787 skills · sorted by relevance
Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.
Organize PyTorch training code with LightningModule and Trainer. This skill guides training, validation, logging, model checkpoint saving, early stopping when progress stalls, and configuration for running the same model across multiple GPUs.
Evaluate Hugging Face Hub models using inspect-ai or lighteval, with local inference or a provider-backed option. Choose an inference engine, start with a small test, and switch engines when model compatibility requires it.
Find skills for tasks involving NVIDIA products or GPU computing using the live catalog. Get up to three relevant recommendations, with reasons, installation commands, and starter prompts; installation requires explicit approval.
Create interactive views of dense datasets, spatial paths, and flows using WebGL, which uses the GPU for rendering. Choose suitable libraries and design navigation, labels, animation, and static alternatives around the analytical task.
Prepare detailed 3D materials that remain clear in close-up views. The skill guides texture resolution, physically based material maps, surface mapping, filtering, and progressive loading while checking download size and GPU memory use.
Run demanding scientific work on SSH compute hosts using direct execution or Slurm, a cluster job scheduler. Choose an enabled host, submit background jobs, check progress, collect outputs, and continue with analysis and artifact publication.
Write, review, and optimize Three.js scenes using guidance on memory cleanup, rendering, models, textures, and lighting. Apply examples to reduce unnecessary work, investigate memory leaks, and adjust 3D experiences for mobile devices.
Fix Cloud Run GPU deployment failures caused by quota errors. Use when: (1) `gcloud run deploy` fails with "You do not have quota for using GPUs with zonal redundancy" AND "You do not have quota for using GPUs without zonal redundancy", (2) The service already exists and is running with a GPU, (3) You only need to update the container image, not change GPU config. Uses `gcloud run services update --image` instead of `gcloud run deploy` to bypass quota re-validation on existing GPU services.
The English summary is being prepared. Showing the original description.
Build and extend pd-console — Port Daddy's GPU-native macOS operator console (GPUI 0.2.x, Zed's Rust UI). Covers the render-agnostic Block/Pane(Surface) contract, the two-thread reqwest↔smol refresh pipeline, Taffy flexbox layout, uniform_list virtual scroll, focus + keyboard nav, the OKLCH theme and ICS maritime flag badges, GPUI's missing text-input, and the real feature-gated cargo/CI gate. Use when adding panes, visual polish, or debugging GPUI rendering/layout/focus in core/pd-console. NOT for the TypeScript daemon, generic Rust toolchain/borrow-checker help (use rust-with-claude-code), or non-pd GPUI apps with a different theme/architecture.
The English summary is being prepared. Showing the original description.
Create full-screen animated visuals with WebGL, a browser technology for GPU rendering. Combine shaders, 3D scenes, or particles with a text overlay, and deliver the result as one self-contained HTML file without external requests.
Prepare and review LoRA or QLoRA settings for adapting language models using example responses. Choose trainable layers, adapter capacity, learning rate, and memory-related options, then produce configuration values for a downstream training script.
Collect and review SGLang startup logs to identify unnecessary output and trace its source. Get saved logs and specific cleanup proposals while preserving useful diagnostics, with runtime changes left for user approval.
Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.
Plans, executes, and validates Google Kubernetes Engine upgrades for Standard and Autopilot clusters. Creates environment-specific upgrade plans, checklists, and command-based runbooks, with guidance on maintenance timing, node upgrade strategies, workload readiness, and stalled upgrades.
Guides fine-tuning and evaluation of OpenVLA-OFT robot models that turn images and language into actions. Covers LIBERO simulation, ALOHA deployment, LoRA adaptation that updates a small set of parameters, and troubleshooting action scaling or configuration mismatches.
Build LLM serving workflows that produce JSON or other required formats. The skill covers reusing computation for shared prompts, tool calls, and ongoing conversations, with examples for server setup and structured output.
Guides experiments that inspect and modify internal values in PyTorch models to study their effects on predictions. Covers local analysis and remote experiments through NDIF for models too large for local GPUs.
Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.
Helps fine-tune large language models with LoRA and QLoRA, methods that train small sets of additional parameters. Covers memory-conscious training, configuration choices, saving adapters, and switching task-specific adapters on a shared base model.
Estimate inference memory for models on Hugging Face Hub without downloading their weights. Check GPU capacity for Safetensors or GGUF files, with optional estimates for the KV cache, memory used to retain attention data during generation.
Search Hugging Face Hub for models, datasets, papers, and AI apps. Inspect documentation, use hosted apps for image generation or transcription, and run or schedule code on cloud CPUs and GPUs through an MCP server connection.
Add a white, twinkling dotted trail that follows the mouse behind website content. The skill guides WebGPU rendering, which uses the graphics processor, with static backgrounds for unsupported devices and accessibility preferences.
Build chat, image generation, and speech transcription features on 0G Compute Network, a distributed GPU marketplace. This skill guides SDK integration, model fine-tuning, response processing for billing, and account funding through code patterns and CLI commands.