159 skills · sorted by relevance
Implement or debug Hugging Face Spaces ZeroGPU code using `@spaces.GPU`, including isolation, state, duration, sizing, and CUDA-wheel constraints. Use for ZeroGPU-specific behavior; use huggingface-spaces for general hosting.
The English summary is being prepared. Showing the original description.
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
The English summary is being prepared. Showing the original description.
Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.
The English summary is being prepared. Showing the original description.
Expert guide for Backend.AI distributed computing platform. Automatically activates when users ask about: - Backend.AI architecture, components (Manager, Agent, Storage Proxy, Webserver, App Proxy) - Features (session scheduling, Sokovan orchestrator, multi-tenancy, resource allocation) - APIs (REST, GraphQL), authentication, RBAC authorization - Container runtime (kernels, jail sandbox, hook library, virtual folders) - Accelerator support (CUDA, ROCm, TPU, NPU, Graphcore IPU) - Client SDKs (Python, Java, JavaScript, PHP) - Setup, requirements (Python 3.13+, Docker, PostgreSQL, Redis, etcd) - How WebUI connects to/interacts with Backend.AI backend - Plugin interfaces, development setup, infrastructure Use when user mentions "Backend.AI", "backend.ai", "Sokovan", component names, or asks about the backend platform this WebUI connects to. allowed-tools: WebFetch, Read
The English summary is being prepared. Showing the original description.
Use Gaussian-SLAM for CUDA RGB-D dense SLAM, Gaussian-splatting mapping, dataset/configuration preflight, checkpoint evaluation, reconstruction metrics, and global-map refinement.
The English summary is being prepared. Showing the original description.
Routes official FlashVSR diffusion-based streaming video super-resolution setup, model preparation, and CUDA inference for v1 and v1.1.
The English summary is being prepared. Showing the original description.
Use the faster-whisper package for CTranslate2-backed Whisper transcription, model selection, CPU/CUDA setup, audio utilities, VAD, timestamps, and conversion guidance.
The English summary is being prepared. Showing the original description.
Routes DINO DETR object-detection setup, COCO data validation, CUDA deformable-attention preparation, training, evaluation, inference, visualization, and bounded benchmarking tasks.
The English summary is being prepared. Showing the original description.
Use DreamCraft3D for image-conditioned 3D generation, staged optimization, texture boosting, export, and CUDA troubleshooting.
The English summary is being prepared. Showing the original description.
Guide Det3D PyTorch 3D object-detection workflows across configuration, KITTI/nuScenes/Lyft data preparation, GPU training and evaluation, custom CUDA operations, and visualization.
The English summary is being prepared. Showing the original description.
Guide DeepMedic 0.8.4 workflows for multi-modal 3D NIFTI medical-image segmentation, including data preparation, model configuration, training, checkpoint continuation, inference, and CPU/CUDA troubleshooting.
The English summary is being prepared. Showing the original description.
Guides CUDA-accelerated cuRobo v2 robotics workflows for robot models, differentiable kinematics, collision-aware IK and motion planning, trajectory optimization, MPC, perception mapping, and motion retargeting.
The English summary is being prepared. Showing the original description.
Routes Big Sleep text-to-image workflows, CUDA setup checks, prompt controls, and Python API usage for the `dream` CLI and `Imagine` API.
The English summary is being prepared. Showing the original description.
Guides Attention-Gated Networks PyTorch medical imaging workflows for ultrasound classification, attention-gated U-Net segmentation, data layout, CUDA setup, and visualization helpers.
The English summary is being prepared. Showing the original description.
Guides CUDA-based BigGAN-PyTorch training, checkpoint sampling, dataset preparation, metric preparation, model customization, and optional TensorFlow Hub weight conversion.
The English summary is being prepared. Showing the original description.
Guide CUDA-enabled BindCraft protein-binder design from target PDB preparation through AF2/MPNN/PyRosetta execution, filtering, output analysis, and conservative troubleshooting.
The English summary is being prepared. Showing the original description.
Use the ALAE repository for Adversarial Latent Autoencoder data preparation, CUDA training, checkpoint-backed generation, latent editing, and legacy metrics.
The English summary is being prepared. Showing the original description.
Think and work like an expert High-Performance Computing Specialist. Use when a task calls for High-Performance Computing Specialist judgment. Reasons from NUMA topology and hybrid MPI+OpenMP+CUDA decomposition through Slurm fairshare/backfill job design, strong/weak scaling (Amdahl/Gustafson), Darshan/mpiP/Nsight profiling, and parallel HDF5/MPI-IO on Lustre while treating I/O storms, collectives bottlenecks, and rank-binding mistakes as first-class failure modes.
The English summary is being prepared. Showing the original description.
Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder). Covers two workflow patterns: (1) MathWorks-native or 3P-imported models rebuilt as dlnetwork for lean hardware (Cortex-M, DSP), (2) direct C/C++ code generation from PyTorch and LiteRT models for high-performance hardware (Cortex-A, x86, GPU). Trigger when: user wants to deploy AI to embedded targets; generate C/CUDA from neural networks; compress AI models for MCU/DSP; integrate AI in Simulink for system-level simulation; import PyTorch/ONNX/TensorFlow models for embedded deployment; optimize AI for resource-constrained hardware; or use loadPyTorchExportedProgram, importNetworkFromPyTorch, dlquantizer, exportNetworkToSimulink, or Embedded Coder with AI models.
The English summary is being prepared. Showing the original description.
Let AKA autonomously add, run, inspect, and revise intra-kernel timeline probes for standalone CUDA/inline PTX or CuTe DSL when ordinary benchmark, NSYS, or NCU evidence cannot answer a specific kernel-internal timing question.
The English summary is being prepared. Showing the original description.
Use when verifying that a model in the imp inference engine produces coherent output without repetition loops, token-stuck states, or state corruption across turns or streams. Triggers on "degenerates", "check degeneration", "repetition loop", "own own own", "stuck token", "empty content", "multi-turn regression", "does it still work", "NIAH", and after enabling CUDA graphs / changing forward pass / MoE routing / KV cache or KV dtype / GDN state or scan / sparse attention / PDL / speculation (MTP, n-gram) / ragged prefill / batched-decode kernels (smallm, producer quantize) / FA2 softmax.
The English summary is being prepared. Showing the original description.
Use when imp outputs differ between two paths that should agree - chunk sizes, prefill vs decode, prefix-cache resend, two engines (imp vs llama.cpp vs HF), two builds or kernels - "output changes with chunk size", "first token differs", "logprobs moved", "which layer diverges", "who is right, imp or llama.cpp", "near-tie". Do NOT use for repetition loops or garbage output (check-degeneration), a new arch that loads wrong (add-model-arch), or perf (benchmark-cuda).
The English summary is being prepared. Showing the original description.
Use when keeping imp's docs and config examples coherent after a change - updating docs/internals/ARCHITECTURE.md / README / docs/GOAL.md / docs/MODELS.md / docs/ROADMAP.md / imp.conf.example / CHANGELOG / MISSION_JOURNAL, or "is this doc stale", "document this change", "the example config is out of date", "the README says X but the code does Y", "add a roadmap ledger row". Do NOT use for layer/frontmatter/lint questions (docs-layers), structural code audits (codebase-audit), measuring perf or refreshing the perf baseline (benchmark-cuda), or the agent's private memory (MEMORY.md).
The English summary is being prepared. Showing the original description.
Use when adding support for a new model architecture to imp, porting a model family, or debugging a model that loads but produces wrong output - "add support for <model>", "new arch", loader detection, chat template, tokenizer parity, RoPE variant, "outputs garbage", "prompt-blind", "digits scrambled", "NaN logits", "describes a different picture", "does it fit in VRAM". Do NOT use for kernel performance (sm120-cuda-expert) or quant-format questions (quant-formats).
The English summary is being prepared. Showing the original description.