Universal LLM Deployment Engine with ML Compilation
This report summarizes scanner evidence for mlc-ai/mlc-llm, a Python project with 23,229 GitHub stars. SynthScan examined 90,104 lines of code across 572 source files, recording 958 pattern matches distributed across 19 syntactic categories. The legacy adjusted pattern signal is 20.6 (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? 515 finding(s).
Are imports declared and package/API names verified? 156 finding(s).
Are wrappers, guards, and repeated structures necessary? 579 finding(s).
Which changes need focused human review? 958 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 958 distinct pattern matches across 19 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 |
|---|---|---|---|---|
| HIGH | python/mlc_llm/nn/__init__.py | 0 | common `nn.modules` used to define llms in this project. | STRING |
| HIGH | python/mlc_llm/model/phi3/__init__.py | 0 | common `nn.modules` used to define llms in this project. | STRING |
| HIGH | python/mlc_llm/model/vision/__init__.py | 0 | common `nn.modules` used to define llms in this project. | STRING |
| HIGH | python/mlc_llm/quantization/group_quantization.py | 0 | quantize model with awq quantization. parameters ---------- model : nn.module the non-quantized nn.module. quant_map : q | STRING |
| HIGH | python/mlc_llm/quantization/ft_quantization.py | 0 | quantize model with awq quantization. parameters ---------- model : nn.module the non-quantized nn.module. quant_map : q | STRING |
| HIGH | python/mlc_llm/quantization/block_scale_quantization.py | 0 | quantize model with awq quantization. parameters ---------- model : nn.module the non-quantized nn.module. quant_map : q | STRING |
| HIGH | python/mlc_llm/quantization/awq_quantization.py | 0 | quantize model with awq quantization. parameters ---------- model : nn.module the non-quantized nn.module. quant_map : q | STRING |
| HIGH | python/mlc_llm/quantization/group_quantization.py | 0 | the visiting method for fastertransformer quantization of nn.module nodes. parameters ---------- name : str the name of | STRING |
| HIGH | python/mlc_llm/quantization/per_tensor_quantization.py | 0 | the visiting method for fastertransformer quantization of nn.module nodes. parameters ---------- name : str the name of | STRING |
| HIGH | python/mlc_llm/quantization/ft_quantization.py | 0 | the visiting method for fastertransformer quantization of nn.module nodes. parameters ---------- name : str the name of | STRING |
| HIGH | python/mlc_llm/quantization/group_quantization.py | 0 | forward method for per-tensor quantized embedding layer. parameters ---------- x : nn.tensor the input tensor. returns - | STRING |
| HIGH | python/mlc_llm/quantization/per_tensor_quantization.py | 0 | forward method for per-tensor quantized embedding layer. parameters ---------- x : nn.tensor the input tensor. returns - | STRING |
| HIGH | python/mlc_llm/quantization/ft_quantization.py | 0 | forward method for per-tensor quantized embedding layer. parameters ---------- x : nn.tensor the input tensor. returns - | STRING |
| HIGH | python/mlc_llm/quantization/awq_quantization.py | 0 | forward method for per-tensor quantized embedding layer. parameters ---------- x : nn.tensor the input tensor. returns - | STRING |
| HIGH | python/mlc_llm/quantization/group_quantization.py | 0 | override to() such that we do not convert bias if there is an out_dtype. otherwise, we might run into dtype mismatch whe | STRING |
| HIGH | python/mlc_llm/quantization/per_tensor_quantization.py | 0 | override to() such that we do not convert bias if there is an out_dtype. otherwise, we might run into dtype mismatch whe | STRING |
| HIGH | python/mlc_llm/quantization/ft_quantization.py | 0 | override to() such that we do not convert bias if there is an out_dtype. otherwise, we might run into dtype mismatch whe | STRING |
| HIGH | python/mlc_llm/quantization/block_scale_quantization.py | 0 | override to() such that we do not convert bias if there is an out_dtype. otherwise, we might run into dtype mismatch whe | STRING |
| HIGH | python/mlc_llm/quantization/awq_quantization.py | 0 | override to() such that we do not convert bias if there is an out_dtype. otherwise, we might run into dtype mismatch whe | STRING |
| HIGH | python/mlc_llm/model/llama4/llama4_model.py | 0 | the embedding module that can be shared with the final lm_head. from qwen2embedding. | STRING |
| HIGH | python/mlc_llm/model/olmo/olmo_model.py | 0 | the embedding module that can be shared with the final lm_head. from qwen2embedding. | STRING |
| HIGH | python/mlc_llm/model/llama/llama_model.py | 0 | the embedding module that can be shared with the final lm_head. from qwen2embedding. | STRING |
| HIGH | python/mlc_llm/model/llama4/llama4_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/ministral3/ministral3_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/cohere/cohere_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/gemma/gemma_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/olmo2/olmo2_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/olmo/olmo_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/phi3/phi3_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/qwen2/qwen2_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/minicpm/minicpm_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/qwen3/qwen3_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/nemotron/nemotron_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/llama/llama_model.py | 0 | the lm_head forwarding, which transposes the weight and multiplies with the input tensor. | STRING |
| HIGH | python/mlc_llm/model/llama4/llama4_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/llama/llama_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/ministral3/ministral3_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/cohere/cohere_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/starcoder2/starcoder2_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/gemma/gemma_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/olmo2/olmo2_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/internlm/internlm_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/gpt_neox/gpt_neox_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/gemma2/gemma2_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/mixtral/mixtral_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/olmo/olmo_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/phi3/phi3_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/phi3v/phi3v_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/phi/phi_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/gemma3/gemma3v_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/gemma3/gemma3_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/qwen2/qwen2_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/qwen3/qwen3_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/qwen2_moe/qwen2_moe_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/qwen3_moe/qwen3_moe_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/minicpm/minicpm_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/stable_lm/stablelm_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/medusa/medusa_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/orion/orion_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| HIGH | python/mlc_llm/model/eagle/eagle_loader.py | 0 | this file specifies how mlc's rwkv6 parameter maps from other formats, for example huggingface pytorch, huggingface safe | STRING |
| 47 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/mlc_llm/__init__.py | 14 | def _create_socket_session_local_workers(num_workers): | CODE |
| LOW | python/mlc_llm/base.py | 26 | def _debug_cuda_profiler_start() -> None: | CODE |
| LOW | python/mlc_llm/base.py | 35 | def _debug_cuda_profiler_stop() -> None: | CODE |
| LOW | python/mlc_llm/json_ffi/engine.py | 26 | def get_request_stream_callback(self) -> Callable[[str], None]: | CODE |
| LOW | python/mlc_llm/json_ffi/engine.py | 34 | def _sync_request_stream_callback(self, chat_completion_stream_responses_json_str: str) -> None: | CODE |
| LOW | python/mlc_llm/bench/request_processor.py | 71 | def _sample_from_plain_request_records( | CODE |
| LOW | python/mlc_llm/bench/request_processor.py | 94 | def _sample_from_grouped_request_records( | CODE |
| LOW | python/mlc_llm/bench/request_processor.py | 274 | def generate_fake_warmup_requests( | CODE |
| LOW | python/mlc_llm/bench/__main__.py | 34 | def _parse_num_concurrent_requests(num_str: Optional[str]) -> Optional[List[int]]: # noqa: UP006 | CODE |
| LOW | python/mlc_llm/bench/request_record.py | 116 | def _compute_metrics_statistics( | CODE |
| LOW | python/mlc_llm/interface/gen_config.py | 32 | def apply_system_defaults_for_missing_fields(mlc_chat_config: MLCChatConfig) -> None: | CODE |
| LOW | python/mlc_llm/interface/compile.py | 63 | def _apply_preproc_to_params_and_check_pipeline( | CODE |
| LOW | python/mlc_llm/interface/calibrate.py | 106 | async def send_calibration_requests( | CODE |
| LOW | python/mlc_llm/interface/convert_weight.py | 74 | def _merge_lora_adapter_with_base_model(base_source: Path, lora_adapter: Path) -> Iterator[Path]: | CODE |
| LOW | python/mlc_llm/interface/router.py | 66 | async def completion_stream_generator() -> AsyncGenerator[str, None]: | CODE |
| LOW | python/mlc_llm/op/triton.py | 483 | def _compute_expert_id_per_block( | CODE |
| LOW | python/mlc_llm/op/triton.py | 515 | def tir_compute_expert_id_per_block( | CODE |
| LOW | python/mlc_llm/op/moe_misc.py | 36 | def _gating_topk_init_local_top_k(k_val, dtype, local_top_k, local_top_k_index): | CODE |
| LOW | python/mlc_llm/op/moe_misc.py | 43 | def _gating_topk_process_value(k_val, x, local_top_k, local_top_k_index, vi, vk): | CODE |
| LOW | python/mlc_llm/op/moe_misc.py | 161 | def _get_topk_softmax_norm_func(k_val: int): | CODE |
| LOW | python/mlc_llm/op/moe_misc.py | 235 | def group_limited_greedy_topk( | CODE |
| LOW | python/mlc_llm/op/moe_misc.py | 303 | def group_limited_mask_scores( | CODE |
| LOW | python/mlc_llm/op/mrope.py | 30 | def _split_indices_from_sizes(sizes: Sequence[int]) -> List[int]: # noqa: UP006 | CODE |
| LOW | python/mlc_llm/op/mrope.py | 123 | def apply_multimodal_rotary_pos_emb( | CODE |
| LOW | python/mlc_llm/op/mrope.py | 263 | def _build_sequence_position_ids( | CODE |
| LOW | python/mlc_llm/op/ft_gemm.py | 11 | def faster_transformer_dequantize_gemm( | CODE |
| LOW | python/mlc_llm/op/ft_gemm.py | 95 | def faster_transformer_moe_gemm( | CODE |
| LOW | python/mlc_llm/compiler_pass/fuse_add_norm.py | 86 | def _get_add_rms_norm_prefill(hidden_size: int, eps: float, TX: int, in_dtype: str): | CODE |
| LOW | python/mlc_llm/compiler_pass/attach_logit_processor.py | 42 | def _get_apply_logit_bias_inplace_cpu(): | CODE |
| LOW | python/mlc_llm/compiler_pass/attach_logit_processor.py | 48 | def _apply_logit_bias_inplace( | CODE |
| LOW | python/mlc_llm/compiler_pass/attach_logit_processor.py | 69 | def _get_apply_logit_bias_inplace(target: tvm.target.Target): | CODE |
| LOW | python/mlc_llm/compiler_pass/attach_logit_processor.py | 80 | def _apply_logit_bias_inplace( | CODE |
| LOW | python/mlc_llm/compiler_pass/attach_logit_processor.py | 105 | def _get_apply_penalty_inplace_cpu(): | CODE |
| LOW | python/mlc_llm/compiler_pass/attach_logit_processor.py | 143 | def _get_apply_penalty_inplace(target: tvm.target.Target): | CODE |
| LOW | python/mlc_llm/compiler_pass/attach_logit_processor.py | 191 | def _get_apply_bitmask_inplace_cpu(): | CODE |
| LOW | python/mlc_llm/compiler_pass/attach_logit_processor.py | 224 | def _get_apply_bitmask_inplace(target: tvm.target.Target): | CODE |
| LOW | python/mlc_llm/compiler_pass/attach_sampler.py | 70 | def _attach_multinomial_sampling_func(bb: relax.BlockBuilder): | CODE |
| LOW | python/mlc_llm/compiler_pass/attach_sampler.py | 153 | def _attach_sample_with_top_p(bb: relax.BlockBuilder): | CODE |
| LOW | python/mlc_llm/compiler_pass/attach_sampler.py | 231 | def _attach_renormalize_by_top_p(bb: relax.BlockBuilder, target: tvm.target.Target): | CODE |
| LOW | …/mlc_llm/compiler_pass/attach_spec_decode_aux_funcs.py | 79 | def _add_scatter_hidden_states(bb: BlockBuilder, tensor_parallel_shards: int, dtype: str): | CODE |
| LOW | …/mlc_llm/compiler_pass/attach_spec_decode_aux_funcs.py | 105 | def _add_gather_hidden_states(bb: BlockBuilder, tensor_parallel_shards: int, dtype: str): | CODE |
| LOW | …c_llm/compiler_pass/attach_softmax_with_temperature.py | 102 | def _get_lse_and_softmax_func(target: tvm.target.Target, chunk_size: int, active_vocab_size: int): | CODE |
| LOW | …hon/mlc_llm/compiler_pass/pipeline_parallel_rewrite.py | 250 | def _prepare_stage_func_params_and_args( | CODE |
| LOW | …hon/mlc_llm/compiler_pass/pipeline_parallel_rewrite.py | 373 | def _analyze_required_func_params( | CODE |
| LOW | …on/mlc_llm/compiler_pass/dispatch_kv_cache_creation.py | 153 | def create_tir_paged_kv_cache( | CODE |
| LOW | …on/mlc_llm/compiler_pass/dispatch_kv_cache_creation.py | 191 | def create_flashinfer_paged_kv_cache( | CODE |
| LOW | python/mlc_llm/protocol/conversation_protocol.py | 247 | def _strip_reasoning_in_history( | CODE |
| LOW | python/mlc_llm/protocol/conversation_protocol.py | 273 | def _combine_consecutive_messages(messages: List[Any]) -> List[Any]: # noqa: UP006 | CODE |
| LOW | python/mlc_llm/protocol/mlc_chat_config.py | 65 | def get_system_defaults_for_missing_fields(self) -> Dict[str, Any]: # noqa: UP006 | CODE |
| LOW | python/mlc_llm/protocol/artifact_manifest.py | 145 | def _validate_parameter_schema_id(cls, value: str) -> str: | CODE |
| LOW | python/mlc_llm/protocol/artifact_manifest.py | 211 | def _omit_empty_adapter_dtypes(self, handler: SerializerFunctionWrapHandler): | CODE |
| LOW | python/mlc_llm/protocol/artifact_manifest.py | 220 | def _validate_token_generation_roles(self): | CODE |
| LOW | python/mlc_llm/protocol/artifact_manifest.py | 342 | def compute_parameter_schema_id(named_parameters: Iterable[tuple[str, Any]]) -> str: | CODE |
| LOW | python/mlc_llm/protocol/artifact_manifest.py | 366 | def build_model_package_manifest( | CODE |
| LOW | python/mlc_llm/protocol/artifact_manifest.py | 382 | def build_compiled_program_artifact( | CODE |
| LOW | python/mlc_llm/protocol/artifact_manifest.py | 420 | def dump_model_package_manifest(manifest: ModelPackageManifest, output: Path) -> Path: | CODE |
| LOW | python/mlc_llm/protocol/openai_api_protocol.py | 366 | def check_function_call_usage(self, conv_template: Conversation) -> None: | CODE |
| LOW | python/mlc_llm/protocol/openai_api_protocol.py | 450 | def openai_api_get_unsupported_fields( | CODE |
| LOW | python/mlc_llm/protocol/error_protocol.py | 33 | async def bad_request_error_handler(_request: fastapi.Request, e: BadRequestError): | CODE |
| LOW | python/mlc_llm/cli/package.py | 26 | def _parse_mlc_llm_source_dir(path: str) -> Path: | CODE |
| 194 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | version.py | 16 | # --------------------------------------------------- | COMMENT |
| MEDIUM | version.py | 27 | # --------------------------------------------------- | COMMENT |
| MEDIUM | python/mlc_llm/op/triton.py | 174 | # ----------------------------------------------------------- | COMMENT |
| MEDIUM | python/mlc_llm/op/triton.py | 187 | # ---------------------------------------------------------- | COMMENT |
| MEDIUM | python/mlc_llm/op/triton.py | 219 | # ----------------------------------------------------------- | COMMENT |
| MEDIUM | python/mlc_llm/op/triton.py | 262 | # ----------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | python/mlc_llm/model/qwen35/qwen35_model.py | 217 | # ============================================================================ | COMMENT |
| MEDIUM⚡ | python/mlc_llm/model/qwen35/qwen35_model.py | 219 | # ============================================================================ | COMMENT |
| MEDIUM | python/mlc_llm/model/qwen35/qwen35_model.py | 359 | # ============================================================================ | COMMENT |
| MEDIUM | python/mlc_llm/model/qwen35/qwen35_model.py | 361 | # ============================================================================ | COMMENT |
| MEDIUM | python/mlc_llm/model/qwen35/qwen35_model.py | 587 | # ============================================================================ | COMMENT |
| MEDIUM | python/mlc_llm/model/qwen35/qwen35_model.py | 589 | # ============================================================================ | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 65 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 67 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 76 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 78 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 94 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 96 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 114 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 116 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 147 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 149 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 169 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 171 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 183 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 185 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 222 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_embedding_engine.py | 224 | # =================================================================== | COMMENT |
| MEDIUM | tests/python/serve/test_embedding_engine.py | 26 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | tests/python/serve/test_embedding_engine.py | 28 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | tests/python/serve/test_embedding_engine.py | 204 | # =================================================================== | COMMENT |
| MEDIUM | tests/python/serve/test_embedding_engine.py | 206 | # =================================================================== | COMMENT |
| MEDIUM | tests/python/serve/test_embedding_engine.py | 334 | # =================================================================== | COMMENT |
| MEDIUM | tests/python/serve/test_embedding_engine.py | 336 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/server/test_embedding_server.py | 217 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/server/test_embedding_server.py | 219 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/server/test_embedding_server.py | 229 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/server/test_embedding_server.py | 231 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/server/test_embedding_server.py | 254 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/server/test_embedding_server.py | 256 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/server/test_embedding_server.py | 277 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/server/test_embedding_server.py | 279 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/server/test_embedding_server.py | 322 | # =================================================================== | COMMENT |
| MEDIUM⚡ | tests/python/serve/server/test_embedding_server.py | 324 | # =================================================================== | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 39 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 41 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 66 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 68 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 121 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 123 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 203 | # =================================================================== | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 205 | # =================================================================== | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 297 | # =================================================================== | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 299 | # =================================================================== | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 344 | # =================================================================== | COMMENT |
| MEDIUM | tests/python/serve/server/test_embedding_server.py | 346 | # =================================================================== | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH⚡ | examples/rest/nodejs/sample_client.js | 28 | print('\n'); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_client.js | 32 | print(color.BOLD + "Without streaming:" + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_client.js | 37 | print(color.GREEN + r.body.choices[0].message.content + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_client.js | 38 | print('\n'); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_client.js | 41 | print(color.BOLD + "Reset chat" + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_client.js | 52 | print( color.BOLD + "With streaming:" + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_client.js | 62 | print(color.GREEN + jsData.choices[0].delta.content + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_client.js | 68 | print(color.BOLD + "Runtime stats:" + color.END + txtresp.body); | CODE |
| HIGH | examples/rest/nodejs/sample_langchain.ts | 26 | print('\n'); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_langchain.ts | 51 | print(color.BOLD + input + "..." + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_langchain.ts | 55 | print(color.GREEN + res.text + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_langchain.ts | 58 | print(color.BOLD + input + "..." + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_langchain.ts | 62 | print(color.GREEN + res.text + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_langchain.ts | 71 | print(color.BOLD + "Query: " + color.END + color.BLUE + query + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_langchain.ts | 74 | print(color.BOLD + "Response: " + color.END + color.GREEN + result.text + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_openai.js | 32 | print('\n'); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_openai.js | 37 | print(color.BOLD + "OpenAI chat completion example without streaming:" + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_openai.js | 46 | print(color.GREEN + completion.data.choices[0].message.content + color.END) | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_openai.js | 53 | print(color.BOLD + "OpenAI chat completion example with streaming:" + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_openai.js | 63 | print(color.GREEN + parsed.choices[0].delta.content + color.END); | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_openai.js | 70 | print(color.BOLD + "OpenAI completion example:" + color.END) | CODE |
| HIGH⚡ | examples/rest/nodejs/sample_openai.js | 73 | print(color.GREEN + res.data.choices[0].text + color.END); | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/mlc_llm/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/__init__.py | 9 | CODE | |
| LOW | python/mlc_llm/__init__.py | 10 | CODE | |
| LOW | python/mlc_llm/__init__.py | 10 | CODE | |
| LOW | python/mlc_llm/tokenizers/__init__.py | 3 | CODE | |
| LOW | python/mlc_llm/tokenizers/__init__.py | 3 | CODE | |
| LOW | python/mlc_llm/tokenizers/__init__.py | 4 | CODE | |
| LOW | python/mlc_llm/json_ffi/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/nn/__init__.py | 3 | CODE | |
| LOW | python/mlc_llm/nn/__init__.py | 4 | CODE | |
| LOW | python/mlc_llm/nn/__init__.py | 4 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/conversation_template/__init__.py | 38 | CODE | |
| LOW | python/mlc_llm/op/mrope.py | 3 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 3 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 3 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 4 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 5 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 6 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 6 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 6 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 7 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 8 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 14 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 15 | CODE | |
| LOW | python/mlc_llm/op/__init__.py | 15 | CODE | |
| LOW | python/mlc_llm/compiler_pass/blas_dispatch.py | 8 | CODE | |
| LOW | python/mlc_llm/compiler_pass/blas_dispatch.py | 9 | CODE | |
| LOW | python/mlc_llm/compiler_pass/__init__.py | 3 | CODE | |
| 71 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | version.py | 123 | CODE | |
| LOW | python/setup.py | 87 | CODE | |
| LOW | python/mlc_llm/__main__.py | 11 | CODE | |
| LOW | python/mlc_llm/json_ffi/engine.py | 38 | CODE | |
| LOW | python/mlc_llm/bench/dataset.py | 283 | CODE | |
| LOW | python/mlc_llm/bench/dataset.py | 735 | CODE | |
| LOW | python/mlc_llm/bench/evaluation/mmlu.py | 128 | CODE | |
| LOW | python/mlc_llm/interface/gen_config.py | 93 | CODE | |
| LOW | python/mlc_llm/interface/chat.py | 249 | CODE | |
| LOW | python/mlc_llm/op/moe_misc.py | 64 | CODE | |
| LOW | python/mlc_llm/op/moe_misc.py | 134 | CODE | |
| LOW | python/mlc_llm/op/moe_misc.py | 438 | CODE | |
| LOW | python/mlc_llm/op/moe_misc.py | 88 | CODE | |
| LOW | python/mlc_llm/op/moe_misc.py | 161 | CODE | |
| LOW | python/mlc_llm/op/moe_misc.py | 481 | CODE | |
| LOW | python/mlc_llm/op/moe_misc.py | 92 | CODE | |
| LOW | python/mlc_llm/op/moe_misc.py | 177 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 13 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 78 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 180 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 299 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 386 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 560 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 51 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 149 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 238 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 262 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 352 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 426 | CODE | |
| LOW | python/mlc_llm/op/moe_matmul.py | 633 | CODE | |
| LOW | python/mlc_llm/op/batch_spec_verify.py | 9 | CODE | |
| LOW | python/mlc_llm/op/batch_spec_verify.py | 63 | CODE | |
| LOW | python/mlc_llm/op/top_p_pivot.py | 12 | CODE | |
| LOW | python/mlc_llm/op/top_p_pivot.py | 265 | CODE | |
| LOW | python/mlc_llm/op/top_p_pivot.py | 57 | CODE | |
| LOW | python/mlc_llm/op/top_p_pivot.py | 301 | CODE | |
| LOW | python/mlc_llm/op/cutlass.py | 9 | CODE | |
| LOW | python/mlc_llm/compiler_pass/fuse_add_norm.py | 15 | CODE | |
| LOW | python/mlc_llm/compiler_pass/fuse_add_norm.py | 86 | CODE | |
| LOW | python/mlc_llm/compiler_pass/fuse_add_norm.py | 25 | CODE | |
| LOW | python/mlc_llm/compiler_pass/fuse_add_norm.py | 96 | CODE | |
| LOW | …thon/mlc_llm/compiler_pass/lift_global_buffer_alloc.py | 153 | CODE | |
| LOW | …hon/mlc_llm/compiler_pass/pipeline_parallel_rewrite.py | 36 | CODE | |
| LOW | …hon/mlc_llm/compiler_pass/pipeline_parallel_rewrite.py | 106 | CODE | |
| LOW | python/mlc_llm/protocol/conversation_protocol.py | 122 | CODE | |
| LOW | python/mlc_llm/protocol/artifact_manifest.py | 347 | CODE | |
| LOW | python/mlc_llm/cli/delivery.py | 219 | CODE | |
| LOW | python/mlc_llm/cli/lib_delivery.py | 122 | CODE | |
| LOW | python/mlc_llm/cli/model_metadata.py | 88 | CODE | |
| LOW | python/mlc_llm/quantization/ft_quantization.py | 170 | CODE | |
| LOW | python/mlc_llm/testing/debug_chat.py | 98 | CODE | |
| LOW | python/mlc_llm/support/auto_device.py | 24 | CODE | |
| LOW | python/mlc_llm/support/auto_device.py | 52 | CODE | |
| LOW | python/mlc_llm/support/download_cache.py | 127 | CODE | |
| LOW | python/mlc_llm/loader/huggingface_loader.py | 208 | CODE | |
| LOW | python/mlc_llm/loader/huggingface_loader.py | 102 | CODE | |
| LOW | python/mlc_llm/loader/utils.py | 55 | CODE | |
| LOW | python/mlc_llm/loader/standard_loader.py | 23 | CODE | |
| LOW | python/mlc_llm/loader/standard_loader.py | 69 | CODE | |
| LOW | python/mlc_llm/model/qwen35/qwen35v_loader.py | 26 | CODE | |
| 49 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/mlc_llm/bench/request_processor.py | 27 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/bench/api_endpoint.py | 15 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/bench/__main__.py | 31 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/bench/request_record.py | 11 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/interface/package.py | 16 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/interface/compiler_flags.py | 11 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/interface/jit.py | 30 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/interface/gen_config.py | 25 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/interface/serve.py | 21 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/interface/compile.py | 25 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/interface/convert_weight.py | 33 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/op/attention.py | 13 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/compiler_pass/dispatch_triton_kernel.py | 15 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/compiler_pass/estimate_memory_usage.py | 13 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/compiler_pass/pipeline.py | 45 | logger = logging.getLogger(__name__) | CODE |
| LOW | …on/mlc_llm/compiler_pass/dispatch_kv_cache_creation.py | 13 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/cli/delivery.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/cli/lib_delivery.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/cli/model_metadata.py | 16 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/contrib/embeddings/openai.py | 15 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/quantization/group_quantization.py | 24 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/quantization/per_tensor_quantization.py | 27 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/quantization/ft_quantization.py | 25 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/quantization/block_scale_quantization.py | 20 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/support/config.py | 21 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/support/config.py | 111 | __all__ = ["ConfigBase", "ConfigOverrideBase"] | CODE |
| LOW | python/mlc_llm/support/auto_config.py | 16 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/support/auto_device.py | 21 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/support/auto_weight.py | 10 | logger = logging.getLogger(__name__) | CODE |
| LOW⚡ | python/mlc_llm/support/download_cache.py | 24 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/support/tqdm.py | 39 | __all__ = ["redirect", "tqdm"] | CODE |
| LOW | python/mlc_llm/support/auto_target.py | 22 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/loader/huggingface_loader.py | 23 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/loader/huggingface_loader.py | 231 | __all__ = ["HuggingFaceLoader"] | CODE |
| LOW | python/mlc_llm/loader/utils.py | 17 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/loader/stats.py | 10 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/loader/mapping.py | 102 | __all__ = ["ExternMapping", "QuantizeMapping"] | CODE |
| LOW | python/mlc_llm/model/qwen35/qwen35_model.py | 26 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/llama4/llama4_model.py | 23 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/ministral3/ministral3_model.py | 22 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/cohere/cohere_model.py | 20 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/starcoder2/starcoder2_model.py | 20 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/gemma/gemma_model.py | 18 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/olmo2/olmo2_model.py | 21 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/internlm/internlm_model.py | 20 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/gpt_neox/gpt_neox_model.py | 20 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/gemma2/gemma2_model.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/mixtral/mixtral_model.py | 21 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/olmo/olmo_model.py | 22 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/phi3/phi3_model.py | 20 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/gemma3/gemma3v_model.py | 20 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/gemma3/gemma3_model.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/gemma4/gemma4_config.py | 11 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/gemma4/__init__.py | 6 | __all__ = [ | CODE |
| LOW | python/mlc_llm/model/gemma4/gemma4_loader.py | 131 | __all__ = ["huggingface"] | CODE |
| LOW | python/mlc_llm/model/gemma4/gemma4_model.py | 643 | __all__ = [ | CODE |
| LOW | python/mlc_llm/model/gemma4/gemma4_audio.py | 450 | __all__ = [ | CODE |
| LOW | python/mlc_llm/model/qwen2/qwen2_model.py | 21 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/minicpm/minicpm_model.py | 23 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/mlc_llm/model/stable_lm/stablelm_model.py | 20 | logger = logging.getLogger(__name__) | CODE |
| 31 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | python/setup.py | 76 | """This class is needed in order to create OS specific wheels.""" | STRING |
| MEDIUM | python/mlc_llm/json_ffi/engine.py | 84 | # Create the background engine-driving thread and start the loop. | COMMENT |
| MEDIUM | python/mlc_llm/bench/request_processor.py | 85 | # Create a new list so that the in-place shuffle does not mutate the input list. | COMMENT |
| MEDIUM | python/mlc_llm/bench/request_processor.py | 109 | # Create a new list so that the in-place shuffle does not mutate the input list. | COMMENT |
| MEDIUM | python/mlc_llm/bench/dataset.py | 254 | # Create a dummy ChatCompletionRequest. | COMMENT |
| MEDIUM | python/mlc_llm/bench/dataset.py | 576 | # Create a dummy ChatCompletionRequest. | STRING |
| MEDIUM | …hon/mlc_llm/compiler_pass/pipeline_parallel_rewrite.py | 165 | # Create the param for the shape variables. | COMMENT |
| MEDIUM | python/mlc_llm/cli/router.py | 11 | # Define a custom argument type for a list of strings | COMMENT |
| MEDIUM | python/mlc_llm/serve/sync_engine.py | 236 | # Define the callback function for request generation results | COMMENT |
| MEDIUM⚡ | python/mlc_llm/serve/engine.py | 1343 | # Create the request with the given id, input data, generation | COMMENT |
| MEDIUM⚡ | python/mlc_llm/serve/engine.py | 1350 | # Create the unique async request stream of the request. | COMMENT |
| MEDIUM | python/mlc_llm/serve/engine.py | 1867 | # Create the request with the given id, input data, generation | COMMENT |
| MEDIUM | tests/python/serve/test_serve_engine_spec.py | 77 | # Define the callback function for request generation results | COMMENT |
| MEDIUM | tests/python/serve/test_serve_engine_spec.py | 141 | # Define the callback function for request generation results | COMMENT |
| MEDIUM | tests/python/serve/test_serve_engine_spec.py | 213 | # Define the callback class for request generation results | COMMENT |
| MEDIUM | tests/python/serve/test_serve_engine_spec.py | 295 | # Define the callback class for request generation results | COMMENT |
| MEDIUM | tests/python/serve/test_serve_engine_spec.py | 477 | # Define the callback function for request generation results | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_serve_engine_spec.py | 536 | # Define the callback function for request generation results | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_serve_engine_spec.py | 602 | # Define the callback function for request generation results | COMMENT |
| MEDIUM | tests/python/serve/test_serve_sync_engine.py | 75 | # Define the callback function for request generation results | COMMENT |
| MEDIUM | tests/python/serve/test_serve_sync_engine.py | 137 | # Define the callback class for request generation results | COMMENT |
| MEDIUM | tests/python/serve/test_serve_sync_engine.py | 217 | # Define the callback class for request generation results | COMMENT |
| MEDIUM | tests/python/serve/test_serve_sync_engine.py | 297 | # Define the callback class for request generation results | COMMENT |
| MEDIUM | tests/python/serve/test_serve_sync_engine.py | 409 | # Define the callback class for request generation results | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | python/mlc_llm/bench/__main__.py | 125 | except Exception: | CODE |
| HIGH | python/mlc_llm/compiler_pass/blas_dispatch.py | 10 | except ImportError: | CODE |
| HIGH | python/mlc_llm/cli/worker.py | 56 | except (OSError, KeyboardInterrupt): | CODE |
| HIGH | python/mlc_llm/contrib/embeddings/openai.py | 73 | except ImportError: | CODE |
| HIGH | python/mlc_llm/contrib/embeddings/openai.py | 99 | except ImportError: | CODE |
| HIGH | python/mlc_llm/serve/server/popen_server.py | 183 | except OSError: | CODE |
| HIGH | python/mlc_llm/serve/server/popen_server.py | 189 | except subprocess.TimeoutExpired: | CODE |
| HIGH | python/mlc_llm/serve/server/popen_server.py | 175 | except psutil.NoSuchProcess: | CODE |
| HIGH | tests/python/serve/server/test_embedding_server.py | 176 | except requests.RequestException: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | tests/python/serve/test_serve_engine_spec.py | 67 | # Hyperparameters for tests (you can try different combinations). | COMMENT |
| MEDIUM | tests/python/serve/test_serve_engine_spec.py | 131 | # Hyperparameters for tests (you can try different combinations). | COMMENT |
| MEDIUM | tests/python/serve/test_serve_engine_spec.py | 201 | # Hyperparameters for tests (you can try different combinations) | COMMENT |
| MEDIUM | tests/python/serve/test_serve_engine_spec.py | 283 | # Hyperparameters for tests (you can try different combinations) | COMMENT |
| MEDIUM | tests/python/serve/test_serve_engine_spec.py | 467 | # Hyperparameters for tests (you can try different combinations). | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_serve_engine_spec.py | 526 | # Hyperparameters for tests (you can try different combinations). | COMMENT |
| MEDIUM⚡ | tests/python/serve/test_serve_engine_spec.py | 592 | # Hyperparameters for tests (you can try different combinations). | COMMENT |
| MEDIUM | tests/python/serve/test_serve_sync_engine.py | 65 | # Hyperparameters for tests (you can try different combinations). | COMMENT |
| MEDIUM | tests/python/serve/test_serve_sync_engine.py | 125 | # Hyperparameters for tests (you can try different combinations) | COMMENT |
| MEDIUM | tests/python/serve/test_serve_sync_engine.py | 205 | # Hyperparameters for tests (you can try different combinations) | COMMENT |
| MEDIUM | tests/python/serve/test_serve_sync_engine.py | 284 | # Hyperparameters for tests (you can try different combinations) | COMMENT |
| MEDIUM | tests/python/serve/test_serve_sync_engine.py | 398 | # Hyperparameters for tests (you can try different combinations) | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/mlc_llm/json_ffi/engine.py | 117 | CODE | |
| LOW | python/mlc_llm/nn/kv_cache.py | 18 | CODE | |
| LOW | python/mlc_llm/nn/rnn_state.py | 73 | CODE | |
| LOW | python/mlc_llm/op/attention.py | 100 | CODE | |
| LOW | python/mlc_llm/compiler_pass/pipeline.py | 82 | CODE | |
| LOW | python/mlc_llm/contrib/embeddings/embeddings.py | 173 | CODE | |
| LOW | python/mlc_llm/quantization/model_quantization.py | 20 | CODE | |
| LOW | python/mlc_llm/loader/standard_loader.py | 23 | CODE | |
| LOW | python/mlc_llm/model/vision/image_processing.py | 91 | CODE | |
| LOW | python/mlc_llm/model/vision/image_processing.py | 150 | CODE | |
| LOW | python/mlc_llm/model/vision/image_processing.py | 194 | CODE | |
| LOW | python/mlc_llm/model/vision/image_processing.py | 250 | CODE | |
| LOW | python/mlc_llm/model/vision/image_processing.py | 325 | CODE | |
| LOW | python/mlc_llm/model/chatglm3/chatglm3_model.py | 162 | CODE | |
| LOW | python/mlc_llm/model/phi3v/phi3v_image.py | 121 | CODE | |
| LOW | python/mlc_llm/model/phi3v/phi3v_image.py | 166 | CODE | |
| LOW | python/mlc_llm/model/phi3v/phi3v_image.py | 205 | CODE | |
| LOW | python/mlc_llm/model/bert/bert_model.py | 110 | CODE | |
| LOW | python/mlc_llm/model/nemotron/nemotron_model.py | 91 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 58 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 113 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 167 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 252 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 307 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 359 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 444 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 499 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 551 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 636 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 691 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 743 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 911 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 1053 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 1483 | CODE | |
| LOW | python/mlc_llm/serve/engine.py | 1615 | CODE | |
| LOW | python/mlc_llm/serve/engine_base.py | 1151 | CODE | |
| LOW | python/mlc_llm/serve/server/popen_server.py | 25 | CODE | |
| LOW | python/mlc_llm/serve/entrypoints/debug_entrypoints.py | 102 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …on/mlc_llm/compiler_pass/dispatch_kv_cache_creation.py | 30 | # Check if attn_kind is a single value or a list with length of hidden layers | COMMENT |
| LOW | python/mlc_llm/serve/embedding_engine.py | 128 | # Check if the post-processor actually appends a special token at the end | COMMENT |
| LOW | python/mlc_llm/serve/server/popen_server.py | 147 | # Check if the subprocess terminates unexpectedly or | COMMENT |
| LOW | tests/python/json_ffi/test_json_ffi_engine_image.py | 62 | # Print output. | COMMENT |
| LOW | tests/python/json_ffi/test_json_ffi_engine.py | 81 | # Print output. | COMMENT |
| LOW | tests/python/json_ffi/test_json_ffi_engine.py | 140 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_engine_rnn.py | 45 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_engine.py | 46 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_engine.py | 91 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_engine.py | 135 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_engine.py | 179 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_engine.py | 222 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_async_engine_spec.py | 69 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_async_engine.py | 66 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_async_engine.py | 117 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_async_engine.py | 167 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_async_engine.py | 217 | # Print output. | COMMENT |
| LOW | tests/python/serve/test_serve_async_engine.py | 266 | # Print output. | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | .pre-commit-config.yaml | 1 | # To use: | COMMENT |
| LOW | pyproject.toml | 1 | # Licensed to the Apache Software Foundation (ASF) under one | COMMENT |
| LOW | python/mlc_llm/interface/router.py | 81 | output_texts = [""] * request.n | COMMENT |
| LOW | …c_llm/compiler_pass/attach_softmax_with_temperature.py | 101 | COMMENT | |
| LOW | python/mlc_llm/protocol/conversation_protocol.py | 61 | # The conversation history messages. | COMMENT |
| LOW | python/mlc_llm/cli/worker.py | 1 | # Licensed to the Apache Software Foundation (ASF) under one | COMMENT |
| LOW | python/mlc_llm/cli/disco_remote_socket_session.py | 1 | # Licensed to the Apache Software Foundation (ASF) under one | COMMENT |
| LOW | python/mlc_llm/model/model_preset.py | 1581 | # "architectures": ["BertModel"], | COMMENT |
| LOW | python/mlc_llm/model/model_preset.py | 1981 | "vocab_size": 49152, | COMMENT |
| LOW | python/mlc_llm/model/model_preset.py | 2001 | # "rms_norm_eps": 1e-05, | COMMENT |
| LOW | tests/python/conftest.py | 1 | # Licensed to the Apache Software Foundation (ASF) under one | COMMENT |
| LOW | ios/MLCSwift/Sources/ObjC/LLMEngine.mm | 1 | // | COMMENT |
| LOW | …gineExample/MLCEngineExample/MLCEngineExampleApp.swift | 1 | // This is a minimum example App to interact with MLC Engine | COMMENT |
| LOW | cpp/base.h | 1 | /*! | COMMENT |
| LOW | cpp/tokenizers/tokenizers.h | 1 | /*! | COMMENT |
| LOW | cpp/json_ffi/openai_api_protocol.h | 1 | /*! | COMMENT |
| LOW | cpp/json_ffi/conv_template.h | 1 | #ifndef MLC_LLM_JSON_FFI_CONV_TEMPLATE_H | COMMENT |
| LOW | cpp/serve/config.h | 1 | /*! | COMMENT |
| LOW | cpp/serve/data.h | 1 | /*! | COMMENT |
| LOW | cpp/serve/model.h | 1 | /*! | COMMENT |
| LOW | cpp/serve/prefix_cache.h | 1 | /*! | COMMENT |
| LOW | cpp/serve/request_state.h | 1 | /*! | COMMENT |
| LOW | cpp/serve/function_table.h | 1 | /*! | COMMENT |
| LOW | examples/rest/python/sample_langchain.py | 161 | COMMENT | |
| LOW | android/mlc4j/src/cpp/tvm_runtime.h | 1 | #define TVM_USE_LIBBACKTRACE 0 | COMMENT |
| LOW | android/mlc4j/src/cpp/tvm_runtime.h | 21 | #include <runtime/cpu_device_api.cc> | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/mlc_llm/json_ffi/engine.py | 70 | except Exception as exception: | CODE |
| LOW | python/mlc_llm/bench/api_endpoint.py | 139 | except Exception: | CODE |
| LOW | python/mlc_llm/bench/api_endpoint.py | 269 | except Exception: | CODE |
| LOW | python/mlc_llm/bench/api_endpoint.py | 383 | except Exception: | CODE |
| LOW | python/mlc_llm/bench/__main__.py | 125 | except Exception: | CODE |
| LOW | python/mlc_llm/interface/gen_config.py | 216 | except Exception: | CODE |
| LOW | python/mlc_llm/interface/gen_config.py | 238 | except Exception: | CODE |
| LOW | python/mlc_llm/interface/gen_config.py | 285 | except Exception: | CODE |
| LOW | …on/mlc_llm/compiler_pass/dispatch_kv_cache_creation.py | 238 | except Exception as e: | CODE |
| LOW | python/mlc_llm/cli/delivery.py | 198 | except Exception as exc: | CODE |
| LOW | python/mlc_llm/cli/check_device.py | 13 | except Exception: | CODE |
| LOW | python/mlc_llm/cli/model_metadata.py | 175 | except Exception: | STRING |
| LOW | python/mlc_llm/support/auto_device.py | 40 | except Exception as err: | CODE |
| LOW | python/mlc_llm/support/auto_target.py | 119 | except Exception as err: | CODE |
| LOW | python/mlc_llm/serve/engine.py | 1034 | except Exception as err: | CODE |
| LOW | python/mlc_llm/serve/engine.py | 1233 | except Exception as err: | CODE |
| LOW | python/mlc_llm/serve/engine.py | 1305 | except Exception as err: | CODE |
| LOW | python/mlc_llm/serve/engine.py | 1381 | except Exception as exception: | CODE |
| LOW | python/mlc_llm/serve/server/popen_server.py | 143 | except Exception: | CODE |
| LOW | python/mlc_llm/serve/entrypoints/openai_entrypoints.py | 78 | except Exception as exc: | CODE |
| LOW | python/mlc_llm/router/router.py | 304 | except Exception as e: | CODE |
| LOW | tests/python/integration/test_model_compile.py | 147 | except Exception: | CODE |
| LOW | scripts/check_url_validity.py | 36 | except Exception as e: | CODE |
| MEDIUM | scripts/check_url_validity.py | 37 | print(f"Error connecting {url}, error: {e}") | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 200 | # Step 1: Preprocess | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 203 | # Step 2: Cast to model dtype | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 206 | # Step 3: Vision encoder -> (1, 4096, 1152) | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 209 | # Step 4: Reshape for average pooling | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 216 | # Step 5: AvgPool2d(4,4) -> (1, 1152, 16, 16) | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 219 | # Step 6: Reshape back to sequence format | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 225 | # Step 7: Multimodal projector (RMSNorm + Linear) | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 228 | # Step 8: Compensate for Gemma's embedding scaling. | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 235 | # Step 9: Reshape to 2D for C++ runtime (requires ndim == 2) | COMMENT |
| LOW | python/mlc_llm/serve/engine_base.py | 486 | # NOTE: This function causes GIL during execution. | COMMENT |
| LOW | …gineExample/MLCEngineExample/MLCEngineExampleApp.swift | 35 | // Step 0: load the engine | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 200 | # Step 1: Preprocess | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 203 | # Step 2: Cast to model dtype | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 206 | # Step 3: Vision encoder -> (1, 4096, 1152) | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 209 | # Step 4: Reshape for average pooling | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 216 | # Step 5: AvgPool2d(4,4) -> (1, 1152, 16, 16) | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 219 | # Step 6: Reshape back to sequence format | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 225 | # Step 7: Multimodal projector (RMSNorm + Linear) | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 228 | # Step 8: Compensate for Gemma's embedding scaling. | COMMENT |
| LOW⚡ | python/mlc_llm/model/gemma3/gemma3v_model.py | 235 | # Step 9: Reshape to 2D for C++ runtime (requires ndim == 2) | COMMENT |
| LOW | …gineExample/MLCEngineExample/MLCEngineExampleApp.swift | 35 | // Step 0: load the engine | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH⚡ | python/mlc_llm/serve/engine.py | 1354 | stream.push( | CODE |
| HIGH | python/mlc_llm/serve/engine_base.py | 518 | stream.push([output]) | CODE |
| HIGH | python/mlc_llm/serve/engine_base.py | 545 | stream.push(outputs) | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | python/mlc_llm/interface/serve.py | 89 | # Set up embedding model if specified | COMMENT |
| MEDIUM | python/mlc_llm/cli/model_metadata.py | 99 | # Compute KV cache size per token of context window. | COMMENT |
| MEDIUM | python/mlc_llm/model/gemma2/gemma2_model.py | 37 | # NOTE: override the context window size with the Gemma2 sliding window size, | COMMENT |
| MEDIUM | python/mlc_llm/model/gemma3/gemma3_model.py | 91 | # NOTE: override the context window size with the Gemma2 sliding window size, | COMMENT |
| MEDIUM | python/mlc_llm/model/rwkv5/rwkv5_model.py | 43 | context_window_size: int = -1 # RWKV does not have context window limitation. | CODE |
| MEDIUM | python/mlc_llm/model/rwkv6/rwkv6_model.py | 43 | context_window_size: int = -1 # RWKV does not have context window limitation. | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | version.py | 90 | # Remove the v prefix, mainly to be robust | COMMENT |
| MEDIUM | python/setup.py | 76 | """This class is needed in order to create OS specific wheels.""" | STRING |
| MEDIUM | python/mlc_llm/interface/chat.py | 173 | # TODO(mlc-team): possibly leverage debug option | COMMENT |
| LOW | python/mlc_llm/serve/engine.py | 1032 | # for cancelled error, we can simply pass it through | COMMENT |
| LOW | python/mlc_llm/serve/engine.py | 1231 | # for cancelled error, we can simply pass it through | COMMENT |
| LOW | python/mlc_llm/serve/engine.py | 1303 | # for cancelled error, we can simply pass it through | COMMENT |
| LOW | python/mlc_llm/serve/engine.py | 1379 | # for cancelled error, we can simply pass it through | COMMENT |