Long Video Gen / World Model / World Action Model (Embodied) Infrastructure
This report summarizes scanner evidence for NVlabs/LongLive, a Python project with 2,745 GitHub stars. SynthScan examined 725,107 lines of code across 1638 source files, recording 4150 pattern matches distributed across 20 syntactic categories. The legacy adjusted pattern signal is 9.9 (Moderate pattern signal); it is not an authorship estimate.
Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.
Use each vector to guide manual verification of the underlying findings.
Can maintainers explain intent, assumptions, and trade-offs? 2601 finding(s).
Are imports declared and package/API names verified? 476 finding(s).
Are wrappers, guards, and repeated structures necessary? 2061 finding(s).
Which changes need focused human review? 4150 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 4150 distinct pattern matches across 20 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.
Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | …_party/LongLive/pipeline/causal_diffusion_inference.py | 0 | initialize a per-gpu cross-attention cache for the wan model. | STRING |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 0 | initialize a per-gpu cross-attention cache for the wan model. | STRING |
| HIGH | LongLive1.0/pipeline/streaming_training.py | 0 | initialize a per-gpu cross-attention cache for the wan model. | STRING |
| HIGH | LongLive1.0/pipeline/causal_inference.py | 0 | initialize a per-gpu cross-attention cache for the wan model. | STRING |
| HIGH | LongLive1.0/pipeline/self_forcing_training.py | 0 | initialize a per-gpu cross-attention cache for the wan model. | STRING |
| HIGH | LongLive2.0/pipeline/causal_diffusion_inference.py | 0 | initialize a per-gpu cross-attention cache for the wan model. | STRING |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 0 | initialize a per-gpu cross-attention cache for the wan model. | STRING |
| HIGH | …_party/LongLive/pipeline/causal_diffusion_inference.py | 0 | set max_attention_size on all submodules that define it. if local_attn_size_value == -1, use the model's global default | STRING |
| HIGH | LongLive1.0/pipeline/causal_inference.py | 0 | set max_attention_size on all submodules that define it. if local_attn_size_value == -1, use the model's global default | STRING |
| HIGH | LongLive2.0/pipeline/causal_diffusion_inference.py | 0 | set max_attention_size on all submodules that define it. if local_attn_size_value == -1, use the model's global default | STRING |
| HIGH | …_party/LongLive/pipeline/causal_diffusion_inference.py | 0 | override sink_size on all submodules that define it. | STRING |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 0 | override sink_size on all submodules that define it. | STRING |
| HIGH | LongLive2.0/pipeline/causal_diffusion_inference.py | 0 | override sink_size on all submodules that define it. | STRING |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 0 | override sink_size on all submodules that define it. | STRING |
| HIGH | …_party/LongLive/pipeline/causal_diffusion_inference.py | 0 | override global_sink_size on all submodules; create the attribute if missing. | STRING |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 0 | override global_sink_size on all submodules; create the attribute if missing. | STRING |
| HIGH | LongLive2.0/pipeline/causal_diffusion_inference.py | 0 | override global_sink_size on all submodules; create the attribute if missing. | STRING |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 0 | override global_sink_size on all submodules; create the attribute if missing. | STRING |
| HIGH | …_party/LongLive/pipeline/causal_diffusion_inference.py | 0 | mark the current chunk's buffer position as pinned for multi-shot sink. the pinned region replaces the original sink on | STRING |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 0 | mark the current chunk's buffer position as pinned for multi-shot sink. the pinned region replaces the original sink on | STRING |
| HIGH | LongLive2.0/pipeline/causal_diffusion_inference.py | 0 | mark the current chunk's buffer position as pinned for multi-shot sink. the pinned region replaces the original sink on | STRING |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 0 | mark the current chunk's buffer position as pinned for multi-shot sink. the pinned region replaces the original sink on | STRING |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 0 | chunk generation method tailored for sequential training args: noise: noise tensor for a single chunk [batch_size, chunk | STRING |
| HIGH | LongLive1.0/pipeline/streaming_training.py | 0 | chunk generation method tailored for sequential training args: noise: noise tensor for a single chunk [batch_size, chunk | STRING |
| HIGH | LongLive1.0/pipeline/self_forcing_training.py | 0 | chunk generation method tailored for sequential training args: noise: noise tensor for a single chunk [batch_size, chunk | STRING |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 0 | chunk generation method tailored for sequential training args: noise: noise tensor for a single chunk [batch_size, chunk | STRING |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 0 | zero out all tensors in kv cache and cross-attention cache instead of setting them to none. this preserves memory alloca | STRING |
| HIGH | LongLive1.0/pipeline/streaming_training.py | 0 | zero out all tensors in kv cache and cross-attention cache instead of setting them to none. this preserves memory alloca | STRING |
| HIGH | LongLive1.0/pipeline/self_forcing_training.py | 0 | zero out all tensors in kv cache and cross-attention cache instead of setting them to none. this preserves memory alloca | STRING |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 0 | zero out all tensors in kv cache and cross-attention cache instead of setting them to none. this preserves memory alloca | STRING |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 0 | set a unified upper bound for all submodules that contain the max_attention_size attribute. local_attn_size_value == -1 | STRING |
| HIGH | LongLive1.0/pipeline/streaming_training.py | 0 | set a unified upper bound for all submodules that contain the max_attention_size attribute. local_attn_size_value == -1 | STRING |
| HIGH | LongLive1.0/pipeline/self_forcing_training.py | 0 | set a unified upper bound for all submodules that contain the max_attention_size attribute. local_attn_size_value == -1 | STRING |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 0 | set a unified upper bound for all submodules that contain the max_attention_size attribute. local_attn_size_value == -1 | STRING |
| HIGH | …g-WAM/stage1/third_party/LongLive/fouroversix/setup.py | 0 | add -gencode flags based on nvcc capabilities. uses the following rules: - sm_100/120 on cuda >= 12.8 - use 100f on cuda | STRING |
| HIGH | Long-WAM/third_party/fouroversix/setup.py | 0 | add -gencode flags based on nvcc capabilities. uses the following rules: - sm_100/120 on cuda >= 12.8 - use 100f on cuda | STRING |
| HIGH | LongLive2.0/fouroversix/setup.py | 0 | add -gencode flags based on nvcc capabilities. uses the following rules: - sm_100/120 on cuda >= 12.8 - use 100f on cuda | STRING |
| HIGH | …g-WAM/stage1/third_party/LongLive/fouroversix/setup.py | 0 | custom bdist wheel command that checks for pre-built wheels on github releases. the cachedwheelscommand plugs into the d | STRING |
| HIGH | Long-WAM/third_party/fouroversix/setup.py | 0 | custom bdist wheel command that checks for pre-built wheels on github releases. the cachedwheelscommand plugs into the d | STRING |
| HIGH | LongLive2.0/fouroversix/setup.py | 0 | custom bdist wheel command that checks for pre-built wheels on github releases. the cachedwheelscommand plugs into the d | STRING |
| HIGH | …g-WAM/stage1/third_party/LongLive/fouroversix/setup.py | 0 | custom build extension that tells ninja how many jobs to run. credit: https://github.com/dao-ailab/flash-attention/blob/ | STRING |
| HIGH | Long-WAM/third_party/fouroversix/setup.py | 0 | custom build extension that tells ninja how many jobs to run. credit: https://github.com/dao-ailab/flash-attention/blob/ | STRING |
| HIGH | LongLive2.0/fouroversix/setup.py | 0 | custom build extension that tells ninja how many jobs to run. credit: https://github.com/dao-ailab/flash-attention/blob/ | STRING |
| HIGH | …rd_party/LongLive/fouroversix/src/fouroversix/utils.py | 0 | return the block size if this a block-scaled format, or `none` otherwise. | STRING |
| HIGH | …g-WAM/third_party/fouroversix/src/fouroversix/utils.py | 0 | return the block size if this a block-scaled format, or `none` otherwise. | STRING |
| HIGH | LongLive2.0/fouroversix/src/fouroversix/utils.py | 0 | return the block size if this a block-scaled format, or `none` otherwise. | STRING |
| HIGH | …rd_party/LongLive/fouroversix/src/fouroversix/utils.py | 0 | return the scale dtype if this a block-scaled format, or `none` otherwise. | STRING |
| HIGH | …g-WAM/third_party/fouroversix/src/fouroversix/utils.py | 0 | return the scale dtype if this a block-scaled format, or `none` otherwise. | STRING |
| HIGH | LongLive2.0/fouroversix/src/fouroversix/utils.py | 0 | return the scale dtype if this a block-scaled format, or `none` otherwise. | STRING |
| HIGH | …rd_party/LongLive/fouroversix/src/fouroversix/utils.py | 0 | return the corresponding torch.dtype if one is available, or `none` otherwise. | STRING |
| HIGH | …g-WAM/third_party/fouroversix/src/fouroversix/utils.py | 0 | return the corresponding torch.dtype if one is available, or `none` otherwise. | STRING |
| HIGH | LongLive2.0/fouroversix/src/fouroversix/utils.py | 0 | return the corresponding torch.dtype if one is available, or `none` otherwise. | STRING |
| HIGH | …rd_party/LongLive/fouroversix/src/fouroversix/utils.py | 0 | backends for matrix multiplication with fp4. - `cutlass`: cutlass implementation. this requires a blackwell gpu. - `pyto | STRING |
| HIGH | …g-WAM/third_party/fouroversix/src/fouroversix/utils.py | 0 | backends for matrix multiplication with fp4. - `cutlass`: cutlass implementation. this requires a blackwell gpu. - `pyto | STRING |
| HIGH | LongLive2.0/fouroversix/src/fouroversix/utils.py | 0 | backends for matrix multiplication with fp4. - `cutlass`: cutlass implementation. this requires a blackwell gpu. - `pyto | STRING |
| HIGH | …rd_party/LongLive/fouroversix/src/fouroversix/utils.py | 0 | backends for quantizing a tensor to nvfp4 or mxfp4. - `cuda`: cuda implementation. requires a blackwell gpu, and current | STRING |
| HIGH | …g-WAM/third_party/fouroversix/src/fouroversix/utils.py | 0 | backends for quantizing a tensor to nvfp4 or mxfp4. - `cuda`: cuda implementation. requires a blackwell gpu, and current | STRING |
| HIGH | LongLive2.0/fouroversix/src/fouroversix/utils.py | 0 | backends for quantizing a tensor to nvfp4 or mxfp4. - `cuda`: cuda implementation. requires a blackwell gpu, and current | STRING |
| HIGH | …rd_party/LongLive/fouroversix/src/fouroversix/utils.py | 0 | rounding styles for quantization. - `nearest`: round to the nearest fp4 value. - `stochastic`: round to the nearest fp4 | STRING |
| HIGH | …g-WAM/third_party/fouroversix/src/fouroversix/utils.py | 0 | rounding styles for quantization. - `nearest`: round to the nearest fp4 value. - `stochastic`: round to the nearest fp4 | STRING |
| 594 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | Long-WAM/pyproject.toml | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …g-WAM/tools/weights/map_longlive_ar_to_video_expert.py | 1 | #!/usr/bin/env python | COMMENT |
| LOW | Long-WAM/tools/results/summarize_domino_eval.py | 1 | #!/usr/bin/env python3 | COMMENT |
| LOW | …ng-WAM/tools/data/build_robocasa_gr1_tabletop_stats.py | 1 | #!/usr/bin/env python3 | COMMENT |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 1 | #!/usr/bin/env python3 | COMMENT |
| LOW | …AM/tools/data/materialize_robotwin_replay_selection.py | 1 | #!/usr/bin/env python3 | COMMENT |
| LOW | Long-WAM/tools/data/build_robocasa_norm_stats.py | 1 | #!/usr/bin/env python3 | COMMENT |
| LOW | Long-WAM/stage1/run.py | 1 | #!/usr/bin/env python3 | COMMENT |
| LOW | Long-WAM/stage1/train.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | Long-WAM/stage1/eval.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | Long-WAM/stage1/validation_artifacts.py | 1 | #!/usr/bin/env python3 | COMMENT |
| LOW | Long-WAM/stage1/runtime/__init__.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | Long-WAM/stage1/runtime/head_sharding.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …-WAM/stage1/requirements/longlive2-bf16-cu128.lock.txt | 1 | # LongLive2 BF16 stage-1 runtime dependencies. | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/train.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …rty/LongLive/pipeline/causal_diffusion_inference_sp.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/fouroversix/setup.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …gLive/fouroversix/src/fouroversix/quantize/__init__.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …LongLive/fouroversix/src/fouroversix/quantize/utils.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …/fouroversix/src/fouroversix/quantize/cuda/__init__.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …ouroversix/src/fouroversix/quantize/triton/__init__.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …uroversix/src/fouroversix/quantize/pytorch/__init__.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …LongLive/fouroversix/src/fouroversix/csrc/bindings.cpp | 1 | // Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …gLive/fouroversix/src/fouroversix/csrc/include/utils.h | 1 | // Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …gLive/fouroversix/src/fouroversix/csrc/include/utils.h | 21 | COMMENT | |
| LOW | …e/fouroversix/src/fouroversix/csrc/include/fp4_quant.h | 1 | // Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …uroversix/src/fouroversix/csrc/include/kernel_traits.h | 1 | // Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …uroversix/src/fouroversix/csrc/include/kernel_traits.h | 101 | // static constexpr int kSwizzleM = 3; | COMMENT |
| LOW | …c/fouroversix/csrc/include/fp4_quant_launch_template.h | 1 | // Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …c/fouroversix/csrc/include/fp4_quant_launch_template.h | 21 | #include <c10/cuda/CUDAException.h> // For C10_CUDA_CHECK and C10_CUDA_KERNEL_LAUNCH_CHECK | COMMENT |
| LOW | …uroversix/src/fouroversix/csrc/include/hardware_info.h | 1 | // Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …uroversix/src/fouroversix/csrc/include/static_switch.h | 1 | // Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …uroversix/src/fouroversix/csrc/include/static_switch.h | 21 | #pragma once | COMMENT |
| LOW | …versix/src/fouroversix/csrc/include/fp4_quant_kernel.h | 1 | // Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …versix/src/fouroversix/csrc/include/fp4_quant_kernel.h | 21 | #pragma once | COMMENT |
| LOW | …rsix/src/fouroversix/csrc/include/hadamard_transform.h | 1 | // Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …/fouroversix/src/fouroversix/model/modules/__init__.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …ongLive/fouroversix/src/fouroversix/matmul/__init__.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …fouroversix/src/fouroversix/matmul/cutlass/__init__.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …rty/LongLive/tests/test_i2v_teacher_forcing_context.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …rty/LongLive/tests/test_wan_backbone_initialization.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …y/LongLive/tests/test_padding_aware_error_recycling.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …party/LongLive/tests/test_distributed_train_sampler.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …ty/LongLive/tests/test_generator_checkpoint_loading.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/config.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/memory.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …ng-WAM/stage1/third_party/LongLive/utils/evaluation.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …age1/third_party/LongLive/utils/torch_compile_utils.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/__init__.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/utils/distributed.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …-WAM/stage1/third_party/LongLive/utils/nvfp4_kernel.py | 1 | #!/usr/bin/env python | COMMENT |
| LOW | …third_party/LongLive/utils/position_embedding_utils.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/utils/rope_triton.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …-WAM/stage1/third_party/LongLive/utils/error_buffer.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …/stage1/third_party/LongLive/utils/nvfp4_checkpoint.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/utils/wan_5b_wrapper.py | 1 | # Long-WAM file attribution; existing upstream notices are retained below. | COMMENT |
| 1039 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …ng-WAM/tools/weights/preprocess_action_dit_backbone.py | 43 | def _is_unresolved_interpolation(value: Any) -> bool: | CODE |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 121 | def _resolve_official_revision(repository: str, requested_revision: str) -> str: | CODE |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 415 | def _validate_trajectory_tree( | CODE |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 468 | def _terminal_trajectory_fingerprint(raw_pickle: bytes) -> str: | CODE |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 522 | def _fetch_official_instructions( | CODE |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 602 | def _fetch_official_trajectory_fingerprints( | CODE |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 685 | def _validate_state_feature_contract(info: Mapping) -> None: | CODE |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 709 | def _combined_terminal_fingerprint( | CODE |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 996 | def _validate_selected_parquets( | CODE |
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 965 | def _set_all_modules_sink_size(self, sink_size_value: int): | CODE |
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 979 | def _set_all_modules_global_sink_size(self, value: int): | CODE |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 872 | def _initialize_crossattn_cache(self, batch_size, dtype, device): | CODE |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 906 | def _initialize_sample_scheduler(self, noise): | CODE |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 929 | def _set_all_modules_max_attention_size(self, local_attn_size_value: int): | CODE |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 1012 | def _update_sink_for_scene_cut(self, kv_cache, current_num_frames): | CODE |
| LOW⚡ | …third_party/LongLive/pipeline/self_forcing_training.py | 383 | def _set_all_modules_sink_size(self, sink_size_value: int): | CODE |
| LOW⚡ | …third_party/LongLive/pipeline/self_forcing_training.py | 395 | def _set_all_modules_global_sink_size(self, value: int): | CODE |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 93 | def _build_default_denoising_step_list(self, sampling_steps): | CODE |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 122 | def generate_chunk_with_cache( | CODE |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 299 | def inference_with_trajectory( | CODE |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 420 | def _inference_with_trajectory_inner( | CODE |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 709 | def _initialize_crossattn_cache(self, batch_size, dtype, device): | CODE |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 755 | def _set_all_modules_max_attention_size(self, local_attn_size_value: int): | CODE |
| LOW | …g-WAM/stage1/third_party/LongLive/fouroversix/setup.py | 46 | def get_cuda_bare_metal_version() -> Version | None: | CODE |
| LOW | …LongLive/fouroversix/src/fouroversix/quantize/utils.py | 26 | def get_no_random_sign_vector(device: int) -> torch.Tensor: | CODE |
| LOW | …LongLive/fouroversix/src/fouroversix/model/quantize.py | 45 | def should_replace_existing_modules_in_model( | CODE |
| LOW | …ve/fouroversix/src/fouroversix/model/modules/linear.py | 281 | def _serialize_quantized_weight( | CODE |
| LOW | …ve/fouroversix/src/fouroversix/model/modules/linear.py | 332 | def quantized_weight_transposed(self) -> QuantizedTensor | None: | CODE |
| LOW | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 55 | def _distributed_failure_worker(rank, world_size, init_file, output_dir): | CODE |
| LOW | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 90 | def test_distributed_failures_reach_every_rank_with_same_message(self): | CODE |
| LOW | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 110 | def test_legacy_config_resolves_to_one_unnamed_group(self): | CODE |
| LOW | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 125 | def test_named_groups_preserve_short_then_long_order(self): | CODE |
| LOW | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 153 | def test_invalid_named_group_contract_fails_early(self): | CODE |
| LOW⚡ | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 177 | def test_selection_uses_ids_not_folder_order(self): | CODE |
| LOW⚡ | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 186 | def test_selection_validates_only_selected_manifest_indices(self): | CODE |
| LOW⚡ | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 192 | def validate_fixed_evaluation_indices(self, indices): | CODE |
| LOW⚡ | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 206 | def test_dataset_cannot_relabel_selected_evaluation_ids(self): | CODE |
| LOW⚡ | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 208 | def validate_fixed_evaluation_indices(self, indices): | CODE |
| LOW⚡ | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 216 | def test_missing_and_duplicate_ids_fail_early(self): | CODE |
| LOW⚡ | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 224 | def test_padded_replicas_have_one_canonical_writer(self): | CODE |
| LOW | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 254 | def test_seed_and_weight_mode_are_stable(self): | CODE |
| LOW | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 267 | def test_legacy_nonfixed_model_artifact_keeps_empty_suffix(self): | CODE |
| LOW | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 303 | def test_single_process_failure_uses_distributed_error_contract(self): | CODE |
| LOW | …e1/third_party/LongLive/tests/test_fixed_evaluation.py | 312 | def test_six_single_weight_panels_have_stable_wandb_keys(self): | CODE |
| LOW | …rty/LongLive/tests/test_i2v_teacher_forcing_context.py | 126 | def _load_causal_diffusion_with_stubs(): | CODE |
| LOW | …rty/LongLive/tests/test_wan_backbone_initialization.py | 156 | def test_default_path_loads_pretrained_weights(self): | CODE |
| LOW | …rty/LongLive/tests/test_wan_backbone_initialization.py | 181 | def test_explicit_config_path_never_loads_pretrained_weights(self): | CODE |
| LOW | …y/LongLive/tests/test_padding_aware_error_recycling.py | 38 | def _load_causal_diffusion_with_stubs(): | CODE |
| LOW | …y/LongLive/tests/test_padding_aware_error_recycling.py | 157 | def test_local_collection_keeps_only_valid_blocks_without_reindexing(self): | CODE |
| LOW | …y/LongLive/tests/test_padding_aware_error_recycling.py | 180 | def test_all_injection_paths_leave_invalid_tail_untouched(self): | CODE |
| LOW | …y/LongLive/tests/test_padding_aware_error_recycling.py | 296 | def test_warmup_gather_propagates_and_filters_block_validity(self): | CODE |
| LOW | …y/LongLive/tests/test_padding_aware_error_recycling.py | 391 | def test_error_buffer_invalid_add_cannot_replace_valid_entry(self): | CODE |
| LOW | …y/LongLive/tests/test_padding_aware_error_recycling.py | 413 | def test_strict_same_stage_error_buffer_round_trip(self): | CODE |
| LOW | …y/LongLive/tests/test_padding_aware_error_recycling.py | 441 | def test_strict_error_buffer_layout_mismatch_fails_before_mutation(self): | CODE |
| LOW | …party/LongLive/tests/test_distributed_train_sampler.py | 88 | def test_train_sampler_is_identical_within_sp_and_disjoint_across_dp(self): | CODE |
| LOW | …party/LongLive/tests/test_distributed_train_sampler.py | 106 | def test_eval_sampler_is_identical_within_sp_and_covers_dataset(self): | CODE |
| LOW | …party/LongLive/tests/test_distributed_train_sampler.py | 121 | def test_epoch_changes_shared_train_order_deterministically(self): | CODE |
| LOW | …party/LongLive/tests/test_distributed_train_sampler.py | 137 | def test_cycle_calls_set_epoch_once_per_completed_pass(self): | CODE |
| LOW | …party/LongLive/tests/test_distributed_train_sampler.py | 148 | def test_resume_cursor_cold_mid_epoch_and_epoch_boundary(self): | CODE |
| LOW | …party/LongLive/tests/test_distributed_train_sampler.py | 182 | def test_mid_epoch_offset_skips_indices_without_decoding_them(self): | CODE |
| 796 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …ng-WAM/tools/data/build_robocasa_gr1_tabletop_stats.py | 23 | CODE | |
| LOW | …AM/tools/data/materialize_robotwin_replay_selection.py | 23 | CODE | |
| LOW | Long-WAM/tools/data/build_robocasa_norm_stats.py | 28 | CODE | |
| LOW | Long-WAM/stage1/run.py | 107 | CODE | |
| LOW | Long-WAM/stage1/infer.py | 11 | CODE | |
| LOW | Long-WAM/stage1/runtime/head_sharding.py | 29 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/pipeline/__init__.py | 10 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/pipeline/__init__.py | 11 | CODE | |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 23 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 13 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 14 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 14 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 14 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 14 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 14 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 21 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 21 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 21 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 22 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 22 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 22 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 22 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 22 | CODE | |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 23 | CODE | |
| LOW | …gLive/fouroversix/src/fouroversix/quantize/__init__.py | 11 | CODE | |
| LOW | …gLive/fouroversix/src/fouroversix/quantize/__init__.py | 12 | CODE | |
| LOW | …gLive/fouroversix/src/fouroversix/quantize/__init__.py | 13 | CODE | |
| LOW | …gLive/fouroversix/src/fouroversix/quantize/__init__.py | 14 | CODE | |
| LOW | …oversix/src/fouroversix/quantize/transformer_engine.py | 43 | CODE | |
| LOW | …e/fouroversix/src/fouroversix/quantize/cuda/backend.py | 39 | CODE | |
| LOW | …/fouroversix/src/fouroversix/quantize/cuda/__init__.py | 11 | CODE | |
| LOW | …/fouroversix/src/fouroversix/quantize/triton/kernel.py | 11 | CODE | |
| LOW | …ouroversix/src/fouroversix/quantize/triton/__init__.py | 11 | CODE | |
| LOW | …uroversix/src/fouroversix/quantize/pytorch/__init__.py | 11 | CODE | |
| LOW | …roversix/src/fouroversix/quantize/pytorch/reference.py | 11 | CODE | |
| LOW | …LongLive/fouroversix/src/fouroversix/model/quantize.py | 11 | CODE | |
| LOW | …LongLive/fouroversix/src/fouroversix/model/__init__.py | 11 | CODE | |
| LOW | …LongLive/fouroversix/src/fouroversix/model/__init__.py | 11 | CODE | |
| LOW | …LongLive/fouroversix/src/fouroversix/model/__init__.py | 12 | CODE | |
| LOW | …LongLive/fouroversix/src/fouroversix/model/__init__.py | 13 | CODE | |
| LOW | …LongLive/fouroversix/src/fouroversix/model/__init__.py | 13 | CODE | |
| LOW | …/fouroversix/src/fouroversix/model/modules/__init__.py | 11 | CODE | |
| LOW | …/fouroversix/src/fouroversix/model/modules/__init__.py | 12 | CODE | |
| LOW | …ongLive/fouroversix/src/fouroversix/matmul/__init__.py | 11 | CODE | |
| LOW | …/fouroversix/src/fouroversix/matmul/cutlass/backend.py | 37 | CODE | |
| LOW | …fouroversix/src/fouroversix/matmul/cutlass/__init__.py | 11 | CODE | |
| LOW | …ng-WAM/stage1/third_party/LongLive/utils/evaluation.py | 24 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 38 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 46 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/utils/rope_triton.py | 27 | CODE | |
| LOW | …/stage1/third_party/LongLive/utils/nvfp4_checkpoint.py | 20 | CODE | |
| LOW | …-WAM/stage1/third_party/LongLive/utils/adaln_triton.py | 29 | CODE | |
| LOW | …M/stage1/third_party/LongLive/utils/inference_utils.py | 22 | CODE | |
| LOW | …M/stage1/third_party/LongLive/utils/inference_utils.py | 27 | CODE | |
| LOW | …stage1/third_party/LongLive/utils/kernel/kv_dequant.py | 23 | CODE | |
| LOW | …stage1/third_party/LongLive/utils/kernel/kv_dequant.py | 25 | CODE | |
| LOW | …stage1/third_party/LongLive/wan_5b/distributed/util.py | 24 | CODE | |
| LOW | …stage1/third_party/LongLive/wan_5b/distributed/util.py | 24 | CODE | |
| LOW | …stage1/third_party/LongLive/wan_5b/distributed/util.py | 24 | CODE | |
| LOW | …stage1/third_party/LongLive/wan_5b/distributed/util.py | 24 | CODE | |
| 409 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | Long-WAM/tools/data/build_robocasa_norm_stats.py | 275 | except FileNotFoundError: | CODE |
| HIGH | …_party/LongLive/pipeline/causal_diffusion_inference.py | 985 | except Exception: | CODE |
| HIGH | …_party/LongLive/pipeline/causal_diffusion_inference.py | 962 | except Exception: | CODE |
| HIGH | …_party/LongLive/pipeline/causal_diffusion_inference.py | 976 | except Exception: | CODE |
| HIGH | …_party/LongLive/pipeline/causal_diffusion_inference.py | 367 | except Exception: | CODE |
| HIGH | …_party/LongLive/pipeline/causal_diffusion_inference.py | 372 | except Exception: | CODE |
| HIGH | …_party/LongLive/pipeline/causal_diffusion_inference.py | 377 | except Exception: | CODE |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 401 | except Exception: | CODE |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 775 | except Exception: | CODE |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 359 | except Exception: | CODE |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 364 | except Exception: | CODE |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 369 | except Exception: | CODE |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 392 | except Exception: | CODE |
| HIGH | …third_party/LongLive/pipeline/self_forcing_training.py | 784 | except Exception: | CODE |
| HIGH | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 800 | except Exception: | CODE |
| HIGH | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 770 | except FileNotFoundError: | CODE |
| HIGH | …/stage1/third_party/LongLive/utils/nvfp4_checkpoint.py | 91 | except ImportError: | CODE |
| HIGH | …AM/stage1/third_party/LongLive/utils/wan_5b_wrapper.py | 429 | except (KeyError, AttributeError, ImportError): | CODE |
| HIGH | Long-WAM/stage1/third_party/LongLive/utils/quant.py | 292 | except Exception: | CODE |
| HIGH | …-WAM/stage1/scripts/longlive/prebuild_video_indexes.py | 97 | except FileNotFoundError: | CODE |
| HIGH | Long-WAM/src/longwam/evaluation.py | 126 | except KeyboardInterrupt: | CODE |
| HIGH | Long-WAM/src/longwam/evaluation.py | 506 | except ProcessLookupError: | CODE |
| HIGH | Long-WAM/src/longwam/runtime/worker.py | 88 | except BaseException: | CODE |
| HIGH | Long-WAM/src/longwam/runtime/worker.py | 270 | except queue.Full: | CODE |
| HIGH | Long-WAM/src/longwam/agentic/_vendor/transport.py | 90 | except queue.Full: | CODE |
| HIGH | Long-WAM/src/longwam/benchmarks/robocasa_gr1/rollout.py | 290 | except (BrokenPipeError, EOFError, OSError): | CODE |
| HIGH | …WAM/src/longwam/benchmarks/robocasa/agentic/session.py | 236 | except Exception: | CODE |
| HIGH | …WAM/src/longwam/benchmarks/robocasa/agentic/session.py | 240 | except Exception: | CODE |
| HIGH | LongLive1.0/pipeline/streaming_training.py | 333 | except Exception: | CODE |
| HIGH | LongLive1.0/pipeline/streaming_training.py | 342 | except Exception: | CODE |
| HIGH | LongLive1.0/pipeline/causal_inference.py | 318 | except Exception: | CODE |
| HIGH | LongLive1.0/pipeline/self_forcing_training.py | 571 | except Exception: | CODE |
| HIGH | LongLive1.0/pipeline/self_forcing_training.py | 580 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/causal_diffusion_inference.py | 971 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/causal_diffusion_inference.py | 948 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/causal_diffusion_inference.py | 962 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/causal_diffusion_inference.py | 353 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/causal_diffusion_inference.py | 358 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/causal_diffusion_inference.py | 363 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 390 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 764 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 348 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 353 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 358 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 381 | except Exception: | CODE |
| HIGH | LongLive2.0/pipeline/self_forcing_training.py | 773 | except Exception: | CODE |
| HIGH | LongLive2.0/utils/nvfp4_checkpoint.py | 81 | except ImportError: | CODE |
| HIGH | LongLive2.0/utils/wan_5b_wrapper.py | 370 | except (KeyError, AttributeError, ImportError): | CODE |
| HIGH | LongLive2.0/utils/quant.py | 282 | except Exception: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 78 | # Step 2: Initialize scheduler | COMMENT |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 50 | # Step 1: Initialize all models | COMMENT |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 243 | # Step 1: Initialize KV cache to all zeros | COMMENT |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 277 | # Step 2: Cache context feature | COMMENT |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 448 | # Step 3: Temporal denoising loop | COMMENT |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 752 | # Step 4: Decode the output | COMMENT |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 457 | # Step 1: Initialize KV cache to all zeros | COMMENT |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 479 | # Step 2: Cache context feature | COMMENT |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 497 | # Step 3: Temporal denoising loop | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1574 | # We need to check if we can get num_frames frames | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/diffusion.py | 55 | # Step 2: Initialize all hyperparameters | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/diffusion.py | 196 | # Step 2: Randomly sample a timestep and add noise to denoiser inputs | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/diffusion.py | 316 | # Step 3: Noise augmentation, also add small noise to clean context latents | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/diffusion.py | 391 | # Step 5: Store prediction errors into error buffer. | COMMENT |
| LOW⚡ | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 498 | # Step 5: Debugging Log | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 58 | # Step 2: Initialize all dmd hyperparameters | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 109 | # Step 1: Compute the fake score | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 130 | # Step 2: Compute the real score | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 149 | # Step 3: Compute the DMD gradient (DMD paper eq. 7). | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 224 | # Step 1: Randomly sample timestep based on the given schedule and corresponding noise | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 258 | # Step 2: Compute the KL grad | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 302 | # Step 1: Unroll generator to obtain fake videos | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 318 | # Step 2: Compute the DMD loss | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 379 | # Step 1: Run generator on backward simulated noisy input | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 421 | # Step 2: Compute the fake prediction | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 461 | # Step 3: Compute the denoising loss for the fake critic | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 1575 | # Step 1: Initialize the distributed training environment (rank, seed, dtype, logging etc.) | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 1804 | # Step 2: Initialize the model and optimizer | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2009 | # Step 3: Initialize the dataloader | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2740 | # Step 1: Get the next batch of text prompts | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2763 | # Step 2: Extract the conditional infos | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2796 | # Step 3: Train the generator | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2825 | # Step 4: Update EMA (if enabled and after start step) | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2869 | # Step 5: Logging | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 52 | # Step 1: Initialize the distributed training environment (rank, seed, dtype, logging etc.) | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 90 | # Step 2: Initialize the model | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 417 | # Step 3: Set up EMA parameter containers | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 441 | # Step 4: Initialize the optimizer | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 458 | # Step 5: Initialize the dataloader | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 542 | # Step 6: Initialize the validation dataloader for visualization (fixed prompts) | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1011 | # Step 1: Get the next batch of text prompts | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1051 | # Step 2: Extract the conditional infos | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1082 | # Step 3: Store gradients for the generator (if training the generator) | COMMENT |
| LOW | …/cutlass/epilogue/threadblock/fusion/visitor_store.hpp | 582 | // Step 1: reduce fragment input (Src) into tRS_rSrc | COMMENT |
| LOW | …/cutlass/epilogue/threadblock/fusion/visitor_store.hpp | 593 | // Step 2: copy the partial results in tRS_rSrc to sRows in shared memory | COMMENT |
| LOW | …/cutlass/epilogue/threadblock/fusion/visitor_store.hpp | 605 | // Step 3: copy the partial results in sRows to tSR_sRow for reduction | COMMENT |
| LOW | …/cutlass/epilogue/threadblock/fusion/visitor_store.hpp | 619 | // Step 4: atomically reduce the results to global memory | COMMENT |
| LOW | …/cutlass/transform/collective/sm90_wgmma_transpose.hpp | 347 | /// Step 0: Step 1: | COMMENT |
| LOW⚡ | …/cutlass/transform/collective/sm90_wgmma_transpose.hpp | 565 | /// Step 0: Step 1: Step 2: Step 3: | COMMENT |
| LOW⚡ | …/cutlass/transform/collective/sm90_wgmma_transpose.hpp | 575 | /// Step 4: Step 5: Step 6: Step 7: | COMMENT |
| LOW⚡ | LongLive1.0/pipeline/causal_inference.py | 23 | # Step 1: Initialize all models | COMMENT |
| LOW⚡ | LongLive1.0/pipeline/causal_inference.py | 31 | # Step 2: Initialize all causal hyperparmeters | COMMENT |
| LOW | LongLive1.0/pipeline/causal_inference.py | 109 | # Step 1: Initialize KV cache to all zeros | COMMENT |
| LOW | LongLive1.0/pipeline/causal_inference.py | 144 | # Step 2: Temporal denoising loop | COMMENT |
| LOW | LongLive1.0/pipeline/causal_inference.py | 219 | # Step 3: Decode the output | COMMENT |
| LOW | LongLive1.0/pipeline/self_forcing_training.py | 322 | # Step 1: Initialize KV cache to all zeros | COMMENT |
| LOW | LongLive1.0/pipeline/self_forcing_training.py | 351 | # Step 2: Cache context feature | COMMENT |
| LOW | LongLive1.0/pipeline/self_forcing_training.py | 368 | # Step 3: Temporal denoising loop | COMMENT |
| LOW⚡ | LongLive1.0/model/dmd.py | 118 | # Step 3: Compute the DMD gradient (DMD paper eq. 7). | COMMENT |
| LOW⚡ | LongLive1.0/model/dmd.py | 123 | # Step 4: Gradient normalization (DMD paper eq. 8). | COMMENT |
| 84 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 78 | # Step 2: Initialize scheduler | COMMENT |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 50 | # Step 1: Initialize all models | COMMENT |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 243 | # Step 1: Initialize KV cache to all zeros | COMMENT |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 277 | # Step 2: Cache context feature | COMMENT |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 448 | # Step 3: Temporal denoising loop | COMMENT |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 752 | # Step 4: Decode the output | COMMENT |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 457 | # Step 1: Initialize KV cache to all zeros | COMMENT |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 479 | # Step 2: Cache context feature | COMMENT |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 497 | # Step 3: Temporal denoising loop | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/diffusion.py | 55 | # Step 2: Initialize all hyperparameters | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/diffusion.py | 196 | # Step 2: Randomly sample a timestep and add noise to denoiser inputs | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/diffusion.py | 316 | # Step 3: Noise augmentation, also add small noise to clean context latents | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/diffusion.py | 391 | # Step 5: Store prediction errors into error buffer. | COMMENT |
| LOW⚡ | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 498 | # Step 5: Debugging Log | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 58 | # Step 2: Initialize all dmd hyperparameters | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 109 | # Step 1: Compute the fake score | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 130 | # Step 2: Compute the real score | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 149 | # Step 3: Compute the DMD gradient (DMD paper eq. 7). | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 224 | # Step 1: Randomly sample timestep based on the given schedule and corresponding noise | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 258 | # Step 2: Compute the KL grad | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 302 | # Step 1: Unroll generator to obtain fake videos | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 318 | # Step 2: Compute the DMD loss | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 379 | # Step 1: Run generator on backward simulated noisy input | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 421 | # Step 2: Compute the fake prediction | COMMENT |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 461 | # Step 3: Compute the denoising loss for the fake critic | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 1575 | # Step 1: Initialize the distributed training environment (rank, seed, dtype, logging etc.) | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 1804 | # Step 2: Initialize the model and optimizer | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2009 | # Step 3: Initialize the dataloader | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2740 | # Step 1: Get the next batch of text prompts | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2763 | # Step 2: Extract the conditional infos | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2796 | # Step 3: Train the generator | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2825 | # Step 4: Update EMA (if enabled and after start step) | COMMENT |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2869 | # Step 5: Logging | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 52 | # Step 1: Initialize the distributed training environment (rank, seed, dtype, logging etc.) | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 90 | # Step 2: Initialize the model | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 417 | # Step 3: Set up EMA parameter containers | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 441 | # Step 4: Initialize the optimizer | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 458 | # Step 5: Initialize the dataloader | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 542 | # Step 6: Initialize the validation dataloader for visualization (fixed prompts) | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1011 | # Step 1: Get the next batch of text prompts | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1051 | # Step 2: Extract the conditional infos | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1082 | # Step 3: Store gradients for the generator (if training the generator) | COMMENT |
| LOW | …/cutlass/epilogue/threadblock/fusion/visitor_store.hpp | 582 | // Step 1: reduce fragment input (Src) into tRS_rSrc | COMMENT |
| LOW | …/cutlass/epilogue/threadblock/fusion/visitor_store.hpp | 593 | // Step 2: copy the partial results in tRS_rSrc to sRows in shared memory | COMMENT |
| LOW | …/cutlass/epilogue/threadblock/fusion/visitor_store.hpp | 605 | // Step 3: copy the partial results in sRows to tSR_sRow for reduction | COMMENT |
| LOW | …/cutlass/epilogue/threadblock/fusion/visitor_store.hpp | 619 | // Step 4: atomically reduce the results to global memory | COMMENT |
| LOW | …/cutlass/transform/collective/sm90_wgmma_transpose.hpp | 347 | /// Step 0: Step 1: | COMMENT |
| LOW⚡ | …/cutlass/transform/collective/sm90_wgmma_transpose.hpp | 565 | /// Step 0: Step 1: Step 2: Step 3: | COMMENT |
| LOW⚡ | …/cutlass/transform/collective/sm90_wgmma_transpose.hpp | 575 | /// Step 4: Step 5: Step 6: Step 7: | COMMENT |
| LOW⚡ | LongLive1.0/pipeline/causal_inference.py | 23 | # Step 1: Initialize all models | COMMENT |
| LOW⚡ | LongLive1.0/pipeline/causal_inference.py | 31 | # Step 2: Initialize all causal hyperparmeters | COMMENT |
| LOW | LongLive1.0/pipeline/causal_inference.py | 109 | # Step 1: Initialize KV cache to all zeros | COMMENT |
| LOW | LongLive1.0/pipeline/causal_inference.py | 144 | # Step 2: Temporal denoising loop | COMMENT |
| LOW | LongLive1.0/pipeline/causal_inference.py | 219 | # Step 3: Decode the output | COMMENT |
| LOW | LongLive1.0/pipeline/self_forcing_training.py | 322 | # Step 1: Initialize KV cache to all zeros | COMMENT |
| LOW | LongLive1.0/pipeline/self_forcing_training.py | 351 | # Step 2: Cache context feature | COMMENT |
| LOW | LongLive1.0/pipeline/self_forcing_training.py | 368 | # Step 3: Temporal denoising loop | COMMENT |
| LOW⚡ | LongLive1.0/model/dmd.py | 118 | # Step 3: Compute the DMD gradient (DMD paper eq. 7). | COMMENT |
| LOW⚡ | LongLive1.0/model/dmd.py | 123 | # Step 4: Gradient normalization (DMD paper eq. 8). | COMMENT |
| LOW⚡ | LongLive1.0/model/dmd.py | 385 | # Step 5: Debugging Log | COMMENT |
| 82 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | …_party/LongLive/pipeline/causal_diffusion_inference.py | 479 | def _vae_thread_fn(): | CODE |
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 75 | except Exception as exc: | CODE |
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 367 | except Exception: | CODE |
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 372 | except Exception: | CODE |
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 377 | except Exception: | CODE |
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 947 | except Exception: | CODE |
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 957 | except Exception: | CODE |
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 962 | except Exception: | CODE |
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 976 | except Exception: | CODE |
| LOW⚡ | …_party/LongLive/pipeline/causal_diffusion_inference.py | 985 | except Exception: | CODE |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 506 | except Exception as exc: | CODE |
| LOW⚡ | …third_party/LongLive/pipeline/self_forcing_training.py | 359 | except Exception: | CODE |
| LOW⚡ | …third_party/LongLive/pipeline/self_forcing_training.py | 364 | except Exception: | CODE |
| LOW⚡ | …third_party/LongLive/pipeline/self_forcing_training.py | 369 | except Exception: | CODE |
| LOW⚡ | …third_party/LongLive/pipeline/self_forcing_training.py | 392 | except Exception: | CODE |
| LOW⚡ | …third_party/LongLive/pipeline/self_forcing_training.py | 401 | except Exception: | CODE |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 775 | except Exception: | CODE |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 784 | except Exception: | CODE |
| LOW | …age1/third_party/LongLive/utils/torch_compile_utils.py | 59 | except Exception as exc: | CODE |
| LOW | …age1/third_party/LongLive/utils/torch_compile_utils.py | 85 | except Exception as exc: | CODE |
| LOW | …age1/third_party/LongLive/utils/torch_compile_utils.py | 122 | except Exception as exc: | CODE |
| MEDIUM | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 594 | def _read_index_header(self): | CODE |
| MEDIUM | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1462 | def get_numeric_key(path): | CODE |
| LOW⚡ | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1234 | except Exception: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 800 | except Exception: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 908 | except Exception: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 985 | except Exception as exc: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1013 | except Exception as exc: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1253 | except Exception: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1447 | except Exception: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1498 | except Exception: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1999 | except Exception as exc: | CODE |
| LOW | …age1/third_party/LongLive/utils/lightvae_5b_wrapper.py | 132 | except Exception as exc: | CODE |
| LOW | …age1/third_party/LongLive/utils/lightvae_5b_wrapper.py | 147 | except Exception: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/quant.py | 292 | except Exception: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/quant.py | 304 | except Exception as copy_exc: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/quant.py | 729 | except Exception as exc: # pragma: no cover - exercised only when extension is stale/missing | CODE |
| LOW | …ge1/third_party/LongLive/wan_5b/utils/prompt_extend.py | 196 | except Exception as e: | CODE |
| LOW | …ge1/third_party/LongLive/wan_5b/utils/prompt_extend.py | 259 | except Exception as e: | CODE |
| LOW | …-WAM/stage1/third_party/LongLive/wan_5b/utils/utils.py | 64 | except Exception as e: | CODE |
| LOW | …-WAM/stage1/third_party/LongLive/wan_5b/utils/utils.py | 86 | except Exception as e: | CODE |
| LOW | …rty/LongLive/wan_5b/modules/causal_model_sp_ulysses.py | 58 | except Exception: | CODE |
| LOW | …tage1/third_party/LongLive/wan_5b/modules/attention.py | 22 | except Exception: | CODE |
| LOW | …tage1/third_party/LongLive/wan_5b/modules/attention.py | 47 | except Exception: | CODE |
| LOW⚡ | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 495 | except Exception: | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/model/dmd.py | 345 | except Exception: | CODE |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 735 | except Exception as exc: | CODE |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 915 | except Exception: | CODE |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 1424 | except Exception as e: | CODE |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 1633 | except Exception as exc: | CODE |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2514 | except Exception as e: | CODE |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2568 | except Exception as e: | CODE |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2898 | except Exception: | CODE |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 2938 | except Exception as exc: | CODE |
| LOW⚡ | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1276 | except Exception as e: | CODE |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 919 | except Exception as e: | CODE |
| LOW | Long-WAM/src/longwam/trainer.py | 1388 | except Exception: | CODE |
| LOW | …AM/src/longwam/datasets/lerobot/robot_video_dataset.py | 432 | except Exception as e: | CODE |
| MEDIUM | …AM/src/longwam/datasets/lerobot/robot_video_dataset.py | 435 | print(f"Error processing sample idx {idx}: {e}. Returning a random sample instead.") | CODE |
| MEDIUM | …AM/src/longwam/datasets/lerobot/robot_video_dataset.py | 427 | def __getitem__(self, idx): | CODE |
| 106 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 415 | CODE | |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 522 | CODE | |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 602 | CODE | |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 798 | CODE | |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 1065 | CODE | |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 210 | CODE | |
| LOW | Long-WAM/tools/data/build_robotwin_episode_manifest.py | 425 | CODE | |
| LOW | Long-WAM/stage1/runtime/head_sharding.py | 120 | CODE | |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 178 | CODE | |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 380 | CODE | |
| LOW | …_party/LongLive/pipeline/causal_diffusion_inference.py | 479 | CODE | |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 122 | CODE | |
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 420 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/fouroversix/setup.py | 66 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 661 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1779 | CODE | |
| LOW | …third_party/LongLive/utils/position_embedding_utils.py | 66 | CODE | |
| LOW | …-WAM/stage1/third_party/LongLive/utils/error_buffer.py | 284 | CODE | |
| LOW | …/stage1/third_party/LongLive/utils/nvfp4_checkpoint.py | 144 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/quant.py | 487 | CODE | |
| LOW | …ng-WAM/stage1/third_party/LongLive/utils/lora_utils.py | 29 | CODE | |
| LOW | …stage1/third_party/LongLive/wan_5b/utils/fm_solvers.py | 425 | CODE | |
| LOW | …stage1/third_party/LongLive/wan_5b/utils/fm_solvers.py | 496 | CODE | |
| LOW | …-WAM/stage1/third_party/LongLive/wan_5b/utils/utils.py | 117 | CODE | |
| LOW | …ge1/third_party/LongLive/wan_5b/utils/qwen_vl_utils.py | 98 | CODE | |
| LOW | …ge1/third_party/LongLive/wan_5b/utils/qwen_vl_utils.py | 341 | CODE | |
| LOW | …tage1/third_party/LongLive/wan_5b/modules/attention.py | 95 | CODE | |
| LOW | …M/stage1/third_party/LongLive/wan_5b/modules/vae2_1.py | 79 | CODE | |
| LOW | …M/stage1/third_party/LongLive/wan_5b/modules/vae2_1.py | 112 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/wan_5b/modules/t5.py | 40 | CODE | |
| LOW | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 103 | CODE | |
| LOW | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 340 | CODE | |
| LOW | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 1384 | CODE | |
| LOW | …M/stage1/third_party/LongLive/wan_5b/modules/vae2_2.py | 84 | CODE | |
| LOW | …M/stage1/third_party/LongLive/wan_5b/modules/vae2_2.py | 122 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/model/diffusion.py | 40 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/model/diffusion.py | 163 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/model/diffusion.py | 712 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 1394 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 1571 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 3112 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 3511 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 3601 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 48 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 842 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 868 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1005 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1163 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1282 | CODE | |
| LOW | Long-WAM/tests/runtime/test_lerobot_policy.py | 76 | CODE | |
| LOW | Long-WAM/third_party/fouroversix/setup.py | 66 | CODE | |
| LOW | Long-WAM/scripts/precompute_text_embeds.py | 242 | CODE | |
| LOW | Long-WAM/scripts/precompute_text_embeds.py | 702 | CODE | |
| LOW | Long-WAM/src/longwam/evaluation.py | 38 | CODE | |
| LOW | Long-WAM/src/longwam/evaluation.py | 176 | CODE | |
| LOW | Long-WAM/src/longwam/evaluation.py | 425 | CODE | |
| LOW | Long-WAM/src/longwam/trainer.py | 569 | CODE | |
| LOW | Long-WAM/src/longwam/trainer.py | 1053 | CODE | |
| LOW | Long-WAM/src/longwam/trainer.py | 1471 | CODE | |
| LOW | …-WAM/src/longwam/datasets/lerobot/episode_selection.py | 136 | CODE | |
| 136 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …third_party/LongLive/pipeline/self_forcing_training.py | 28 | CODE | |
| LOW | …rty/LongLive/pipeline/causal_diffusion_inference_sp.py | 42 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 304 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1303 | CODE | |
| LOW | …age1/third_party/LongLive/utils/lightvae_5b_wrapper.py | 171 | CODE | |
| LOW | …-WAM/stage1/third_party/LongLive/utils/error_buffer.py | 68 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/utils/wan_5b_wrapper.py | 207 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/utils/wan_5b_wrapper.py | 232 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/utils/wan_5b_wrapper.py | 297 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/utils/wan_5b_wrapper.py | 301 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/utils/wan_5b_wrapper.py | 512 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/scheduler.py | 117 | CODE | |
| LOW | Long-WAM/stage1/third_party/LongLive/utils/quant.py | 595 | CODE | |
| LOW | …/stage1/third_party/LongLive/wan_5b/textimage2video.py | 47 | CODE | |
| LOW | …/stage1/third_party/LongLive/wan_5b/textimage2video.py | 173 | CODE | |
| LOW | …/stage1/third_party/LongLive/wan_5b/textimage2video.py | 250 | CODE | |
| LOW | …/stage1/third_party/LongLive/wan_5b/textimage2video.py | 424 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/wan_5b/text2video.py | 44 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/wan_5b/text2video.py | 214 | CODE | |
| LOW | …-WAM/stage1/third_party/LongLive/wan_5b/image2video.py | 46 | CODE | |
| LOW | …-WAM/stage1/third_party/LongLive/wan_5b/image2video.py | 217 | CODE | |
| LOW | …party/LongLive/wan_5b/distributed/sequence_parallel.py | 391 | CODE | |
| LOW | …stage1/third_party/LongLive/wan_5b/utils/fm_solvers.py | 144 | CODE | |
| LOW | …/third_party/LongLive/wan_5b/utils/fm_solvers_unipc.py | 92 | CODE | |
| LOW | …rty/LongLive/wan_5b/modules/causal_model_sp_ulysses.py | 125 | CODE | |
| LOW | …rty/LongLive/wan_5b/modules/causal_model_sp_ulysses.py | 354 | CODE | |
| LOW | …rty/LongLive/wan_5b/modules/causal_model_sp_ulysses.py | 453 | CODE | |
| LOW | …tage1/third_party/LongLive/wan_5b/modules/attention.py | 95 | CODE | |
| LOW | …tage1/third_party/LongLive/wan_5b/modules/attention.py | 271 | CODE | |
| LOW | …AM/stage1/third_party/LongLive/wan_5b/modules/model.py | 336 | CODE | |
| LOW | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 340 | CODE | |
| LOW | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 842 | CODE | |
| LOW | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 987 | CODE | |
| LOW | …M/stage1/third_party/LongLive/wan_5b/modules/vae2_2.py | 746 | CODE | |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/diffusion.py | 1301 | CODE | |
| LOW | …gwam/datasets/lerobot/robocasa_gr1_tabletop_dataset.py | 633 | CODE | |
| LOW | …AM/src/longwam/datasets/lerobot/robot_video_dataset.py | 57 | CODE | |
| LOW | …M/src/longwam/datasets/lerobot/base_lerobot_dataset.py | 636 | CODE | |
| LOW | …M/src/longwam/datasets/lerobot/base_lerobot_dataset.py | 65 | CODE | |
| LOW | …rc/longwam/datasets/lerobot/lerobot/lerobot_dataset.py | 412 | CODE | |
| LOW | …rc/longwam/datasets/lerobot/lerobot/lerobot_dataset.py | 588 | CODE | |
| LOW | …rc/longwam/datasets/lerobot/lerobot/lerobot_dataset.py | 820 | CODE | |
| LOW | …rc/longwam/datasets/lerobot/lerobot/lerobot_dataset.py | 1158 | CODE | |
| LOW | …g-WAM/src/longwam/datasets/lerobot/utils/normalizer.py | 233 | CODE | |
| LOW | Long-WAM/src/longwam/runtime/factory.py | 93 | CODE | |
| LOW | Long-WAM/src/longwam/runtime/factory.py | 180 | CODE | |
| LOW | Long-WAM/src/longwam/runtime/factory.py | 343 | CODE | |
| LOW | Long-WAM/src/longwam/runtime/factory.py | 477 | CODE | |
| LOW | Long-WAM/src/longwam/utils/pytorch_utils.py | 121 | CODE | |
| LOW | Long-WAM/src/longwam/models/wan22/longwam_idm.py | 240 | CODE | |
| LOW | Long-WAM/src/longwam/models/wan22/longwam_idm.py | 279 | CODE | |
| LOW | Long-WAM/src/longwam/models/wan22/longwam_base.py | 48 | CODE | |
| LOW | Long-WAM/src/longwam/models/wan22/longwam_base.py | 141 | CODE | |
| LOW | Long-WAM/src/longwam/models/wan22/longwam_base.py | 1182 | CODE | |
| LOW | Long-WAM/src/longwam/models/wan22/longwam_base.py | 1362 | CODE | |
| LOW | Long-WAM/src/longwam/models/wan22/longwam_base.py | 1729 | CODE | |
| LOW | Long-WAM/src/longwam/models/wan22/longwam_base.py | 2017 | CODE | |
| LOW | Long-WAM/src/longwam/models/wan22/wan22.py | 56 | CODE | |
| LOW | Long-WAM/src/longwam/models/wan22/wan22.py | 284 | CODE | |
| LOW | …WAM/src/longwam/models/wan22/wan_video_text_encoder.py | 239 | CODE | |
| 72 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1187 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1189 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1198 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1200 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1238 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1240 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 259 | # ------------------------------- | STRING |
| MEDIUM | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 262 | # ------------------------------- | STRING |
| MEDIUM | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 277 | # ------------------------------- | STRING |
| MEDIUM | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 282 | # ------------------------------- | STRING |
| MEDIUM | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 1230 | # ========================================== | STRING |
| MEDIUM | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 1232 | # ========================================== | STRING |
| MEDIUM | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 1244 | # ========================================== | STRING |
| MEDIUM | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 1246 | # ========================================== | STRING |
| MEDIUM | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 1263 | # ========================================== | STRING |
| MEDIUM | …e1/third_party/LongLive/wan_5b/modules/causal_model.py | 1265 | # ========================================== | STRING |
| MEDIUM | …AM/stage1/third_party/LongLive/trainer/distillation.py | 612 | # ---------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …AM/stage1/third_party/LongLive/trainer/distillation.py | 614 | # ---------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1343 | # -------------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1345 | # -------------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | LongLive1.0/trainer/distillation.py | 440 | # ---------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | LongLive1.0/trainer/distillation.py | 442 | # ---------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | LongLive1.0/trainer/distillation.py | 1458 | # -------------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | LongLive1.0/trainer/distillation.py | 1460 | # -------------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | LongLive2.0/utils/dataset.py | 164 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | LongLive2.0/utils/dataset.py | 166 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | LongLive2.0/utils/dataset.py | 175 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | LongLive2.0/utils/dataset.py | 177 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | LongLive2.0/utils/dataset.py | 215 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | LongLive2.0/utils/dataset.py | 217 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | LongLive2.0/wan_5b/modules/causal_model.py | 246 | # ------------------------------- | STRING |
| MEDIUM | LongLive2.0/wan_5b/modules/causal_model.py | 249 | # ------------------------------- | STRING |
| MEDIUM | LongLive2.0/wan_5b/modules/causal_model.py | 264 | # ------------------------------- | STRING |
| MEDIUM | LongLive2.0/wan_5b/modules/causal_model.py | 269 | # ------------------------------- | STRING |
| MEDIUM | LongLive2.0/wan_5b/modules/causal_model.py | 1217 | # ========================================== | STRING |
| MEDIUM | LongLive2.0/wan_5b/modules/causal_model.py | 1219 | # ========================================== | STRING |
| MEDIUM | LongLive2.0/wan_5b/modules/causal_model.py | 1231 | # ========================================== | STRING |
| MEDIUM | LongLive2.0/wan_5b/modules/causal_model.py | 1233 | # ========================================== | STRING |
| MEDIUM | LongLive2.0/wan_5b/modules/causal_model.py | 1250 | # ========================================== | STRING |
| MEDIUM | LongLive2.0/wan_5b/modules/causal_model.py | 1252 | # ========================================== | STRING |
| MEDIUM | LongLive2.0/trainer/distillation.py | 600 | # ---------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | LongLive2.0/trainer/distillation.py | 602 | # ---------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | LongLive2.0/trainer/distillation.py | 1331 | # -------------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | LongLive2.0/trainer/distillation.py | 1333 | # -------------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | LongLive-Plug/trainer/distillation.py | 671 | # ---------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | LongLive-Plug/trainer/distillation.py | 673 | # ---------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | LongLive-Plug/trainer/distillation.py | 1838 | # -------------------------------------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | LongLive-Plug/trainer/distillation.py | 1840 | # -------------------------------------------------------------------------------------------------------------- | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …g-WAM/stage1/third_party/LongLive/pipeline/__init__.py | 13 | __all__ = [ | CODE |
| LOW | …party/LongLive/fouroversix/src/fouroversix/__init__.py | 27 | __all__ = [ | CODE |
| LOW | …gLive/fouroversix/src/fouroversix/quantize/__init__.py | 16 | __all__ = ["QuantizationConfig", "QuantizedTensor", "get_rht_matrix", "quantize_to_fp4"] | CODE |
| LOW | …/fouroversix/src/fouroversix/quantize/cuda/__init__.py | 13 | __all__ = ["CUDAQuantizeBackend"] | CODE |
| LOW | …ouroversix/src/fouroversix/quantize/triton/__init__.py | 13 | __all__ = ["TritonQuantizeBackend"] | CODE |
| LOW | …uroversix/src/fouroversix/quantize/pytorch/__init__.py | 13 | __all__ = ["PyTorchQuantizeBackend"] | CODE |
| LOW | …oversix/src/fouroversix/weight_conversions/__init__.py | 23 | __all__ = ["FourOverSixGptOssDeserialize", "GptOssWeightConverter", "WeightConversions"] | CODE |
| LOW | …LongLive/fouroversix/src/fouroversix/model/__init__.py | 15 | __all__ = [ | CODE |
| LOW | …/fouroversix/src/fouroversix/model/modules/__init__.py | 16 | __all__ = ["FourOverSixGptOssMLP", "FourOverSixLinear"] | CODE |
| LOW | …ongLive/fouroversix/src/fouroversix/matmul/__init__.py | 13 | __all__ = ["fp4_matmul"] | CODE |
| LOW | …fouroversix/src/fouroversix/matmul/cutlass/__init__.py | 13 | __all__ = ["CUTLASSMatmulBackend"] | CODE |
| LOW | …-WAM/stage1/third_party/LongLive/utils/nvfp4_kernel.py | 32 | __all__ = ["fp4_dequantize", "static_blockwise_fp4_fake_quant"] | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/wan_5b/__init__.py | 14 | __all__ = ["WanI2V", "WanT2V", "WanTI2V"] | CODE |
| LOW | …stage1/third_party/LongLive/wan_5b/distributed/util.py | 51 | __all__ = [ | CODE |
| LOW | …ge1/third_party/LongLive/wan_5b/distributed/ulysses.py | 58 | __all__ = ["distributed_attention", "distributed_flex_attention"] | CODE |
| LOW | …M/stage1/third_party/LongLive/wan_5b/utils/__init__.py | 20 | __all__ = [ | CODE |
| LOW | …-WAM/stage1/third_party/LongLive/wan_5b/utils/utils.py | 23 | __all__ = ['save_video', 'save_image', 'str2bool'] | CODE |
| LOW | …ge1/third_party/LongLive/wan_5b/utils/qwen_vl_utils.py | 36 | logger = logging.getLogger(__name__) | CODE |
| LOW | …tage1/third_party/LongLive/wan_5b/modules/attention.py | 89 | __all__ = [ | CODE |
| LOW | …M/stage1/third_party/LongLive/wan_5b/modules/vae2_1.py | 21 | __all__ = [ | CODE |
| LOW | …g-WAM/stage1/third_party/LongLive/wan_5b/modules/t5.py | 25 | __all__ = [ | CODE |
| LOW | …stage1/third_party/LongLive/wan_5b/modules/__init__.py | 20 | __all__ = [ | CODE |
| LOW | …AM/stage1/third_party/LongLive/wan_5b/modules/model.py | 23 | __all__ = ['WanModel'] | CODE |
| LOW | …M/stage1/third_party/LongLive/wan_5b/modules/vae2_2.py | 21 | __all__ = [ | CODE |
| LOW | …age1/third_party/LongLive/wan_5b/modules/tokenizers.py | 20 | __all__ = ['HuggingfaceTokenizer'] | CODE |
| LOW | Long-WAM/stage1/third_party/LongLive/model/__init__.py | 12 | __all__ = [ | CODE |
| LOW | …ng-WAM/stage1/third_party/LongLive/trainer/__init__.py | 13 | __all__ = [ | CODE |
| LOW | …g-WAM/stage1/third_party/LongLive/trainer/sp_helper.py | 28 | __all__ = ["DEFAULT_SP_VAE_HALO_LATENTS", "SequenceParallelHelper"] | CODE |
| LOW | …AM/third_party/fouroversix/src/fouroversix/__init__.py | 27 | __all__ = [ | CODE |
| LOW | …party/fouroversix/src/fouroversix/quantize/__init__.py | 16 | __all__ = ["QuantizationConfig", "QuantizedTensor", "get_rht_matrix", "quantize_to_fp4"] | CODE |
| LOW | …/fouroversix/src/fouroversix/quantize/cuda/__init__.py | 13 | __all__ = ["CUDAQuantizeBackend"] | CODE |
| LOW | …ouroversix/src/fouroversix/quantize/triton/__init__.py | 13 | __all__ = ["TritonQuantizeBackend"] | CODE |
| LOW | …uroversix/src/fouroversix/quantize/pytorch/__init__.py | 13 | __all__ = ["PyTorchQuantizeBackend"] | CODE |
| LOW | …oversix/src/fouroversix/weight_conversions/__init__.py | 23 | __all__ = ["FourOverSixGptOssDeserialize", "GptOssWeightConverter", "WeightConversions"] | CODE |
| LOW | …rd_party/fouroversix/src/fouroversix/model/__init__.py | 15 | __all__ = [ | CODE |
| LOW | …/fouroversix/src/fouroversix/model/modules/__init__.py | 15 | __all__ = ["FourOverSixGptOssMLP", "FourOverSixLinear", "FourOverSixQwenExperts"] | CODE |
| LOW | …d_party/fouroversix/src/fouroversix/matmul/__init__.py | 13 | __all__ = ["fp4_matmul"] | CODE |
| LOW | …fouroversix/src/fouroversix/matmul/cutlass/__init__.py | 13 | __all__ = ["CUTLASSMatmulBackend"] | CODE |
| LOW | …src/longwam/datasets/lerobot/gr1_tabletop_omissions.py | 209 | __all__ = [ | CODE |
| LOW | …gwam/datasets/lerobot/robocasa_gr1_tabletop_dataset.py | 162 | def set_epoch(self, epoch: int) -> None: | CODE |
| LOW | …gwam/datasets/lerobot/robocasa_gr1_tabletop_dataset.py | 763 | def set_epoch(self, epoch: int) -> None: | CODE |
| LOW | …gwam/datasets/lerobot/robocasa_gr1_tabletop_dataset.py | 788 | __all__ = [ | CODE |
| LOW | …AM/src/longwam/datasets/lerobot/gr1_tabletop_recipe.py | 139 | __all__ = [ | CODE |
| LOW | …rc/longwam/datasets/lerobot/lerobot/lerobot_dataset.py | 357 | def update_video_info(self) -> None: | CODE |
| LOW | Long-WAM/src/longwam/runtime/robotwin.py | 25 | logger = logging.getLogger(__name__) | CODE |
| LOW | Long-WAM/src/longwam/runtime/optim/projections.py | 408 | def set_kv_cache_quantizer(self, quantizer) -> None: | CODE |
| LOW⚡ | Long-WAM/src/longwam/utils/index_manifest_sampler.py | 770 | def set_epoch(self, epoch: int) -> None: | CODE |
| LOW⚡ | Long-WAM/src/longwam/utils/index_manifest_sampler.py | 778 | def set_epoch_offset(self, epoch_offset: int) -> None: | CODE |
| LOW⚡ | Long-WAM/src/longwam/utils/index_manifest_sampler.py | 784 | def set_resume_batch_offset(self, batch_in_epoch: int) -> None: | CODE |
| LOW | Long-WAM/src/longwam/utils/pytorch_utils.py | 53 | def set_model_initialization_seed(seed: int) -> None: | CODE |
| LOW | Long-WAM/src/longwam/utils/__init__.py | 12 | __all__ = ["ensure_dir", "save_mp4"] | CODE |
| LOW | Long-WAM/src/longwam/agentic/__init__.py | 26 | __all__ = [ | CODE |
| LOW | Long-WAM/src/longwam/models/wan22/long_wam.py | 20 | logger = logging.getLogger(__name__) | CODE |
| LOW | Long-WAM/src/longwam/models/wan22/helpers/__init__.py | 16 | __all__ = [ | CODE |
| LOW | …ng-WAM/src/longwam/benchmarks/robocasa_gr1/__init__.py | 24 | __all__ = ["TASK_SPECS", "TaskSpec"] | CODE |
| LOW | …ng-WAM/src/longwam/benchmarks/robocasa_gr1/contract.py | 605 | def _update_length_prefixed(digest: Any, value: bytes) -> None: | CODE |
| LOW | LongLive1.0/pipeline/__init__.py | 8 | __all__ = [ | CODE |
| LOW | LongLive1.0/wan/utils/__init__.py | 5 | __all__ = [ | CODE |
| LOW | LongLive1.0/wan/utils/utils.py | 11 | __all__ = ['cache_video', 'cache_image', 'str2bool'] | CODE |
| LOW | LongLive1.0/wan/utils/qwen_vl_utils.py | 23 | logger = logging.getLogger(__name__) | CODE |
| 48 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1147 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1150 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1151 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1155 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1181 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1185 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1187 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1189 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1191 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1192 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1193 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1200 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1202 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1207 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1208 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1215 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1219 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1239 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1248 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1253 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1262 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1266 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1269 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 1270 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1087 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1090 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1091 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1095 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1121 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1125 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1127 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1129 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1131 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1132 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1133 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1140 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1142 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1147 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1148 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1155 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1159 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1179 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1188 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1193 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1202 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1206 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1209 | CODE | |
| MEDIUM | LongLive1.0/wan/modules/causal_model.py | 1210 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | …-WAM/stage1/third_party/LongLive/wan_5b/utils/utils.py | 91 | Convert a string to a boolean. Supported true values: 'yes', 'true', 't', 'y', '1' Supported false values: | STRING |
| HIGH | …ge1/third_party/LongLive/wan_5b/utils/qwen_vl_utils.py | 151 | calculate the number of frames for video used for model inputs. Args: ele (dict): a dict contains the confi | STRING |
| HIGH | …src/longwam/datasets/lerobot/lerobot/datasets/utils.py | 598 | This check is to make sure that each timestamp is separated from the next by (1/fps) +/- tolerance to account f | STRING |
| HIGH | LongLive1.0/wan/utils/utils.py | 95 | Convert a string to a boolean. Supported true values: 'yes', 'true', 't', 'y', '1' Supported false values: | STRING |
| HIGH | LongLive1.0/wan/utils/qwen_vl_utils.py | 138 | calculate the number of frames for video used for model inputs. Args: ele (dict): a dict contains the confi | STRING |
| HIGH | LongLive2.0/wan_5b/utils/utils.py | 80 | Convert a string to a boolean. Supported true values: 'yes', 'true', 't', 'y', '1' Supported false values: | STRING |
| HIGH | LongLive2.0/wan_5b/utils/qwen_vl_utils.py | 138 | calculate the number of frames for video used for model inputs. Args: ele (dict): a dict contains the confi | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1287 | # Define the specific modules we want to apply LoRA to | COMMENT |
| MEDIUM | …WAM/src/longwam/benchmarks/libero/summarize_results.py | 83 | # Create the task identifier (suite_taskid) | COMMENT |
| MEDIUM | …WAM/src/longwam/benchmarks/libero/summarize_results.py | 219 | # Create the per-task success-rate CSV | COMMENT |
| MEDIUM | LongLive1.0/pipeline/streaming_switch_training.py | 284 | # Create an appropriate BlockMask for recomputation | COMMENT |
| MEDIUM | LongLive1.0/utils/lora_utils.py | 34 | # Define the specific modules we want to apply LoRA to | COMMENT |
| MEDIUM | LongLive1.0/wan/modules/causal_model_infinity.py | 292 | # Create a grid_sizes for the cached K | STRING |
| MEDIUM⚡ | LongLive1.0/trainer/distillation.py | 1403 | # Define the specific modules we want to apply LoRA to | COMMENT |
| MEDIUM⚡ | LongLive2.0/trainer/distillation.py | 1275 | # Define the specific modules we want to apply LoRA to | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | Long-WAM/stage1/third_party/LongLive/utils/dataset.py | 1502 | # Check if we have enough frames for all segments | COMMENT |
| LOW | …AM/stage1/third_party/LongLive/trainer/distillation.py | 1167 | # Check if we should train generator on this optimization step | COMMENT |
| LOW | …ngwam/datasets/lerobot/lerobot/datasets/video_utils.py | 446 | # Check if ffmpeg is available | COMMENT |
| LOW | …src/longwam/datasets/lerobot/lerobot/datasets/utils.py | 633 | # Check if all remaining diffs are within tolerance | COMMENT |
| LOW | LongLive1.0/model/streaming_training.py | 139 | # Check if the model supports switching (DMDSwitch) | COMMENT |
| LOW | LongLive1.0/model/streaming_training.py | 160 | # Check if the switch point falls within the current chunk range [chunk_start_frame, chunk_start_frame + chunk_s | COMMENT |
| LOW | LongLive1.0/model/streaming_training.py | 438 | # Check if previous_frames can be used for overlap and auto-compute overlap frame count | COMMENT |
| LOW | LongLive1.0/trainer/distillation.py | 1176 | # Check if we should train generator on this optimization step | COMMENT |
| LOW | LongLive2.0/utils/dataset.py | 589 | # Check if we have enough frames for all segments | COMMENT |
| LOW | LongLive2.0/trainer/distillation.py | 1155 | # Check if we should train generator on this optimization step | COMMENT |
| LOW | LongLive-Plug/trainer/distillation.py | 1528 | # Check if we should train generator on this optimization step | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| CRITICAL | …ive2.0/fouroversix/scripts/ptq/evaluators/spinquant.py | 230 | model.lm_head.weight.data = model.model.embed_tokens.weight.data.clone() | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | Long-WAM/README.md | 104 | - [Agentic API + Long-WAM](#agentic-api--long-wam) | CODE |
| MEDIUM | Long-WAM/README.md | 329 | The [Agentic experiment](#agentic-api--long-wam) uses a separate protocol. | CODE |
| MEDIUM | Long-WAM/configs/eval/robocasa365.yaml | 28 | split: pretrain # Human300 zero-shot Target50 protocol; target is a different split. | CODE |
| MEDIUM | Long-WAM/configs/eval/robocasa365_gpt6.yaml | 20 | # Compatibility recipe. Prefer robocasa365_agentic.yaml and agentic.* overrides. | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | Long-WAM/stage1/third_party/LongLive/model/base.py | 62 | self.fake_model_name = getattr(args, "fake_name", "Wan2.2-TI2V-5B") | CODE |
| LOW | LongLive1.0/configs/longlive_train_init.yaml | 7 | fake_name: Wan2.1-T2V-1.3B | CODE |
| LOW | LongLive1.0/configs/longlive_train_long.yaml | 7 | fake_name: Wan2.1-T2V-1.3B | CODE |
| LOW | LongLive1.0/model/base.py | 31 | self.fake_model_name = getattr(args, "fake_name", "Wan2.1-T2V-1.3B") | CODE |
| LOW | LongLive2.0/model/base.py | 51 | self.fake_model_name = getattr(args, "fake_name", "Wan2.2-TI2V-5B") | CODE |
| LOW | LongLive-Plug/model/base.py | 34 | self.fake_model_name = getattr(args, "fake_name", model_name) | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | …ss/include/cutlass/gemm/kernel/tile_scheduler_params.h | 920 | // the problem can leverage a basic split-K decomposition for the stream-K tiles. | COMMENT |
| MEDIUM | …rc/longwam/datasets/lerobot/lerobot/lerobot_dataset.py | 1173 | """Create a LeRobot Dataset from scratch in order to record data.""" | STRING |