | CODE |
| HIGH | finetune/json2binidx_tool/tools/rwkv_tokenizer.py | 90 | except: | CODE |
| HIGH | finetune/lora/v6/src/trainer.py | 144 | except: | CODE |
| HIGH | finetune/lora/v6/src/trainer.py | 117 | except: | CODE |
| HIGH | finetune/lora/v5/src/trainer.py | 145 | except: | CODE |
| HIGH | finetune/lora/v5/src/trainer.py | 118 | except: | CODE |
| HIGH | finetune/lora/v4/src/trainer.py | 100 | except: | CODE |
| HIGH | finetune/lora/v4/src/trainer.py | 73 | except: | CODE |
| HIGH | backend-python/main.py | 129 | except NameError: | CODE |
| HIGH | backend-python/utils/rwkv.py | 275 | except HTTPException: | CODE |
| HIGH | backend-python/utils/rwkv.py | 551 | except HTTPException: | CODE |
| HIGH | backend-python/utils/rwkv.py | 310 | except HTTPException: | CODE |
| HIGH | backend-python/utils/rwkv.py | 337 | except HTTPException: | CODE |
| HIGH | backend-python/utils/rwkv.py | 366 | except HTTPException: | CODE |
| HIGH | backend-python/utils/rwkv.py | 422 | except HTTPException: | CODE |
| HIGH | backend-python/utils/rwkv.py | 385 | except HTTPException: | CODE |
| HIGH | backend-python/utils/rwkv.py | 403 | except HTTPException: | CODE |
| HIGH | backend-python/utils/llama.py | 139 | except: | CODE |
| HIGH | backend-python/utils/torch.py | 29 | except: | CODE |
| HIGH | backend-python/rwkv_pip/rwkv_tokenizer.py | 103 | except: | CODE |
| HIGH | backend-python/rwkv_pip/model.py | 1346 | except: | CODE |
| HIGH | backend-python/rwkv_pip/cpp/rwkv_cpp_model.py | 8 | except ModuleNotFoundError: | CODE |
| HIGH | backend-python/albatross_engine/worker.py | 534 | except queue.Empty: | CODE |
| HIGH | backend-python/albatross_engine/adapter.py | 459 | except Exception: | CODE |
| HIGH | backend-python/albatross_engine/adapter.py | 333 | except asyncio.QueueFull: | CODE |
| HIGH | backend-python/albatross_engine/adapter.py | 449 | except Exception: | CODE |
| HIGH | backend-python/albatross_engine/adapter.py | 266 | except Exception: | CODE |
| HIGH | backend-python/albatross_engine/adapter.py | 390 | except Exception: | CODE |
| HIGH | backend-python/albatross_engine/core.py | 375 | except Exception: | CODE |
| HIGH | backend-python/albatross_engine/core.py | 70 | except asyncio.QueueFull: | CODE |
| HIGH | backend-python/albatross/utils.py | 156 | except: | CODE |
| HIGH | backend-python/routes/config.py | 70 | except HTTPException: | CODE |
| HIGH | backend-python/routes/state_cache.py | 232 | except: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | parse_api_log.py | 5 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 585 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1495 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1884 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 5737 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 588 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1535 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1619 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1945 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 2228 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 2972 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 3074 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 3266 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 3635 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1669 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 1398 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 1969 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 85 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 873 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 1107 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 1244 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 1794 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_ctypes_extensions.py | 23 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_grammar.py | 296 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_grammar.py | 319 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_grammar.py | 603 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_grammar.py | 663 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_grammar.py | 834 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_grammar.py | 609 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_grammar.py | 687 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_embedding.py | 85 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_embedding.py | 119 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_embedding.py | 179 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/model.py | 74 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/errors.py | 162 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/errors.py | 170 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/server/__main__.py | 43 | CODE | |
| LOW | finetune/json2binidx_tool/tools/rwkv_tokenizer.py | 76 | CODE | |
| LOW | finetune/json2binidx_tool/tools/indexed_dataset.py | 35 | CODE | |
| LOW | finetune/lora/v6/fla/layers/delta_net.py | 140 | CODE | |
| LOW | finetune/lora/v6/fla/layers/linear_attn.py | 15 | CODE | |
| LOW | finetune/lora/v6/fla/layers/multiscale_retention.py | 155 | CODE | |
| LOW | finetune/lora/v6/fla/models/abc/modeling_abc.py | 128 | CODE | |
| LOW | …une/lora/v6/fla/models/delta_net/modeling_delta_net.py | 128 | CODE | |
| LOW | finetune/lora/v6/fla/models/hgrn/modeling_hgrn.py | 123 | CODE | |
| LOW | …lora/v6/fla/models/transformer/modeling_transformer.py | 257 | CODE | |
| LOW | finetune/lora/v6/fla/models/mamba/modeling_mamba.py | 330 | CODE | |
| LOW | finetune/lora/v6/fla/models/gla/modeling_gla.py | 128 | CODE | |
| LOW | …lora/v6/fla/models/linear_attn/modeling_linear_attn.py | 128 | CODE | |
| LOW | finetune/lora/v6/fla/models/retnet/modeling_retnet.py | 126 | CODE | |
| LOW | finetune/lora/v6/fla/models/hgrn2/modeling_hgrn2.py | 123 | CODE | |
| LOW | finetune/lora/v6/fla/models/rwkv6/modeling_rwkv6.py | 166 | CODE | |
| LOW | finetune/lora/v6/fla/modules/feature_map.py | 219 | CODE | |
| LOW | finetune/lora/v6/src/model.py | 86 | CODE | |
| LOW | finetune/lora/v6/src/model.py | 1271 | CODE | |
| LOW | finetune/lora/v6/src/model.py | 1479 | CODE | |
| LOW | finetune/lora/v6/src/model.py | 1868 | CODE | |
| LOW | finetune/lora/v6/src/model.py | 1632 | CODE | |
| LOW | finetune/lora/v6/src/model.py | 1763 | CODE | |
| LOW | finetune/lora/v6/src/dataset.py | 15 | CODE | |
| 54 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 726 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1026 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1790 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 2173 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 2959 | except Exception: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 3251 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 3531 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 5938 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 6087 | except Exception as e: | CODE |
| MEDIUM | py310/Lib/site-packages/llama_cpp/_internals.py | 1323 | def __del__(self): | CODE |
| MEDIUM | py310/Lib/site-packages/llama_cpp/_internals.py | 1676 | def __del__(self): | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 85 | except Exception: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 510 | except Exception: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 935 | except Exception: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 1148 | except Exception: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 1316 | except Exception: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 1326 | except Exception: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 1659 | except Exception: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 1679 | except Exception: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 1799 | except Exception: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 1851 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 604 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 653 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 930 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 1046 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ctypes_extensions.py | 107 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/_ctypes_extensions.py | 118 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_grammar.py | 43 | except Exception as err: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_grammar.py | 77 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/llama_embedding.py | 437 | except Exception as e: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/server/errors.py | 180 | except Exception as exc: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/server/errors.py | 198 | except Exception: | CODE |
| LOW | py310/Lib/site-packages/llama_cpp/server/__main__.py | 80 | except Exception as e: | CODE |
| LOW | finetune/json2binidx_tool/tools/preprocess_data.py | 248 | except Exception as e: | CODE |
| LOW | finetune/lora/merge_lora.py | 66 | except Exception as e: | CODE |
| LOW | finetune/lora/v6/src/trainer.py | 287 | except Exception as e: | CODE |
| LOW | finetune/lora/v5/src/trainer.py | 254 | except Exception as e: | CODE |
| LOW | finetune/lora/v4/src/trainer.py | 174 | except Exception as e: | CODE |
| LOW | backend-python/convert_safetensors.py | 119 | except Exception as e: | CODE |
| LOW | backend-python/convert_pytorch_to_ggml.py | 245 | except Exception as e: | CODE |
| LOW | backend-python/convert_model.py | 233 | except Exception as e: | CODE |
| LOW | backend-python/bench/albatross_api_benchmark.py | 141 | except Exception as error: | CODE |
| LOW | backend-python/bench/albatross_http_client.py | 30 | except Exception as exc: | CODE |
| LOW | backend-python/bench/albatross_real_http_benchmark.py | 53 | except Exception as exc: | CODE |
| LOW | backend-python/tests/manual_albatross_smoke.py | 111 | except Exception: | CODE |
| LOW | backend-python/utils/rwkv.py | 813 | except Exception as e: | STRING |
| LOW | backend-python/utils/log.py | 40 | except Exception as e: | CODE |
| LOW | backend-python/utils/log.py | 49 | except Exception as e: | CODE |
| LOW | backend-python/rwkv_pip/utils.py | 84 | except Exception as e: | CODE |
| MEDIUM | backend-python/rwkv_pip/utils.py | 85 | print(f"Error loading {WORD_NAME}: {e}") | CODE |
| LOW | backend-python/albatross_engine/worker.py | 209 | except Exception as e: | CODE |
| LOW | backend-python/albatross_engine/worker.py | 256 | except Exception as e: | CODE |
| MEDIUM⚡ | backend-python/albatross_engine/adapter.py | 444 | print(f"Error shutting down Albatross engine: {e}") | CODE |
| MEDIUM | backend-python/albatross_engine/adapter.py | 110 | def run_event_loop(): | CODE |
| MEDIUM | backend-python/albatross_engine/adapter.py | 234 | def async_completion(): | CODE |
| MEDIUM | backend-python/albatross_engine/adapter.py | 330 | def put_result(event): | CODE |
| MEDIUM | backend-python/albatross_engine/adapter.py | 456 | def __del__(self): | CODE |
| LOW⚡ | backend-python/albatross_engine/adapter.py | 443 | except Exception as e: | CODE |
| LOW⚡ | backend-python/albatross_engine/adapter.py | 449 | except Exception: | CODE |
| LOW⚡ | backend-python/albatross_engine/adapter.py | 459 | except Exception: | CODE |
| 12 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | frontend/wailsjs/runtime/runtime.d.ts | 101 | // *Windows only* | COMMENT |
| LOW | frontend/src/App.tsx | 1 | // reference: https://github.com/oliverschwendener/electron-fluent-ui | COMMENT |
| LOW | frontend/src/components/RunButton.tsx | 181 | // await startWebGPUTaskChain(modelName, modelConfig) | COMMENT |
| LOW | frontend/src/_locales/resources.ts | 1 | import ja from './ja/main.json' | COMMENT |
| LOW | frontend/src/_locales/resources.ts | 21 | // translation: it, | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 81 | # // NOTE: always add types at the end of the enum to keep backward compatibility | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 101 | # GGML_TYPE_IQ3_XXS = 18, | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 161 | GGML_TYPE_Q1_0 = 41 | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 181 | # GGML_FTYPE_MOSTLY_Q4_1 = 3, // except 1d tensors | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 241 | # GGML_OP_ADD_ID, | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 261 | # GGML_OP_SILU_BACK, | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 281 | # GGML_OP_GET_ROWS_BACK, | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 301 | # GGML_OP_POOL_2D_BACK, | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 321 | # GGML_OP_ADD_REL_POS, | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 461 | # GGML_UNARY_OP_RELU, | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 561 | ("type", ctypes.c_int), | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 621 | COMMENT | |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 661 | COMMENT | |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 821 | COMMENT | |
| LOW | py310/Lib/site-packages/llama_cpp/_ggml.py | 1141 | Reset ggml_backend_buffer | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 3221 | # The C++ parser only sees identical placeholders (e.g., "<__media__>"). | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 141 | # NOTE: Deprecated and will be removed in the future. (already gone in llama.cpp) | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 161 | # LLAMA_VOCAB_PRE_TYPE_CHATGLM3 = 16, | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 181 | # LLAMA_VOCAB_PRE_TYPE_HUNYUAN = 36, | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 281 | LLAMA_TOKEN_TYPE_USER_DEFINED = 4 | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 321 | # LLAMA_FTYPE_MOSTLY_Q8_0 = 7, // except 1d tensors | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 341 | # LLAMA_FTYPE_MOSTLY_IQ3_M = 27, // except 1d tensors | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 401 | # LLAMA_ROPE_SCALING_TYPE_LINEAR = 1, | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 461 | COMMENT | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 541 | # // Input data for llama_encode/llama_decode | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 701 | COMMENT | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 721 | # // Called with a progress value between 0.0 and 1.0. Pass NULL to disable. | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 821 | COMMENT | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 841 | # float yarn_ext_factor; // YaRN extrapolation mix factor, negative = from model | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 861 | # bool offload_kqv; // offload the KQV ops (including the KV cache) to GPU | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 1021 | COMMENT | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 1161 | COMMENT | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 1181 | # ggml_tensor * apply_to(ggml_context * ctx, ggml_tensor * cur, int il) const; | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 2141 | # // n_embd should be the size of a single layer's control, and data should point | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 2881 | COMMENT | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 2941 | COMMENT | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 3701 | # // The API is thread-safe. | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 3761 | COMMENT | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 3801 | vocab: The vocabulary to use for tokenization. | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 3861 | # // | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 3941 | Returns: | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 3961 | # // | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 4001 | ("logits", ctypes.c_void_p), | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 4021 | # // note: call once per sampler | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 4581 | # /// | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 4641 | # // "hell": 0.2 | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 4781 | ... | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/mtmd_cpp.py | 61 | # * WARNING: This API is experimental and subject to many BREAKING CHANGES. | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/mtmd_cpp.py | 81 | # struct mtmd_context; | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/mtmd_cpp.py | 101 | # }; | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/mtmd_cpp.py | 121 | # } | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/mtmd_cpp.py | 141 | # struct mtmd_input_chunk { | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/mtmd_cpp.py | 181 | # enum clip_flash_attn_type flash_attn_type; | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/mtmd_cpp.py | 201 | # enum llama_flash_attn_type flash_attn_type; | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/mtmd_cpp.py | 621 | # // 1. "here is an image: <start_of_image>" | COMMENT |
| 37 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1495 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 1884 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 5737 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 85 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 588 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 3266 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 1276 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 85 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 1107 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 1244 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 1794 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 2446 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 2600 | CODE | |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 2749 | CODE | |
| LOW | finetune/lora/v6/fla/layers/hgrn.py | 22 | CODE | |
| LOW | finetune/lora/v6/fla/layers/hgrn2.py | 22 | CODE | |
| LOW | finetune/lora/v6/fla/layers/delta_net.py | 49 | CODE | |
| LOW | finetune/lora/v6/fla/layers/rwkv6.py | 21 | CODE | |
| LOW | finetune/lora/v6/fla/layers/rebased.py | 21 | CODE | |
| LOW | finetune/lora/v6/fla/layers/simple_gla.py | 49 | CODE | |
| LOW | finetune/lora/v6/fla/layers/gla.py | 68 | CODE | |
| LOW | finetune/lora/v6/fla/layers/based.py | 18 | CODE | |
| LOW | finetune/lora/v6/fla/layers/gated_abc.py | 22 | CODE | |
| LOW | finetune/lora/v6/fla/layers/linear_attn.py | 15 | CODE | |
| LOW | finetune/lora/v6/fla/layers/multiscale_retention.py | 62 | CODE | |
| LOW | finetune/lora/v6/fla/layers/abc.py | 22 | CODE | |
| LOW | finetune/lora/v6/fla/models/abc/modeling_abc.py | 183 | CODE | |
| LOW | finetune/lora/v6/fla/models/abc/modeling_abc.py | 341 | CODE | |
| LOW | finetune/lora/v6/fla/models/abc/configuration_abc.py | 13 | CODE | |
| LOW | …une/lora/v6/fla/models/delta_net/modeling_delta_net.py | 183 | CODE | |
| LOW | …une/lora/v6/fla/models/delta_net/modeling_delta_net.py | 352 | CODE | |
| LOW | …ora/v6/fla/models/delta_net/configuration_delta_net.py | 13 | CODE | |
| LOW | finetune/lora/v6/fla/models/hgrn/modeling_hgrn.py | 180 | CODE | |
| LOW | finetune/lora/v6/fla/models/hgrn/modeling_hgrn.py | 354 | CODE | |
| LOW | finetune/lora/v6/fla/models/hgrn/configuration_hgrn.py | 13 | CODE | |
| LOW | …lora/v6/fla/models/transformer/modeling_transformer.py | 312 | CODE | |
| LOW | …lora/v6/fla/models/transformer/modeling_transformer.py | 469 | CODE | |
| LOW | …v6/fla/models/transformer/configuration_transformer.py | 13 | CODE | |
| LOW | …netune/lora/v6/fla/models/mamba/configuration_mamba.py | 99 | CODE | |
| LOW | finetune/lora/v6/fla/models/gla/modeling_gla.py | 183 | CODE | |
| LOW | finetune/lora/v6/fla/models/gla/modeling_gla.py | 350 | CODE | |
| LOW | finetune/lora/v6/fla/models/gla/configuration_gla.py | 13 | CODE | |
| LOW | …lora/v6/fla/models/linear_attn/modeling_linear_attn.py | 185 | CODE | |
| LOW | …lora/v6/fla/models/linear_attn/modeling_linear_attn.py | 368 | CODE | |
| LOW | …v6/fla/models/linear_attn/configuration_linear_attn.py | 13 | CODE | |
| LOW | finetune/lora/v6/fla/models/retnet/modeling_retnet.py | 183 | CODE | |
| LOW | finetune/lora/v6/fla/models/retnet/modeling_retnet.py | 356 | CODE | |
| LOW | …tune/lora/v6/fla/models/retnet/configuration_retnet.py | 15 | CODE | |
| LOW | finetune/lora/v6/fla/models/hgrn2/modeling_hgrn2.py | 180 | CODE | |
| LOW | finetune/lora/v6/fla/models/hgrn2/modeling_hgrn2.py | 354 | CODE | |
| LOW | …netune/lora/v6/fla/models/hgrn2/configuration_hgrn2.py | 13 | CODE | |
| LOW | finetune/lora/v6/fla/models/rwkv6/modeling_rwkv6.py | 223 | CODE | |
| LOW | finetune/lora/v6/fla/models/rwkv6/modeling_rwkv6.py | 390 | CODE | |
| LOW | …netune/lora/v6/fla/models/rwkv6/configuration_rwkv6.py | 13 | CODE | |
| LOW | finetune/lora/v6/fla/modules/fused_cross_entropy.py | 324 | CODE | |
| LOW | backend-python/rwkv_pip/utils.py | 13 | CODE | |
| LOW | backend-python/albatross_engine/interface.py | 30 | CODE | |
| LOW | backend-python/albatross_engine/core.py | 227 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | finetune/json2binidx_tool/tools/indexed_dataset.py | 0 | retrieves a single item from the dataset with the option to only return a portion of the item. get(idx) is the same as [ | STRING |
| HIGH | finetune/lora/v6/src/binidx.py | 0 | retrieves a single item from the dataset with the option to only return a portion of the item. get(idx) is the same as [ | STRING |
| HIGH | finetune/lora/v5/src/binidx.py | 0 | retrieves a single item from the dataset with the option to only return a portion of the item. get(idx) is the same as [ | STRING |
| HIGH | finetune/lora/v4/src/binidx.py | 0 | retrieves a single item from the dataset with the option to only return a portion of the item. get(idx) is the same as [ | STRING |
| HIGH | finetune/lora/v6/src/model.py | 0 | ############################################################################ # # init model weight (slow for large model | STRING |
| HIGH | finetune/lora/v5/src/model.py | 0 | ############################################################################ # # init model weight (slow for large model | STRING |
| HIGH | finetune/lora/v4/src/model.py | 0 | ############################################################################ # # init model weight (slow for large model | STRING |
| HIGH | finetune/lora/v6/src/binidx.py | 0 | if distributed is initialized print only on rank 0. | STRING |
| HIGH | finetune/lora/v5/src/binidx.py | 0 | if distributed is initialized print only on rank 0. | STRING |
| HIGH | finetune/lora/v4/src/binidx.py | 0 | if distributed is initialized print only on rank 0. | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | py310/Lib/site-packages/llama_cpp/llama_speculative.py | 43 | def _update_cache(self, input_ids: npt.NDArray[np.intc]) -> None: | CODE |
| LOW | finetune/lora/v6/fla/__init__.py | 16 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/layers/__init__.py | 14 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/models/__init__.py | 18 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/models/abc/__init__.py | 13 | __all__ = ['ABCConfig', 'ABCForCausalLM', 'ABCModel'] | CODE |
| LOW | finetune/lora/v6/fla/models/delta_net/__init__.py | 14 | __all__ = ['DeltaNetConfig', 'DeltaNetForCausalLM', 'DeltaNetModel'] | CODE |
| LOW | finetune/lora/v6/fla/models/hgrn/__init__.py | 13 | __all__ = ['HGRNConfig', 'HGRNForCausalLM', 'HGRNModel'] | CODE |
| LOW | finetune/lora/v6/fla/models/transformer/__init__.py | 14 | __all__ = ['TransformerConfig', 'TransformerForCausalLM', 'TransformerModel'] | CODE |
| LOW | finetune/lora/v6/fla/models/mamba/__init__.py | 14 | __all__ = ['MambaConfig', 'MambaForCausalLM', 'MambaModel', 'MambaBlock'] | CODE |
| LOW | finetune/lora/v6/fla/models/gla/__init__.py | 13 | __all__ = ['GLAConfig', 'GLAForCausalLM', 'GLAModel'] | CODE |
| LOW | finetune/lora/v6/fla/models/linear_attn/__init__.py | 14 | __all__ = ['LinearAttentionConfig', 'LinearAttentionForCausalLM', 'LinearAttentionModel'] | CODE |
| LOW | finetune/lora/v6/fla/models/retnet/__init__.py | 13 | __all__ = ['RetNetConfig', 'RetNetForCausalLM', 'RetNetModel'] | CODE |
| LOW | finetune/lora/v6/fla/models/hgrn2/__init__.py | 13 | __all__ = ['HGRN2Config', 'HGRN2ForCausalLM', 'HGRN2Model'] | CODE |
| LOW | finetune/lora/v6/fla/models/rwkv6/__init__.py | 13 | __all__ = ['RWKV6Config', 'RWKV6ForCausalLM', 'RWKV6Model'] | CODE |
| LOW | finetune/lora/v6/fla/ops/__init__.py | 8 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/ops/abc/__init__.py | 7 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/ops/delta_rule/__init__.py | 7 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/ops/retention/__init__.py | 8 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/ops/hgrn/__init__.py | 6 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/ops/rwkv4/__init__.py | 5 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/ops/simple_gla/__init__.py | 5 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/ops/gla/__init__.py | 7 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/ops/linear_attn/__init__.py | 7 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/ops/rebased/__init__.py | 5 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/ops/based/__init__.py | 6 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/ops/rwkv6/__init__.py | 6 | __all__ = [ | CODE |
| LOW | finetune/lora/v6/fla/modules/__init__.py | 14 | __all__ = [ | CODE |
| LOW | backend-python/scripts/build_albatross_kernel.py | 208 | def update_manifest(manifest_path: Path, entry: dict) -> None: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | py310/Lib/site-packages/llama_cpp/llama.py | 156 | Load a llama.cpp model from `model_path`. Examples: Basic usage >>> import llama_cpp | STRING |
| HIGH | py310/Lib/site-packages/llama_cpp/llama.py | 809 | Tokenize a string. Args: text: The utf-8 encoded string to tokenize. add_bos: Whether t | STRING |
| HIGH | py310/Lib/site-packages/llama_cpp/llama.py | 1284 | Create a generator of tokens from a prompt. Examples: >>> llama = Llama("models/ggml-7b.bin") | STRING |
| HIGH | py310/Lib/site-packages/llama_cpp/llama.py | 2491 | Generate text from a prompt. Args: prompt: The prompt to generate text from. suffix: A suffix to ap | STRING |
| HIGH | py310/Lib/site-packages/llama_cpp/llama.py | 2645 | Generate text from a prompt. Args: prompt: The prompt to generate text from. suffix: A | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | py310/Lib/site-packages/llama_cpp/llama_types.py | 519 | # NOTE: The following type names are not part of the OpenAI OpenAPI specification | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 3868 | # /// NOTE: This function does not use a jinja parser. It only support a pre-defined list of template. See more: https:/ | COMMENT |
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_internals.py | 1112 | # Step 1: Transfer new logits from the model output to our working buffer. | COMMENT |
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_internals.py | 1115 | # Step 2: Critical Reset. | COMMENT |
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_internals.py | 1120 | # Step 3: Metadata update. | COMMENT |
| LOW⚡ | backend-python/tests/function_call_stream.py | 110 | # Step 3: call the function | COMMENT |
| LOW⚡ | backend-python/tests/function_call_stream.py | 115 | # Step 4: send the info for each function call and function response to the model | COMMENT |
| LOW | backend-python/tests/function_call.py | 29 | # Step 1: send the conversation and available functions to the model | COMMENT |
| LOW⚡ | backend-python/tests/function_call.py | 64 | # Step 2: check if the model wanted to call a function | COMMENT |
| LOW⚡ | backend-python/tests/function_call.py | 66 | # Step 3: call the function | COMMENT |
| LOW⚡ | backend-python/tests/function_call.py | 72 | # Step 4: send the info for each function call and function response to the model | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_internals.py | 1112 | # Step 1: Transfer new logits from the model output to our working buffer. | COMMENT |
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_internals.py | 1115 | # Step 2: Critical Reset. | COMMENT |
| LOW⚡ | py310/Lib/site-packages/llama_cpp/_internals.py | 1120 | # Step 3: Metadata update. | COMMENT |
| LOW⚡ | backend-python/tests/function_call_stream.py | 110 | # Step 3: call the function | COMMENT |
| LOW⚡ | backend-python/tests/function_call_stream.py | 115 | # Step 4: send the info for each function call and function response to the model | COMMENT |
| LOW | backend-python/tests/function_call.py | 29 | # Step 1: send the conversation and available functions to the model | COMMENT |
| LOW⚡ | backend-python/tests/function_call.py | 64 | # Step 2: check if the model wanted to call a function | COMMENT |
| LOW⚡ | backend-python/tests/function_call.py | 66 | # Step 3: call the function | COMMENT |
| LOW⚡ | backend-python/tests/function_call.py | 72 | # Step 4: send the info for each function call and function response to the model | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | py310/Lib/site-packages/llama_cpp/_internals.py | 1076 | # Define the structure of llama_token_data to match the C++ memory layout. | COMMENT |
| MEDIUM | py310/Lib/site-packages/llama_cpp/llama.py | 693 | # Create a thread-safe interrupt event | COMMENT |
| MEDIUM | finetune/json2binidx_tool/tools/preprocess_data.py | 2 | # This file is based on code by the authors denoted below and has been modified from its original version. | COMMENT |
| MEDIUM | finetune/json2binidx_tool/tools/tokenizer.py | 2 | # This file is based on code by the authors denoted below and has been modified from its original version. | COMMENT |
| MEDIUM | finetune/json2binidx_tool/tools/indexed_dataset.py | 2 | # This file is based on code by the authors denoted below and has been modified from its original version. | COMMENT |
| MEDIUM | assets/sound-font/sound_fetch.py | 86 | # Create the file name | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | py310/Lib/site-packages/llama_cpp/llama_cache.py | 241 | # Check if the empty prefix (root) is cached | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_speculative.py | 54 | # Check if it's a perfect incremental append (verify if the previous token matches) | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 2936 | # Check if vision is supported | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama_chat_format.py | 2945 | # Check if audio is supported | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_internals.py | 448 | # Check if the adapter exists and hasn't been freed yet | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/llama.py | 2095 | # Check if stop sequence is in the token | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/_utils.py | 48 | # Check if sys.stdout and sys.stderr have fileno method | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/server/app.py | 110 | # Check if yaml file | COMMENT |
| LOW | py310/Lib/site-packages/llama_cpp/server/__main__.py | 63 | # Check if yaml file | COMMENT |
| LOW | assets/sound-font/sound_fetch.py | 89 | # Check if the file already exists | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | exportModelsJson.js | 1 | // Execute this script on the Hugging Face files list page to export JSON data. Don't forget to click "Load more files". | COMMENT |
| MEDIUM | manifest.json | 4 | "en": "RWKV is an open-source, commercially usable large language model with high flexibility and great potential fo | CODE |
| LOW | frontend/src/_locales/zh-hans/main.json | 368 | "Don't forget to correctly fill in your Ollama API Chat Model Name.": "不要忘记正确填写你的Ollama API 聊天模型名", | CODE |
| LOW | frontend/src/_locales/zh-hans/main.json | 369 | "Don't forget to correctly fill in your llmman API Chat Model Name.": "不要忘记正确填写你的llmman API 聊天模型名", | CODE |
| LOW | frontend/src/_locales/ja/main.json | 368 | "Don't forget to correctly fill in your Ollama API Chat Model Name.": "Ollama APIチャットモデル名を正しく記入するのを忘れないでください。", | CODE |
| LOW | frontend/src/_locales/ja/main.json | 369 | "Don't forget to correctly fill in your llmman API Chat Model Name.": "llmman APIチャットモデル名を正しく記入するのを忘れないでください。", | CODE |
| LOW | frontend/src/pages/Settings.tsx | 259 | "Don't forget to correctly fill in your Ollama API Chat Model Name." | CODE |
| LOW | frontend/src/pages/Settings.tsx | 266 | "Don't forget to correctly fill in your llmman API Chat Model Name." | CODE |
| MEDIUM | finetune/lora/v6/fla/ops/abc/naive.py | 73 | This is just for demonstration purposes, with no numerical stabilities guaranteed. | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | py310/Lib/site-packages/llama_cpp/llama.py | 900 | # 2. Sanity check: If the incoming chunk itself is larger than the entire context window, | COMMENT |
| MEDIUM | py310/Lib/site-packages/llama_cpp/llama.py | 1949 | # Truncate max_tokens if requested tokens would exceed the context window | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | frontend/package-lock.json | 7327 | "resolved": "https://registry.npmjs.org/robust-predicates/-/robust-predicates-3.0.2.tgz", | CODE |
| MEDIUM | py310/Lib/site-packages/llama_cpp/llama_cpp.py | 2862 | # // NOTE: this is a helper function to facilitate transition to the new batch API - avoid using it | COMMENT |
| LOW | finetune/lora/v6/fla/modules/feature_map.py | 158 | # currently we simply use linear layers without any non-linear activations | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | backend-python/routes/completion.py | 1177 | # ----------------------------------- | STRING |
| MEDIUM | backend-python/routes/completion.py | 1179 | # ----------------------------------- | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | assets/soundfont_builder.rb | 18 | # Usage: | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | frontend/i18nally.json | 70 | "placeholder", | CODE |