为 LightX2V 新模型或新推理路径实现、审查、调试和评测 `use_compile`/`torch.compile`。适用于普通推理以及模型原本已支持的 CPU offload model、block、phase 和 lazy-load；指导确认支持矩阵，选择 block/phase 编译边界与缓存键，处理层号、staging buffer、动态 guider、第三方算子、Dynamo 重编译，并用可信 warmup 区分首次编译成本、正式请求延迟和稳态收益。
为尚无 warmup 的 LightX2V 模型或新任务设计、实现、审查和验证 `--warmup`。先核对普通推理、CPU offload model/block/phase 和 lazy-load block/phase 的原生与 warmup 支持范围，再复用 Wan/Qwen-Image/LTX2/Lingbot-Video 经验覆盖 compile、MoE、多阶段或并行路径，检查 Encoder、DiT、scheduler 和 VAE decode 是否真正预热，并排查正式 Step 1…
审查并简化 AI 生成感较重的代码，重点移除内部配置路径中的过度防御、输入格式穷举、无依据的能力拦截、冗余异常和模板化注释，同时保留防止静默错误的算法与领域边界。用于用户要求“去 AI 味”、简化代码、删除过度防御、按项目约定而非不可信输入编程，或逐处审查可疑 guard、validation 和 comment 时。
Use this skill when adding native LightX2V support for a new model or task: understand an upstream inference repo, map it onto LightX2V runner/model/weight/infer/scheduler/input-encoder/VAE conventions, convert or load weights, add configs and Wan-style…
Full pipeline for turning a SYCL/ESIMD GPU kernel into a Python-importable wheel package on Windows with Intel oneAPI 2025.x and conda. Covers every layer of the stack: ESIMD kernel (.cpp/.h) → Windows DLL (icpx) → PyTorch C++ extension (.pyd, CMake) → Python…
LSC 2D block load/store, 1D block load/store, and gather/scatter operations in Intel ESIMD. Use this skill when working with lsc_load_2d, lsc_store_2d, lsc_prefetch_2d, config_2d_mem_access, block_load, block_store, gather, or scatter in ESIMD kernels. Covers…
LSC Shared Local Memory (SLM) operations in Intel ESIMD. Use this skill when working with slm_init, slm_block_load, slm_block_store, lsc_slm_gather, lsc_slm_scatter, SLM layout design, barrier synchronization, named barriers, cooperative SLM loading, or any…
Foundational Intel ESIMD GPU programming skill. Use this skill proactively whenever the user is writing, optimizing, or debugging any SYCL/ESIMD kernel for Intel GPUs — including Intel Arc, Iris Xe, or Data Center GPU Max. Covers kernel design, memory access…