القائمة
Use during /add-model Phase 4 or Phase 6 to prototype or parity-debug one FastVideo-native DiT/transformer component.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Re-seed the HF performance-tracking baseline for an intentional runtime, dependency, environment-caused benchmark shift, or reviewed v2 calibration using one or more reviewed normalized performance JSONs. Use when performance CI fails because metrics such as latency, throughput, component time, or peak memory changed for an accepted reason and the rolling median baseline in FastVideo/performance-tracking must be advanced, or when a new v2 exact comparable identity needs its first approved baseline. The workflow backs up existing history under /tmp, validates all source JSONs for the same legacy (model_id, gpu_type) target or the same v2 exact identity, rejects internally inconsistent source batches, uploads one success=true baseline record per accepted source JSON, and offers to clean local temp state after a successful upload.
Seed HF reference artefacts for a single newly-added SSIM test (pixel `.mp4` for `run_text_to_video_similarity_test`-style tests, or latent `.pt` for `run_text_to_latent_similarity_test`-style tests). Runs the test on Modal L40S, downloads the generated artefacts via `modal volume get`, pauses for the user to verify (visual eyeball for mp4, numerics dump for pt), then uploads only that test's files to `FastVideo/ssim-reference-videos`. Use when a new `fastvideo/tests/ssim/test_*_similarity.py` has just been added and has no references on HF yet.
Manual /add-model workflow for implementing a FastVideo model or first-class component port after add-model-01-prep has staged reference code and weights. Organizes the port into numbered phases with conversion rules, component policies, parity gates, and handoff checks.
Decompose an oversized FastVideo pipeline PR into a stack of independently-reviewable PRs. Tiers the diff by blast radius (invisible / dead code / cross-cutting infra / activation), produces a branch graph and worktree bootstrap, drafts the AGENTS.md manifest, flags missing tests on cross-cutting infra changes, and extracts lessons from the PR body.
Use when redeploying the migrated Dreamverse app backend and frontend on a chosen local GPU; tears down existing ports, launches services, and waits for readiness checks.
Use during /add-model after reference/architecture study to scaffold and later activate local FastVideo component parity tests. Emphasizes early test creation, official-reference loading, standardized FastVideo loading, and non-skip handoff gates.
| name | add-model-03-port-dit |
| description | Use during /add-model Phase 4 or Phase 6 to prototype or parity-debug one FastVideo-native DiT/transformer component. |
Prototype or parity-debug one diffusion transformer in FastVideo-native code. This skill is for one component only; do not work on the VAE, encoders, pipeline, or unrelated conversion code unless the current component cannot load without a minimal fix there.
Follow ../add-model/shared/component_skill_common.md and require the complete
packet from ../add-model/contracts/component_context.md.
DiT-specific packet fields:
component: transformer or DiT name.parity_test: tests/local_tests/<bucket>/test_<family>_<component>_parity.py.weights: converted transformer dir or local official path.target_files: fastvideo/models/dits/<family>.py and
fastvideo/configs/models/dits/<family>.py.Use the common prototype and parity-debug modes from
../add-model/shared/component_skill_common.md.
DiT-specific prototype concerns include ambiguous official flags, shape mismatches, missing FastVideo layer equivalents, and dedicated output heads.
Apply the shared reuse proof. DiT-specific comparison must include attention algorithm, positional embeddings, RoPE/patching, timestep/guidance embeddings, scaling constants, dtype casts, state-dict names, and every output head.
fastvideo/models/dits/base.py::BaseDiT.DiTConfig and DiTArchConfig in
fastvideo/configs/models/dits/base.py.fastvideo/configs/models/dits/__init__.py.EntryClass = <ClassName> in the model file.TransformerLoader reads transformer/config.json, calls
dit_config.update_model_arch(config), resolves _class_name through
ModelRegistry, and constructs the class with config and hf_config.stable_audio.py, wanvideo.py, sd3.py, longcat.py,
and ltx2.py.fastvideo/layers/AGENTS.md.ReplicatedLinear for DiT hot-path
linears, DistributedAttention for standard full-sequence attention, and
LocalAttention for local/window attention or simple single-GPU parity paths.DiTArchConfig; keep inference steps, CFG scales,
FPS, flow shift, and sampling defaults out of the arch config._fsdp_shard_conditions, _compile_conditions,
param_names_mapping, and reverse_param_names_mapping where needed.../add-model/shared/common_rules.md.Follow the shared prototype success criteria. A useful one-off check is:
python - <<'PY'
# Import the target config/class, instantiate with random weights, and print
# state_dict names/shapes for the conversion mapping.
PY
Run the shared parity-debug loop. The component test command is:
pytest <parity_test> -v -s
For numerical drift, use ../add-model-08-trace/SKILL.md before writing bespoke
hooks. Start with FastVideo's activation trace (fastvideo/hooks/activation_trace.py;
docs/contributing/activation_trace.md) and a block-level regex such as
FASTVIDEO_TRACE_LAYERS="^block\.layers\.[0-9]+$". Only fall back to custom
per-block hooks if the needed boundary or statistic is not exposed by
FASTVIDEO_TRACE_STATS.
Follow ../add-model/shared/common_rules.md and the component-specific guidance
in ../add-model/shared/component_skill_common.md. DiT-specific ask cases include
dropping an output head/modality, accepting an unsupported kernel/private op, or
choosing between incompatible official transformer definitions.
Return ../add-model/contracts/component_skill_handoff.md following the common
handoff rules in ../add-model/shared/component_skill_common.md.