The Triton Inference Server provides an optimized cloud and edge inferencing solution.
This report summarizes scanner evidence for triton-inference-server/server, a Python project with 11,066 GitHub stars. SynthScan examined 191,102 lines of code across 818 source files, recording 2679 pattern matches distributed across 17 syntactic categories. The legacy adjusted pattern signal is 18.2 (Elevated 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? 2062 finding(s).
Are imports declared and package/API names verified? 117 finding(s).
Are wrappers, guards, and repeated structures necessary? 1380 finding(s).
Which changes need focused human review? 2679 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 2679 distinct pattern matches across 17 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 | build.py | 1 | #!/usr/bin/env python3 | COMMENT |
| LOW | build.py | 41 | import distro | COMMENT |
| LOW | build.py | 61 | # upstream container version, | COMMENT |
| LOW | build.py | 1841 | ] | COMMENT |
| LOW | build.py | 2841 | COMMENT | |
| LOW | CMakeLists.txt | 1 | # Copyright 2020-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | compose.py | 1 | #!/usr/bin/env python3 | COMMENT |
| LOW | .pre-commit-config.yaml | 1 | # Copyright 2023-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | pyproject.toml | 1 | # Copyright 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | pyproject.toml | 21 | # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | COMMENT |
| LOW | README.md | 1 | <!-- | COMMENT |
| LOW | CONTRIBUTING.md | 1 | <!-- | COMMENT |
| LOW | SECURITY.md | 1 | <!-- | COMMENT |
| LOW | tools/add_copyright.py | 1 | # Copyright (c) 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | tools/add_copyright.py | 161 | with open(path, "w") as f: | COMMENT |
| LOW | docker/entrypoint.d/99-check-run-aip-mode.sh | 1 | #!/bin/bash | COMMENT |
| LOW | docker/cpu_only/nvidia_entrypoint.sh | 1 | #!/bin/bash | COMMENT |
| LOW | python/openai/requirements.txt | 1 | # Copyright 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/requirements.txt | 21 | # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | COMMENT |
| LOW | python/openai/requirements-test.txt | 1 | # Copyright 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/requirements-test.txt | 21 | # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | COMMENT |
| LOW | python/openai/README.md | 1 | <!-- | COMMENT |
| LOW | python/openai/openai_frontend/__init__.py | 1 | # Copyright 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/__init__.py | 21 | # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | COMMENT |
| LOW | python/openai/openai_frontend/main.py | 1 | #!/usr/bin/env python3 | COMMENT |
| LOW | …on/openai/openai_frontend/frontend/fastapi_frontend.py | 1 | # Copyright 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/frontend/frontend.py | 1 | # Copyright 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/frontend/__init__.py | 1 | # Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/frontend/__init__.py | 21 | # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | COMMENT |
| LOW | …on/openai/openai_frontend/frontend/fastapi/__init__.py | 1 | # Copyright 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | …on/openai/openai_frontend/frontend/fastapi/__init__.py | 21 | # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | COMMENT |
| LOW | …nai/openai_frontend/frontend/fastapi/routers/models.py | 1 | # Copyright 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | …i/openai_frontend/frontend/fastapi/routers/__init__.py | 1 | # Copyright 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | …i/openai_frontend/frontend/fastapi/routers/__init__.py | 21 | # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | COMMENT |
| LOW | …nai_frontend/frontend/fastapi/routers/observability.py | 1 | # Copyright 2024-2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | …penai_frontend/frontend/fastapi/routers/completions.py | 1 | # Copyright 2024-2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | …penai/openai_frontend/frontend/fastapi/routers/chat.py | 1 | # Copyright 2024-2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | …openai_frontend/frontend/fastapi/routers/embeddings.py | 1 | # Copyright 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | …_frontend/frontend/fastapi/routers/model_management.py | 1 | # Copyright 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | …i_frontend/frontend/fastapi/middleware/request_size.py | 1 | # Copyright 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | …penai_frontend/frontend/fastapi/middleware/__init__.py | 1 | # Copyright 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | …penai_frontend/frontend/fastapi/middleware/__init__.py | 21 | # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | COMMENT |
| LOW | …rontend/frontend/fastapi/middleware/api_restriction.py | 1 | # Copyright 2025-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/utils/utils.py | 1 | # Copyright 2025-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/schemas/__init__.py | 1 | # Copyright 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/schemas/__init__.py | 21 | # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | COMMENT |
| LOW | python/openai/openai_frontend/schemas/openai.py | 1 | # Copyright (c) 2024-2025, NVIDIA CORPORATION. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/engine/__init__.py | 1 | # Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/engine/__init__.py | 21 | # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | COMMENT |
| LOW | python/openai/openai_frontend/engine/engine.py | 1 | # Copyright 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 1 | # Copyright 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 1 | # Copyright 2024-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/engine/utils/__init__.py | 1 | # Copyright 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/engine/utils/__init__.py | 21 | # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | COMMENT |
| LOW | python/openai/openai_frontend/engine/utils/tokenizer.py | 1 | # Copyright (c) 2024-2026, NVIDIA CORPORATION. All rights reserved. | COMMENT |
| LOW | python/openai/openai_frontend/engine/utils/chat.py | 1 | # Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved. | COMMENT |
| LOW | …end/engine/utils/tool_call_parsers/tool_call_parser.py | 1 | # Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved. | COMMENT |
| LOW | …ne/utils/tool_call_parsers/mistral_tool_call_parser.py | 1 | # Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved. | COMMENT |
| LOW | …ai_frontend/engine/utils/tool_call_parsers/__init__.py | 1 | # Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved. | COMMENT |
| LOW | …penai_frontend/engine/utils/tool_call_parsers/utils.py | 1 | # Copyright (c) 2025-2026, NVIDIA CORPORATION. All rights reserved. | COMMENT |
| 801 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | build.py | 194 | def default_build_container_image(): | CODE |
| LOW | build.py | 426 | def cmake_repoagent_extra_args(): | CODE |
| LOW | build.py | 780 | def fastertransformer_cmake_args(): | CODE |
| LOW | build.py | 983 | def create_dockerfile_buildbase_rhel(ddir, dockerfile_name, argmap): | CODE |
| LOW | build.py | 1106 | def create_dockerfile_buildbase(ddir, dockerfile_name, argmap): | STRING |
| LOW | build.py | 1370 | def dockerfile_prepare_container_linux(argmap, backends, enable_gpu, target_machine): | STRING |
| LOW | build.py | 1599 | def add_cpu_libs_to_linux_dockerfile(backends, target_machine): | STRING |
| LOW | build.py | 1661 | def set_python_location_to_manylinux_for_rhel(): | STRING |
| LOW | build.py | 1668 | def restore_embeddable_python_lib_rhel(): | STRING |
| LOW | build.py | 1762 | def create_docker_build_script(script_name, container_install_dir, container_ci_dir): | STRING |
| LOW | compose.py | 174 | def get_container_version_if_not_specified(): | STRING |
| LOW | tools/add_copyright.py | 372 | def test_adding_new_copyrights(content, extension, expected): | CODE |
| LOW | tools/add_copyright.py | 376 | def test_license_has_current_year(): | CODE |
| LOW | python/openai/README.md | 803 | def get_n_day_weather_forecast(city: str, state: str, unit: str, num_days: int): | CODE |
| LOW | …on/openai/openai_frontend/frontend/fastapi_frontend.py | 138 | def _add_api_restriction_middleware(self, app: FastAPI): | CODE |
| LOW | …on/openai/openai_frontend/frontend/fastapi_frontend.py | 146 | def _add_request_size_limit_middleware(self, app: FastAPI): | CODE |
| LOW | …i_frontend/frontend/fastapi/middleware/request_size.py | 138 | def _oversized_request_message(actual_bytes: int, max_bytes: int) -> str: | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 319 | def _get_chat_completion_response_message( | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 494 | def _determine_request_converter(self, backend: str, request_type: RequestKind): | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 639 | def _get_streaming_chat_response_chunk( | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 657 | def _get_first_streaming_chat_response( | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 686 | async def _stream_with_inference_cancellation( | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 845 | def _get_streaming_response_delta( | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 1012 | def _verify_chat_tool_call_settings(self, request: CreateChatCompletionRequest): | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 1049 | async def _streaming_completion_iterator( | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 1117 | def _validate_completion_request( | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 1193 | def _validate_embedding_request( | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 1219 | def _should_stream_with_auto_tool_parsing( | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 1229 | def _should_check_for_unstreamed_tool_arg_tokens( | CODE |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 70 | def _create_vllm_generate_request( | CODE |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 179 | def _create_trtllm_generate_request( | CODE |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 252 | def _create_vllm_embedding_request( | CODE |
| LOW⚡ | python/openai/openai_frontend/engine/utils/triton.py | 272 | def _create_trtllm_embedding_request( | CODE |
| LOW⚡ | python/openai/openai_frontend/engine/utils/triton.py | 281 | def _construct_string_from_pointer(pointer: int, size: int) -> str: | CODE |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 429 | def _get_logprobs_from_response( | CODE |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 468 | def _get_openai_chat_format_logprobs_from_vllm_response( | CODE |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 526 | def _get_openai_completion_format_logprobs_from_vllm_response( | CODE |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 584 | def _validate_triton_responses_non_streaming( | CODE |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 597 | def _get_guided_json_from_tool( | CODE |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 620 | def _validate_lora_path_trtllm(repo_path: str, lora_path: str, lora_name: str): | CODE |
| LOW | python/openai/openai_frontend/engine/utils/chat.py | 61 | def _frontend_schema_to_openai_schema_completion_tool_call( | CODE |
| LOW | python/openai/openai_frontend/engine/utils/chat.py | 74 | def _parse_chat_message_content_parts( | CODE |
| LOW | python/openai/openai_frontend/engine/utils/chat.py | 91 | def _parse_chat_message_content( | CODE |
| LOW | …end/engine/utils/tool_call_parsers/tool_call_parser.py | 61 | def parse_tool_calls_streaming( | CODE |
| LOW | …ne/utils/tool_call_parsers/mistral_tool_call_parser.py | 58 | def generate_mistral_random_id(): | CODE |
| LOW | …ne/utils/tool_call_parsers/mistral_tool_call_parser.py | 144 | def parse_tool_calls_streaming( | CODE |
| LOW | …penai_frontend/engine/utils/tool_call_parsers/utils.py | 106 | def extract_intermediate_diff(curr: str, old: str) -> str: | CODE |
| LOW | …gine/utils/tool_call_parsers/llama_tool_call_parser.py | 137 | def parse_tool_calls_streaming( | CODE |
| LOW | python/openai/tests/conftest.py | 70 | def infer_test_model_repository(backend, tool_call_parser): | CODE |
| LOW | python/openai/tests/conftest.py | 167 | def fastapi_client_class_scope( | CODE |
| LOW | python/openai/tests/conftest.py | 187 | def pytest_collection_modifyitems(session, config, items): | CODE |
| LOW | python/openai/tests/test_tool_calling.py | 152 | def validate_tool_calls_present( | CODE |
| LOW | python/openai/tests/test_tool_calling.py | 163 | def validate_weather_tool_arguments(self, parsed_arguments: Dict): | CODE |
| LOW | python/openai/tests/test_tool_calling.py | 172 | def validate_weather_forcast_tool_arguments(self, parsed_arguments: Dict): | CODE |
| LOW | python/openai/tests/test_tool_calling.py | 183 | async def test_tool_call_and_choice( | CODE |
| LOW | python/openai/tests/test_tool_calling.py | 298 | async def test_tool_call_with_reply_response( | CODE |
| LOW | python/openai/tests/test_tool_calling.py | 358 | async def test_tool_call_with_named_tool_choice( | CODE |
| LOW | python/openai/tests/test_tool_calling.py | 461 | async def test_tool_call_with_required_tool_choice( | CODE |
| LOW | python/openai/tests/test_tool_calling.py | 564 | async def test_inconsistent_tool_choice_and_tools( | CODE |
| LOW⚡ | python/openai/tests/test_tool_calling.py | 664 | def test_truncated_when_tool_call_exceeds_limit(self, client): | CODE |
| 799 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | build.py | 129 | except (OSError, ValueError, IndexError): | CODE |
| HIGH | build.py | 252 | except TypeError: | CODE |
| HIGH | qa/L0_http/http_request_many_chunks.py | 84 | except (BrokenPipeError, ConnectionResetError): | CODE |
| HIGH | qa/L0_client_nobatch/client_test.py | 91 | except InferenceServerException as ex: | CODE |
| HIGH | qa/L0_client_nobatch/client_test.py | 143 | except InferenceServerException as ex: | CODE |
| HIGH | qa/common/gen_qa_trt_plugin_models.py | 176 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_trt_plugin_models.py | 244 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_ort_scalar_models.py | 69 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_ort_scalar_models.py | 104 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_ragged_models.py | 133 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_ragged_models.py | 265 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_ragged_models.py | 328 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_ragged_models.py | 406 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_ragged_models.py | 459 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_ragged_models.py | 509 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_ragged_models.py | 545 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_ragged_models.py | 603 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 110 | except AttributeError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 117 | except AttributeError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 124 | except AttributeError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 213 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 323 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 375 | except AttributeError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 468 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 702 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 796 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 892 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 937 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 1035 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_dyna_sequence_models.py | 1166 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 102 | except AttributeError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 109 | except AttributeError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 116 | except AttributeError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 196 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 287 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 331 | except AttributeError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 412 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 589 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 695 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 772 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 825 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 909 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_sequence_models.py | 1011 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_trt_format_models.py | 193 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_trt_format_models.py | 338 | except OSError: | CODE |
| HIGH | qa/common/gen_ensemble_model_utils.py | 1018 | except OSError: | CODE |
| HIGH | qa/common/gen_ensemble_model_utils.py | 1062 | except OSError: | CODE |
| HIGH | qa/common/gen_ensemble_model_utils.py | 1087 | except OSError: | CODE |
| HIGH | qa/common/gen_ensemble_model_utils.py | 764 | except OSError: | CODE |
| HIGH | qa/common/gen_ensemble_model_utils.py | 837 | except OSError: | CODE |
| HIGH | qa/common/gen_ensemble_model_utils.py | 870 | except OSError: | CODE |
| HIGH | qa/common/gen_ensemble_model_utils.py | 918 | except OSError: | CODE |
| HIGH | qa/common/gen_ensemble_model_utils.py | 940 | except OSError: | CODE |
| HIGH | qa/common/gen_ensemble_model_utils.py | 982 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_torchtrt_models.py | 75 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_torchtrt_models.py | 110 | except OSError: | CODE |
| HIGH | qa/common/gen_archive.py | 366 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_implicit_models.py | 255 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_implicit_models.py | 369 | except OSError: | CODE |
| HIGH | qa/common/gen_qa_implicit_models.py | 445 | except OSError: | CODE |
| 67 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | build.py | 102 | except Exception: | CODE |
| LOW | compose.py | 41 | except Exception: | CODE |
| LOW | …penai_frontend/frontend/fastapi/routers/completions.py | 61 | except Exception as e: | CODE |
| LOW | …penai/openai_frontend/frontend/fastapi/routers/chat.py | 62 | except Exception as e: | CODE |
| LOW | …openai_frontend/frontend/fastapi/routers/embeddings.py | 59 | except Exception as e: | CODE |
| LOW | …_frontend/frontend/fastapi/routers/model_management.py | 59 | except Exception as e: | CODE |
| LOW | …_frontend/frontend/fastapi/routers/model_management.py | 88 | except Exception as e: | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 681 | except Exception: | CODE |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 705 | except Exception: | CODE |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 700 | except Exception: | CODE |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 726 | except Exception as e: | CODE |
| LOW | …ne/utils/tool_call_parsers/mistral_tool_call_parser.py | 138 | except Exception: | CODE |
| LOW | …ne/utils/tool_call_parsers/mistral_tool_call_parser.py | 317 | except Exception: | CODE |
| LOW | …gine/utils/tool_call_parsers/llama_tool_call_parser.py | 131 | except Exception as e: | CODE |
| LOW | …gine/utils/tool_call_parsers/llama_tool_call_parser.py | 288 | except Exception: | CODE |
| LOW | python/openai/tests/utils.py | 151 | except Exception as err: | CODE |
| LOW | python/openai/tests/test_lora.py | 134 | except Exception as e: | CODE |
| MEDIUM | python/openai/tests/test_lora.py | 45 | def is_vllm_installed(): | CODE |
| LOW | …ploy/mlflow-triton-plugin/mlflow_triton/deployments.py | 481 | except Exception as e: | STRING |
| MEDIUM | qa/L0_lifecycle/lifecycle_test.py | 93 | def _infer_success_identity(self, model_base, versions, tensor_dtype, tensor_sha | CODE |
| MEDIUM | qa/L0_lifecycle/lifecycle_test.py | 134 | def _async_load(self, model_name, use_grpc): | CODE |
| LOW⚡ | qa/L0_lifecycle/lifecycle_test.py | 453 | except Exception as ex: | CODE |
| LOW⚡ | qa/L0_lifecycle/lifecycle_test.py | 461 | except Exception as ex: | CODE |
| LOW⚡ | qa/L0_lifecycle/lifecycle_test.py | 1538 | except Exception as ex: | CODE |
| LOW⚡ | qa/L0_lifecycle/lifecycle_test.py | 1548 | except Exception as ex: | CODE |
| LOW⚡ | qa/L0_lifecycle/lifecycle_test.py | 1558 | except Exception as ex: | CODE |
| LOW⚡ | qa/L0_lifecycle/lifecycle_test.py | 2175 | except Exception as ex: | CODE |
| LOW⚡ | qa/L0_lifecycle/lifecycle_test.py | 2185 | except Exception as ex: | CODE |
| LOW⚡ | qa/L0_lifecycle/lifecycle_test.py | 2195 | except Exception as ex: | CODE |
| LOW⚡ | qa/L0_lifecycle/lifecycle_test.py | 2863 | except Exception as ex: | CODE |
| LOW⚡ | qa/L0_lifecycle/lifecycle_test.py | 2873 | except Exception as ex: | CODE |
| LOW⚡ | qa/L0_lifecycle/lifecycle_test.py | 2882 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 90 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 120 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 138 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 193 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 202 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 230 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 256 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 265 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 293 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 321 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 345 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 365 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 375 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 391 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 411 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 426 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 483 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 498 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 517 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 532 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 555 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 573 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 588 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 631 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 649 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 667 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 714 | except Exception as ex: | CODE |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 732 | except Exception as ex: | CODE |
| 264 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | build.py | 1413 | # Create a user that can be used to run triton as | COMMENT |
| MEDIUM⚡ | python/openai/openai_frontend/engine/utils/triton.py | 284 | # Create a ctypes string buffer | COMMENT |
| MEDIUM | qa/L0_nan_inf/models/nan_inf_output/1/model.py | 38 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/L0_lifecycle/lifecycle_test.py | 1830 | # Create a new version for reload | COMMENT |
| MEDIUM | qa/L0_model_namespacing/python_subadd/__init__.py | 97 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/L0_model_namespacing/python_addsub/__init__.py | 97 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/L0_http/test.sh | 253 | # Create a password file with username:password | COMMENT |
| MEDIUM | …on/decoupled/models/decoupled_execute_error/1/model.py | 63 | """This function is called on inference request.""" | STRING |
| MEDIUM | …ython/decoupled/models/decoupled_bls_stream/1/model.py | 60 | """This function is called on inference request.""" | STRING |
| MEDIUM | …ckend_python/decoupled/models/decoupled_bls/1/model.py | 77 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/L0_sequence_batcher/test.sh | 282 | # Create the input_state_data file. | COMMENT |
| MEDIUM⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 199 | # Create a valid cuda shared memory region, fill data in it and register | COMMENT |
| MEDIUM⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 215 | # Create a valid cuda shared memory region and unregister before register | COMMENT |
| MEDIUM⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 226 | # Create a valid cuda shared memory region and unregister after register | COMMENT |
| MEDIUM⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 240 | # Create a valid cuda shared memory region and unregister after register | COMMENT |
| MEDIUM | qa/L0_perf_resnet/test.sh | 94 | # Create the TensorRT plan from ONNX model | COMMENT |
| MEDIUM | qa/L0_perf_resnet/test.sh | 156 | # Create the TensorRT plan from ONNX model | COMMENT |
| MEDIUM | qa/L0_trace/trace_stress_grpc_client.py | 61 | # Define the callback function. Note the last two parameters should be | COMMENT |
| MEDIUM | qa/L0_trace/models/input_all_required/1/model.py | 39 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/L0_string_io/string_client_test.py | 103 | # Create the data for the input tensor. Initialize the tensor to 8 | COMMENT |
| MEDIUM | qa/L0_nullchar_string/nullchar_string_client.py | 77 | # Create the inference context for the model. | COMMENT |
| MEDIUM | qa/L0_nullchar_string/nullchar_string_client.py | 85 | # Create the data for the input tensor. It contains a null character in | COMMENT |
| MEDIUM | qa/L0_sequence_stress/sequence_stress.py | 182 | # Create a variable length sequence with "start" and "end" flags. | COMMENT |
| MEDIUM | qa/L0_sequence_stress/sequence_stress.py | 305 | # Create a sequence without a "start" flag. Sequence should get an | COMMENT |
| MEDIUM | qa/L0_sequence_stress/sequence_stress.py | 344 | # Create a variable length sequence with "start" flag but that | COMMENT |
| MEDIUM | qa/L0_sequence_stress/sequence_stress.py | 609 | # Create the seed for the thread. Since these are created in | COMMENT |
| MEDIUM | qa/L0_libtorch_io_names/io_names_client.py | 46 | # Create the data for the two inputs. Initialize the first to unique | COMMENT |
| MEDIUM | qa/python_models/add_sub/model.py | 48 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/python_models/cuda_memory_consumer/1/model.py | 63 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/python_models/string_identity/model.py | 41 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/python_models/request_rescheduling_addsub/model.py | 49 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/python_models/sub_add/model.py | 51 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/python_models/execute_error/model.py | 32 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/python_models/execute_grpc_error/model.py | 36 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/python_models/python_version/model.py | 61 | """This function is called on inference request.""" | STRING |
| MEDIUM | qa/python_models/auto_complete/model.py | 63 | """This function is called on inference request.""" | STRING |
| MEDIUM | …_models/python_based_backends/add_sub_backend/model.py | 38 | """This function is called only once when loading the model assuming | STRING |
| MEDIUM | …_models/python_based_backends/add_sub_backend/model.py | 125 | """This function is called when an inference request is made | STRING |
| MEDIUM | qa/L0_grpc/test.sh | 407 | # Create a password file with username:password | COMMENT |
| MEDIUM | qa/L0_perf_deeprecommender/test.sh | 56 | # Create the TensorRT plan from ONNX | COMMENT |
| MEDIUM | qa/L0_perf_deeprecommender/test.sh | 125 | # Create the TensorRT plan from ONNX | COMMENT |
| MEDIUM | qa/common/libtorch_infer_client.py | 61 | # Create the data for the two input tensors. Initialize the first | COMMENT |
| MEDIUM | qa/common/gen_qa_ort_scalar_models.py | 42 | # Create the model | COMMENT |
| MEDIUM | qa/common/gen_qa_ort_scalar_models.py | 76 | # Create the model | COMMENT |
| MEDIUM | qa/common/gen_qa_ragged_models.py | 164 | # Create the model | COMMENT |
| MEDIUM | qa/common/gen_qa_ragged_models.py | 293 | # Create the model | COMMENT |
| MEDIUM | qa/common/gen_qa_ragged_models.py | 475 | # Create the model | STRING |
| MEDIUM | qa/common/gen_qa_ragged_models.py | 522 | # Create the model | STRING |
| MEDIUM | qa/common/gen_qa_dyna_sequence_models.py | 222 | # Create the model. For now don't implement a proper accumulator | COMMENT |
| MEDIUM | qa/common/gen_qa_dyna_sequence_models.py | 334 | # Create the model. For now don't implement a proper accumulator | COMMENT |
| MEDIUM | qa/common/gen_qa_dyna_sequence_models.py | 718 | # Create the model. For now don't implement a proper accumulator | STRING |
| MEDIUM | qa/common/gen_qa_sequence_models.py | 205 | # Create the model. For now don't implement a proper accumulator | COMMENT |
| MEDIUM | qa/common/gen_qa_sequence_models.py | 298 | # Create the model. For now don't implement a proper accumulator | COMMENT |
| MEDIUM | qa/common/gen_qa_sequence_models.py | 605 | # Create the model. For now don't implement a proper accumulator | STRING |
| MEDIUM | qa/common/gen_qa_trt_format_models.py | 84 | # Create the model | COMMENT |
| MEDIUM | qa/common/gen_qa_identity_models.py | 92 | # Create the model | COMMENT |
| MEDIUM | qa/common/gen_qa_identity_models.py | 181 | # Create the model | COMMENT |
| MEDIUM | qa/common/gen_qa_identity_models.py | 424 | # Create the model | STRING |
| MEDIUM | qa/common/gen_qa_identity_models.py | 533 | # Create the model | STRING |
| MEDIUM | qa/common/gen_qa_identity_models.py | 764 | # Create the model | STRING |
| 50 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | build.py | 120 | CODE | |
| LOW | build.py | 564 | CODE | |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 357 | CODE | |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 648 | CODE | |
| LOW | …ne/utils/tool_call_parsers/mistral_tool_call_parser.py | 144 | CODE | |
| LOW | …gine/utils/tool_call_parsers/llama_tool_call_parser.py | 137 | CODE | |
| LOW | python/openai/tests/conftest.py | 187 | CODE | |
| LOW | python/openai/tests/conftest.py | 188 | CODE | |
| LOW | python/openai/tests/test_tool_calling.py | 630 | CODE | |
| LOW | python/openai/tests/test_models/mock_llm/1/model.py | 73 | CODE | |
| LOW | …ploy/mlflow-triton-plugin/mlflow_triton/deployments.py | 186 | CODE | |
| LOW | …ploy/mlflow-triton-plugin/mlflow_triton/deployments.py | 240 | CODE | |
| LOW | …ploy/mlflow-triton-plugin/mlflow_triton/deployments.py | 335 | CODE | |
| LOW | …ploy/mlflow-triton-plugin/mlflow_triton/deployments.py | 407 | CODE | |
| LOW | qa/L0_trt_reformat_free/trt_reformat_free_test.py | 47 | CODE | |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 58 | CODE | |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 3013 | CODE | |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 3176 | CODE | |
| LOW | qa/L0_request_cancellation/cancellation_test_utils.py | 146 | CODE | |
| LOW | qa/L0_batcher/verify_timestamps.py | 34 | CODE | |
| LOW | qa/L0_http/http_test.py | 194 | CODE | |
| LOW | qa/L0_http/http_test.py | 416 | CODE | |
| LOW | qa/L0_http/http_request_many_chunks.py | 55 | CODE | |
| LOW | …equence_corrid_batcher/sequence_corrid_batcher_test.py | 87 | CODE | |
| LOW | …equence_corrid_batcher/sequence_corrid_batcher_test.py | 231 | CODE | |
| LOW | qa/L0_backend_python/python_test.py | 248 | CODE | |
| LOW | qa/L0_backend_python/python_test.py | 490 | CODE | |
| LOW | qa/L0_backend_python/decoupled/decoupled_test.py | 93 | CODE | |
| LOW | qa/L0_backend_python/decoupled/decoupled_test.py | 178 | CODE | |
| LOW | …ython/decoupled/models/decoupled_bls_stream/1/model.py | 77 | CODE | |
| LOW | …backend_python/response_sender/response_sender_test.py | 181 | CODE | |
| LOW | qa/L0_backend_python/io/io_test.py | 68 | CODE | |
| LOW | qa/L0_backend_python/io/requested_output_model/model.py | 70 | CODE | |
| LOW | qa/L0_backend_python/lifecycle/lifecycle_test.py | 93 | CODE | |
| LOW | …_backend_python/parameters/response_parameters_test.py | 48 | CODE | |
| LOW | …_python/model_readiness/test_models/readiness_model.py | 60 | CODE | |
| LOW | qa/L0_logging/log_format_test.py | 425 | CODE | |
| LOW | qa/L0_logging/log_format_test.py | 474 | CODE | |
| LOW | qa/L0_server_status/server_status_test.py | 45 | CODE | |
| LOW | qa/L0_server_status/server_status_test.py | 156 | CODE | |
| LOW | qa/L0_server_status/server_status_test.py | 314 | CODE | |
| LOW | qa/L0_server_status/server_status_test.py | 440 | CODE | |
| LOW | qa/L0_server_status/server_status_test.py | 515 | CODE | |
| LOW | qa/L0_server_status/server_status_test.py | 616 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 169 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 235 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 291 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 374 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 446 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 526 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 610 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 671 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 795 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 983 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 1166 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 1365 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 1561 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 1776 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 2013 | CODE | |
| LOW | qa/L0_sequence_batcher/sequence_batcher_test.py | 2262 | CODE | |
| 87 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | qa/L0_vertex_ai/vertex_ai_test.py | 0 | inference-header-content-length value exceeding int_max triggers std::out_of_range in std::stoi. before the fix this cra | STRING |
| HIGH | qa/L0_sagemaker/sagemaker_test.py | 0 | inference-header-content-length value exceeding int_max triggers std::out_of_range in std::stoi. before the fix this cra | STRING |
| HIGH | qa/L0_http/http_test.py | 0 | inference-header-content-length value exceeding int_max triggers std::out_of_range in std::stoi. before the fix this cra | STRING |
| HIGH | …ython/decoupled/models/decoupled_bls_cancel/1/model.py | 0 | this model sends a decoupled bls inference request to 'response_sender_until_cancelled' model, and sums up its responses | STRING |
| HIGH | …/models/decoupled_bls_cancel_after_complete/1/model.py | 0 | this model sends a decoupled bls inference request to 'response_sender_until_cancelled' model, and sums up its responses | STRING |
| HIGH | …decoupled/models/decoupled_bls_async_cancel/1/model.py | 0 | this model sends a decoupled bls inference request to 'response_sender_until_cancelled' model, and sums up its responses | STRING |
| HIGH | …on/decoupled/models/decoupled_execute_error/1/model.py | 0 | the model `{}` can generate any number of responses per request, enable decoupled transaction policy in model configurat | STRING |
| HIGH | …ython/decoupled/models/decoupled_bls_stream/1/model.py | 0 | the model `{}` can generate any number of responses per request, enable decoupled transaction policy in model configurat | STRING |
| HIGH | …led/models/decoupled_send_after_close_error/1/model.py | 0 | the model `{}` can generate any number of responses per request, enable decoupled transaction policy in model configurat | STRING |
| HIGH | …pled/models/decoupled_return_response_error/1/model.py | 0 | the model `{}` can generate any number of responses per request, enable decoupled transaction policy in model configurat | STRING |
| HIGH | …ckend_python/decoupled/models/decoupled_bls/1/model.py | 0 | the model `{}` can generate any number of responses per request, enable decoupled transaction policy in model configurat | STRING |
| HIGH | qa/python_models/dlpack_square/model.py | 0 | the model `{}` can generate any number of responses per request, enable decoupled transaction policy in model configurat | STRING |
| HIGH | qa/python_models/iterative_sequence/model.py | 0 | the model `{}` can generate any number of responses per request, enable decoupled transaction policy in model configurat | STRING |
| HIGH | …led/models/decoupled_send_after_close_error/1/model.py | 0 | tries to create a response sender object and use that for sending the response. | STRING |
| HIGH | …pled/models/decoupled_return_response_error/1/model.py | 0 | tries to create a response sender object and use that for sending the response. | STRING |
| HIGH | qa/python_models/response_sender_error/model.py | 0 | tries to create a response sender object and use that for sending the response. | STRING |
| HIGH | qa/common/gen_qa_trt_plugin_models.py | 0 | name: "{}" platform: "tensorrt_plan" max_batch_size: {} version_policy: {} input [ {{ name: "input0" data_type: {} dims: | STRING |
| HIGH | qa/common/gen_qa_trt_format_models.py | 0 | name: "{}" platform: "tensorrt_plan" max_batch_size: {} version_policy: {} input [ {{ name: "input0" data_type: {} dims: | STRING |
| HIGH | qa/common/gen_qa_models.py | 0 | name: "{}" platform: "tensorrt_plan" max_batch_size: {} version_policy: {} input [ {{ name: "input0" data_type: {} dims: | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH⚡ | build.py | 1418 | RUN userdel tensorrt-server > /dev/null 2>&1 || true \\ | CODE |
| HIGH⚡ | build.py | 1419 | && userdel ubuntu > /dev/null 2>&1 || true \\ | CODE |
| HIGH | build.py | 1084 | && (cd /tmp && tar xzf boost.tar.gz) \\ | CODE |
| HIGH | build.py | 1142 | "$(. /etc/os-release && echo "$VERSION_CODENAME")" stable" | \\ | CODE |
| HIGH | build.py | 1198 | && (cd /tmp && tar xzf boost.tar.gz) \\ | CODE |
| HIGH | build.py | 1219 | && apt-get install -y --no-install-recommends ccache && ccache -p \\ | CODE |
| HIGH | build.py | 1568 | RUN dirname $(find /usr -name "libcudart*.so" -o -name "libnvinf*.so" -o -name "libnvshm*" -type f) | sort -u > /etc/l | CODE |
| HIGH⚡ | qa/L0_sequence_batcher/sequence_batcher_test.py | 3054 | # execution to be a batch of 'null, seq 2'. The second execution should | COMMENT |
| HIGH⚡ | qa/L0_sequence_batcher/sequence_batcher_test.py | 3165 | # execution to be a batch of 'null, seq 2'. Both executions should be | COMMENT |
| HIGH | qa/L0_sequence_batcher/sequence_batcher_test.py | 2943 | # execution to be a batch of 'null, seq 2'. The executions should not be | COMMENT |
| HIGH | qa/common/gen_qa_model_repository.py | 708 | " rm -rf build && mkdir build && cd build && cmake .. &&" | CODE |
| HIGH | qa/common/gen_qa_model_repository.py | 829 | + " --format=csv || true", | CODE |
| HIGH | qa/common/gen_qa_model_repository.py | 830 | "nvidia-smi || true", | CODE |
| HIGH | qa/common/gen_qa_model_repository.py | 850 | " --summary {root}/manifest-summary.json || true".format( | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | qa/L0_trace/test.sh | 214 | #======================================= | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 191 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 193 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 222 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 224 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 278 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 280 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 318 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 320 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 798 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 800 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 997 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 999 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 1197 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_manifest.py | 1199 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 187 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 189 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 220 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 222 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 741 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 743 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 887 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 889 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 1253 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 1255 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 1744 | # -------------------------------------------------------------------------- | COMMENT |
| MEDIUM | qa/common/gen_qa_model_repository.py | 1746 | # -------------------------------------------------------------------------- | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …on/openai/openai_frontend/frontend/fastapi_frontend.py | 27 | CODE | |
| LOW | python/openai/openai_frontend/frontend/frontend.py | 27 | CODE | |
| LOW | python/openai/openai_frontend/schemas/openai.py | 31 | CODE | |
| LOW | python/openai/openai_frontend/engine/engine.py | 28 | CODE | |
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 28 | CODE | |
| LOW | …ai_frontend/engine/utils/tool_call_parsers/__init__.py | 31 | CODE | |
| LOW | …ai_frontend/engine/utils/tool_call_parsers/__init__.py | 32 | CODE | |
| LOW | …ai_frontend/engine/utils/tool_call_parsers/__init__.py | 33 | CODE | |
| LOW | …ai_frontend/engine/utils/tool_call_parsers/__init__.py | 33 | CODE | |
| LOW | python/openai/tests/test_lora.py | 47 | CODE | |
| LOW | qa/L0_rate_limiter/rate_limiter_test.py | 42 | CODE | |
| LOW | …no_duplication/subadd_repo/composing_subadd/1/model.py | 6 | CODE | |
| LOW | …no_duplication/addsub_repo/composing_addsub/1/model.py | 6 | CODE | |
| LOW | …le_duplication/subadd_repo/composing_subadd/1/model.py | 6 | CODE | |
| LOW | …le_duplication/addsub_repo/composing_addsub/1/model.py | 6 | CODE | |
| LOW | …amic_resolution/subadd_repo/composing_model/1/model.py | 6 | CODE | |
| LOW | …amic_resolution/addsub_repo/composing_model/1/model.py | 6 | CODE | |
| LOW | …est_duplication/subadd_repo/composing_model/1/model.py | 6 | CODE | |
| LOW | …est_duplication/addsub_repo/composing_model/1/model.py | 6 | CODE | |
| LOW | qa/L0_http/python_http_aio_test.py | 31 | CODE | |
| LOW | qa/L0_backend_python/test_infer_shm_leak.py | 34 | CODE | |
| LOW | qa/L0_backend_python/test_infer_shm_leak.py | 39 | CODE | |
| LOW | qa/L0_backend_python/python_test.py | 41 | CODE | |
| LOW | qa/L0_backend_python/ensemble/ensemble_test.py | 39 | CODE | |
| LOW | qa/L0_backend_python/decoupled/decoupled_test.py | 42 | CODE | |
| LOW | …/models/decoupled_bls_cancel_after_complete/1/model.py | 26 | CODE | |
| LOW | …decoupled/models/decoupled_bls_async_cancel/1/model.py | 26 | CODE | |
| LOW | qa/L0_backend_python/io/io_test.py | 42 | CODE | |
| LOW | qa/L0_backend_python/lifecycle/lifecycle_test.py | 47 | CODE | |
| LOW | qa/L0_backend_python/restart/restart_test.py | 39 | CODE | |
| LOW | …/L0_backend_python/model_control/model_control_test.py | 42 | CODE | |
| LOW | …on/python_based_backends/python_based_backends_test.py | 34 | CODE | |
| LOW | qa/L0_backend_python/logging/logging_test.py | 38 | CODE | |
| LOW | qa/L0_server_status/server_status_test.py | 41 | CODE | |
| LOW | qa/L0_http_fuzz/fuzztest.py | 39 | CODE | |
| LOW | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 46 | CODE | |
| LOW | qa/L0_pytorch_python_runtime/infer.py | 35 | CODE | |
| LOW | qa/L0_model_queue/model_queue_test.py | 38 | CODE | |
| LOW | qa/L0_grpc/python_grpc_aio_test.py | 31 | CODE | |
| LOW | qa/L0_response_cache/ensemble_cache_test.py | 40 | CODE | |
| LOW | qa/common/sequence_util.py | 41 | CODE | |
| LOW | qa/common/shm_util.py | 32 | CODE | |
| LOW | qa/common/shm_util.py | 41 | CODE | |
| LOW | qa/common/infer_util.py | 42 | CODE | |
| LOW | qa/L0_metrics/pinned_memory_metrics_test.py | 37 | CODE | |
| LOW | qa/L0_long_running_stress/stress.py | 31 | CODE | |
| LOW | qa/L0_model_config/compare_status.py | 38 | CODE | |
| LOW | docs/conf.py | 50 | CODE | |
| LOW | docs/conf.py | 51 | CODE | |
| LOW | docs/conf.py | 53 | CODE | |
| LOW | src/python/tritonfrontend/__init__.py | 29 | CODE | |
| LOW | src/python/tritonfrontend/__init__.py | 30 | CODE | |
| LOW | src/python/tritonfrontend/__init__.py | 30 | CODE | |
| LOW | src/python/tritonfrontend/__init__.py | 33 | CODE | |
| LOW | src/python/tritonfrontend/__init__.py | 39 | CODE | |
| LOW | src/python/tritonfrontend/__init__.py | 45 | CODE | |
| LOW | src/python/tritonfrontend/_api/__init__.py | 28 | CODE | |
| LOW | src/python/tritonfrontend/_api/__init__.py | 35 | CODE | |
| LOW | src/python/tritonfrontend/_api/__init__.py | 42 | CODE | |
| LOW | src/python/tritonfrontend/_c/__init__.py | 27 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 195 | cshm.create_shared_memory_region("dummy_data", -1, 0) | CODE |
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 200 | shm_op0_handle = cshm.create_shared_memory_region("dummy_data", 8, 0) | CODE |
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 205 | "dummy_data", cshm.get_raw_handle(shm_op0_handle), 0, 8 | CODE |
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 216 | shm_op0_handle = cshm.create_shared_memory_region("dummy_data", 8, 0) | CODE |
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 217 | self.triton_client.unregister_cuda_shared_memory("dummy_data") | CODE |
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 227 | shm_op0_handle = cshm.create_shared_memory_region("dummy_data", 8, 0) | CODE |
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 229 | "dummy_data", cshm.get_raw_handle(shm_op0_handle), 0, 8 | CODE |
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 231 | self.triton_client.unregister_cuda_shared_memory("dummy_data") | CODE |
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 241 | shm_op0_handle = cshm.create_shared_memory_region("dummy_data", 8, 0) | CODE |
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 243 | "dummy_data", cshm.get_raw_handle(shm_op0_handle), 0, 8 | CODE |
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 247 | "dummy_data", cshm.get_raw_handle(shm_op0_handle), 0, 8 | CODE |
| LOW⚡ | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 251 | "shared memory region 'dummy_data' already in manager", str(ex) | CODE |
| LOW | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 159 | shm_op0_handle = cshm.create_shared_memory_region("dummy_data", 8, 0) | CODE |
| LOW | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 173 | "dummy_data", cshm.get_raw_handle(shm_op0_handle), 0, 8 | CODE |
| LOW | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 180 | self.triton_client.unregister_cuda_shared_memory("dummy_data") | CODE |
| LOW | qa/L0_parameters/parameters_test.py | 288 | parameters = {reserved_key: "dummy-value"} | CODE |
| LOW⚡ | qa/L0_parameters/parameters_test.py | 338 | body, extra_headers={reserved_key: "dummy-value"} | CODE |
| LOW | qa/L0_parameters/parameters_test.py | 356 | headers={reserved_key: "dummy-value"}, | CODE |
| LOW | qa/L0_parameters/parameters_test.py | 363 | headers={reserved_key: "dummy-value"}, | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 186 | shm.create_shared_memory_region("dummy_data", "/dummy_data", -1) | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 191 | shm_op0_handle = shm.create_shared_memory_region("dummy_data", "/dummy_data", 8) | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 195 | self.triton_client.register_system_shared_memory("dummy_data", "/dummy_data", 8) | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 205 | shm_op0_handle = shm.create_shared_memory_region("dummy_data", "/dummy_data", 8) | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 206 | self.triton_client.unregister_system_shared_memory("dummy_data") | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 216 | shm_op0_handle = shm.create_shared_memory_region("dummy_data", "/dummy_data", 8) | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 217 | self.triton_client.register_system_shared_memory("dummy_data", "/dummy_data", 8) | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 218 | self.triton_client.unregister_system_shared_memory("dummy_data") | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 228 | shm_op0_handle = shm.create_shared_memory_region("dummy_data", "/dummy_data", 8) | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 229 | self.triton_client.register_system_shared_memory("dummy_data", "/dummy_data", 8) | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 232 | "dummy_data", "/dummy_data", 8 | CODE |
| LOW⚡ | qa/L0_shared_memory/shared_memory_test.py | 236 | "shared memory region 'dummy_data' already in manager", str(ex) | CODE |
| LOW | qa/L0_shared_memory/shared_memory_test.py | 151 | shm_op0_handle = shm.create_shared_memory_region("dummy_data", "/dummy_data", 8) | CODE |
| LOW | qa/L0_shared_memory/shared_memory_test.py | 165 | "dummy_data", "/dummy_data", 8 | CODE |
| LOW | qa/L0_shared_memory/shared_memory_test.py | 172 | self.triton_client.unregister_system_shared_memory("dummy_data") | CODE |
| LOW | qa/L0_storage_S3/test.sh | 97 | aws configure set aws_access_key_id "dummy_id" && \ | CODE |
| LOW | qa/L0_storage_S3/test.sh | 98 | aws configure set aws_secret_access_key "dummy_key" | CODE |
| LOW | qa/L0_storage_S3/test.sh | 140 | aws configure set aws_access_key_id "dummy_id" && \ | CODE |
| LOW | qa/L0_storage_S3/test.sh | 141 | aws configure set aws_secret_access_key "dummy_key" | CODE |
| LOW | qa/L0_storage_S3/test.sh | 199 | aws configure set aws_access_key_id "dummy_id" && \ | CODE |
| LOW | qa/L0_storage_S3/test.sh | 200 | aws configure set aws_secret_access_key "dummy_key" | CODE |
| LOW⚡ | qa/L0_client_timeout/client_non_infer_timeout_test.py | 305 | "dummy_data", byte_size=byteSize, device_id=0 | CODE |
| LOW⚡ | qa/L0_client_timeout/client_non_infer_timeout_test.py | 310 | "dummy_data", | CODE |
| LOW⚡ | qa/L0_client_timeout/client_non_infer_timeout_test.py | 319 | "dummy_data", | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …rontend/frontend/fastapi/middleware/api_restriction.py | 193 | # Check if the request matches any restricted patterns | COMMENT |
| LOW | python/openai/openai_frontend/engine/utils/triton.py | 639 | # Check if the files exist | COMMENT |
| LOW | python/openai/tests/test_chat_completions.py | 288 | # Check if the number of words is around max_completion_tokens | COMMENT |
| LOW | …ploy/mlflow-triton-plugin/mlflow_triton/deployments.py | 485 | # Check if the deployment directory exists | STRING |
| LOW | …ploy/mlflow-triton-plugin/mlflow_triton/deployments.py | 520 | # Check if the model name is empty or only contains whitespace, tabs, or newlines | STRING |
| LOW | qa/L0_lifecycle/retry_model/1/model.py | 50 | # Check if an special file has been created in the version directory, | COMMENT |
| LOW | qa/L0_batcher/queue_timeout_test.py | 81 | # Check if the request has timed-out | COMMENT |
| LOW | qa/L0_http/test.sh | 521 | # Check if the server is still working after the above bad requests | COMMENT |
| LOW | …equence_corrid_batcher/sequence_corrid_batcher_test.py | 236 | # Check if the corrid data type matches the expected corrid data type specified in the model config | COMMENT |
| LOW | …/L0_backend_python/model_control/model_control_test.py | 104 | # Check if curl is available | COMMENT |
| LOW | qa/L0_backend_python/logging/test.sh | 107 | # Check if correct # log messages are present [ non-verbose-msg-cnt | verbose-msg-cnt ] | COMMENT |
| LOW | qa/L0_logging/test.sh | 125 | # Check if the current settings are returned [ file | info | warn | error | verbosity |format ] | COMMENT |
| LOW | qa/L0_logging/test.sh | 370 | # Check if the current settings are returned [ file | info | warn | error | verbosity |format ] | COMMENT |
| LOW | qa/L0_trace/test.sh | 232 | # Check if the current setting is returned | COMMENT |
| LOW | qa/L0_trace/test.sh | 292 | # Check if the current setting is returned (not specified setting from global) | COMMENT |
| LOW | qa/L0_trace/test.sh | 302 | # Check if the current setting is returned (not specified setting from global) | COMMENT |
| LOW | qa/L0_trace/test.sh | 386 | # Check if the current setting is returned | COMMENT |
| LOW | qa/L0_trace/test.sh | 417 | # Check if the current setting (global) is returned | COMMENT |
| LOW | qa/L0_trace/test.sh | 514 | # Check if the current setting is returned | COMMENT |
| LOW | qa/L0_trace/test.sh | 562 | # Check if the indexed file has been generated when trace count reaches 0 | COMMENT |
| LOW | qa/L0_pytorch_python_runtime/test.sh | 168 | # Print result and exit | COMMENT |
| LOW | qa/python_models/bls/model.py | 311 | # Check if any of the threads had an exception | COMMENT |
| LOW | qa/L0_cmdline_trace/test.sh | 469 | # Check if the traces are captured with proper hierarchy | COMMENT |
| LOW | qa/L0_cmdline_trace/test.sh | 528 | # Check if the traces are captured with proper hierarchy | COMMENT |
| LOW | qa/L0_response_cache/test.sh | 412 | # Check if the JSON data file was generated | COMMENT |
| LOW | qa/common/check_copyright.py | 208 | # Check if the copyright year line matches the regex | STRING |
| LOW | qa/common/check_massif_log.py | 41 | # Read the file | COMMENT |
| LOW | qa/L0_storage_S3_local/mock_s3_service.py | 109 | # Print the result | COMMENT |
| LOW | qa/L0_simple_ensemble/ensemble_backpressure_test.py | 100 | # Add response to list if it has data (not empty final-only response) | COMMENT |
| LOW | qa/L0_simple_ensemble/ensemble_backpressure_test.py | 104 | # Check if this is the final response | COMMENT |
| LOW | qa/L0_metrics/test.sh | 192 | # Check if memory usage HAS reduced to 0 after using the --enable-peer-access flag | COMMENT |
| LOW | qa/L0_infer/test.sh | 340 | # Check if running a memory leak check | COMMENT |
| LOW | qa/L0_mlflow/plugin_test.py | 110 | # Check if the additional files are properly copied | COMMENT |
| LOW | qa/L0_model_update/instance_update_test.py | 69 | # Check if the test passed for this test case that is tearing down | COMMENT |
| LOW | docs/generate_docs.py | 230 | # Check if target is valid for conversion | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | python/openai/openai_frontend/engine/utils/triton.py | 303 | # FIXME: This could be a bit more robust by reading byte size from first | COMMENT |
| MEDIUM | …ne/utils/tool_call_parsers/mistral_tool_call_parser.py | 220 | # re-set stuff pertaining to progress in the current tool | COMMENT |
| MEDIUM | …gine/utils/tool_call_parsers/llama_tool_call_parser.py | 221 | # re-set stuff pertaining to progress in the current tool | COMMENT |
| MEDIUM | qa/L0_lifecycle/test.sh | 1442 | # some more comprehensive fuzz attacks. | COMMENT |
| MEDIUM | qa/L0_trace/opentelemetry_unittest.py | 102 | # Essentially, this is what will be injected to headers/metadata | COMMENT |
| MEDIUM | qa/python_models/bls_request_rescheduling/model.py | 38 | # TODO: Make this more robust to wait until fully unloaded | COMMENT |
| MEDIUM | qa/python_models/bls_model_loading/model.py | 42 | # TODO: Make this more robust to wait until fully unloaded | COMMENT |
| MEDIUM | qa/L0_response_cache/test.sh | 119 | # Redis >= 6.0 and is more comprehensive in what can be configured. | COMMENT |
| MEDIUM | qa/L0_torch_aoti_hstu/test.sh | 45 | # The CI harness runs this with `bash -ex`. The test checks exit codes itself and | COMMENT |
| MEDIUM | qa/common/gen_qa_trt_plugin_models.py | 328 | # Linux can leverage LD_PRELOAD. We must load the Windows plugin manually | STRING |
| LOW | qa/common/gen_qa_dyna_sequence_models.py | 223 | # just return 0 if not-ready and 'INPUT'+'START'*('END'*'CORRID') | COMMENT |
| LOW | qa/common/gen_qa_dyna_sequence_models.py | 335 | # just return 0 if not-ready and 'INPUT'+'START'*('END'*'CORRID') | COMMENT |
| LOW | qa/common/gen_qa_dyna_sequence_models.py | 719 | # just return 0 if not-ready and 'INPUT'+'START'*('END'*'CORRID') | STRING |
| LOW | qa/common/gen_qa_sequence_models.py | 206 | # just return 0 if not-ready and 'INPUT'+'START' otherwise... the | COMMENT |
| LOW | qa/common/gen_qa_sequence_models.py | 299 | # just return 0 if not-ready and 'INPUT'+'START' otherwise... the | COMMENT |
| LOW | qa/common/gen_qa_sequence_models.py | 606 | # just return 0 if not-ready and 'INPUT'+'START' otherwise... the | STRING |
| LOW | qa/common/gen_qa_dyna_sequence_implicit_models.py | 55 | # just return 0 if not-ready and 'INPUT'+'START'*('END'*'CORRID') | COMMENT |
| MEDIUM | qa/L0_metrics/metrics_queue_size_test.py | 281 | # is less comprehensive on checking exact queue values, and just verifies | COMMENT |
| LOW | qa/L0_metrics/test.sh | 382 | # Don't use special debug env var for this, just set sufficient parameters for | COMMENT |
| MEDIUM | qa/L0_model_config/test.sh | 79 | # load the files provided in the version directory. Essentially, | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/openai/tests/test_openai_restricted_apis.py | 102 | CODE | |
| LOW | python/openai/tests/test_openai_restricted_apis.py | 124 | CODE | |
| LOW | python/openai/tests/test_openai_restricted_apis.py | 142 | CODE | |
| LOW | qa/L0_lifecycle/lifecycle_test.py | 3142 | CODE | |
| LOW | qa/L0_cuda_shared_memory/cuda_shared_memory_test.py | 742 | CODE | |
| LOW | qa/L0_storage_swiftstack/infer_test.py | 44 | CODE | |
| LOW | qa/L0_decoupled/decoupled_test.py | 246 | CODE | |
| LOW | qa/python_models/pytorch_fp32_fp32/model.py | 57 | CODE | |
| LOW | qa/python_models/response_sender/model_common.py | 114 | CODE | |
| LOW | qa/common/gen_ensemble_model_utils.py | 50 | CODE | |
| LOW | qa/common/gen_manifest.py | 803 | CODE | |
| LOW | qa/common/gen_manifest.py | 1039 | CODE | |
| LOW | qa/common/gen_qa_models.py | 1528 | CODE | |
| LOW | qa/common/infer_test.py | 51 | CODE | |
| LOW | qa/common/infer_util.py | 99 | CODE | |
| LOW | qa/common/infer_util.py | 737 | CODE | |
| LOW | qa/common/infer_util.py | 1019 | CODE | |
| LOW | qa/common/infer_util.py | 1363 | CODE | |
| LOW | qa/L0_grpc_state_cleanup/cleanup_test.py | 333 | CODE | |
| LOW | qa/L0_infer_variable/infer_variable_test.py | 59 | CODE | |
| LOW | qa/L0_infer/infer_test.py | 97 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | README.md | 92 | # Step 1: Create the example model repository | COMMENT |
| LOW⚡ | README.md | 97 | # Step 2: Launch triton from the NGC Triton container | COMMENT |
| LOW⚡ | README.md | 100 | # Step 3: Sending an Inference Request | COMMENT |
| LOW | qa/python_models/identity_bf16/model.py | 83 | # NOTE: The following helper function is for testing and example | COMMENT |
| LOW | qa/L0_simple_ensemble/test.sh | 434 | # Step 1 - decoupled_producer (batch size 2) | COMMENT |
| LOW | …ials/Feature_Guide/Speculative_Decoding/vLLM/README.md | 166 | ### Step 1: Launch Container | COMMENT |
| LOW | …ials/Feature_Guide/Speculative_Decoding/vLLM/README.md | 176 | ### Step 2: Start Triton Server | COMMENT |
| LOW | …ials/Feature_Guide/Speculative_Decoding/vLLM/README.md | 193 | ### Step 3: Send Inference Requests | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | deploy/gke-marketplace-app/README.md | 59 | Users need to follow these [instructions](https://cloud.google.com/kubernetes-engine/docs/how-to/kubernetes-service-acco | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/openai/openai_frontend/engine/triton_engine.py | 102 | logger = logging.getLogger(__name__) | CODE |
| LOW | …ai_frontend/engine/utils/tool_call_parsers/__init__.py | 35 | __all__ = [ | CODE |
| LOW | …ploy/mlflow-triton-plugin/mlflow_triton/deployments.py | 50 | logger = logging.getLogger(__name__) | CODE |