Loading...
Loading...
Found 401 Skills
Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the Hyperloom multi-agent optimizer. Given a model, framework, workload (TP/EP, concurrency, ISL/OSL, precision), an objective and a time budget, it explores per-workload which levers to pull (serving/config parameters and env, framework enablement and source patches, and hot GPU-kernel rewrites), benchmarks each candidate, and returns the optimization stack that produced the gain. Use when the user wants to make a model serve faster, raise tokens/sec or throughput, optimize or tune vLLM or SGLang on MI300X/MI325X/MI355X, run Hyperloom, run the kernel-agent, quantize-then-optimize with Quark, set up Hyperloom from scratch, or resume a Hyperloom session. Do not use to stand up a server for plain serving, diagnose a broken ROCm install, or run a one-off kernel/benchmark or trace analysis without the optimization loop.
Perform SGLang code review in the style of human maintainers by consulting the 2024-2025 non-agent PR review corpus, including inline code snippets, original multilingual comments, and discussion threads. Use when reviewing SGLang PRs, diffs, patches, or local changes for correctness, tests, performance, GPU/runtime risks, API compatibility, and maintainability.
Serves AI models on AMD Instinct GPU hardware using vLLM. Use this skill whenever the user wants to run, serve, deploy, start, host, or launch a language model on an AMD GPU, AMD Instinct, MI300X, MI325X, MI350X, or MI355X. Also use when the user mentions vLLM on ROCm, vLLM on AMD, serving on HBM, or asks how to get a model running on AMD data center hardware. Use when the user asks "run Qwen3", "serve DeepSeek", "start a vLLM endpoint", "get a model running on my AMD machine", or any similar phrasing. Handles the full flow: GPU detection, environment validation, vLLM configuration, launch, and health verification. Do not use for NVIDIA GPUs, consumer AMD GPUs (RX series, Radeon), Ryzen AI, NPU, MI250X, or MI100.
Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.
Benchmarks LLM inference and drives GPU kernel optimization with Magpie. Use when the user wants to benchmark vLLM, SGLang, or Atom; capture torch traces; post-process inference traces with TraceLens into prefill/decode and roofline reports; identify top bottleneck kernels or map profiler names to source; analyze or compare HIP, CUDA, PyTorch, or Triton kernels; validate and rank optimized variants; run local, container, or Ray workloads; or mentions Magpie, TraceLens, gap analysis, TTFT, TPOT, kernel evaluation, or AMD GPU optimization.
Build native UIs in the style of Raph Levien, architect of Druid, Xilem, and Vello. Emphasizes declarative reactive architecture, synchronized tree transformations, GPU-accelerated rendering, and idiomatic Rust patterns. Use when designing responsive, beautiful native UIs or 2D graphics systems.
The basics of how to program GPUs using Mojo. Use this skill in addition to mojo-syntax when writing Mojo code that targets GPUs or other accelerators. Use targeting code to NVIDIA, AMD, Apple silicon GPUs, or others. Use this skill to overcome misconceptions about how Mojo GPU code is written.
Runpod CLI for managing GPU/CPU workloads from the terminal — pods, serverless endpoints, templates, network volumes, Hub deploys, models, SSH, and file transfer (send/receive). Use for terminal/CI/scripting, Hub browse/deploy, SSH setup, `doctor`, or when the Runpod MCP tools are not connected. For structured tool calls in an MCP-enabled session, prefer runpod-mcp.
This skill should be used when the user asks to "build a particle system", "make confetti/snow/smoke/sparks", "create a connected-dot/constellation network background", "add a flow-field or curl-noise particle effect", "render thousands of GPU particles with Three.js Points", or "animate emitters with forces". Covers per-particle integration, forces, flow fields, burst/continuous emission, spatial-grid connected dots, and GPU points + shaders.
Brev managed GPU instances with Docker support. Use when running TAO training, evaluation, or inference on Brev GPU instances, managing Brev deployments, or dispatching TAO jobs through the Brev CLI. Trigger phrases include "run on Brev", "Brev GPU instance", "submit job to Brev", "Brev CLI deployment".
Manage Runpod infrastructure — pods, serverless endpoints, jobs, templates, network volumes, container-registry auth, GPU/CPU catalog, and billing — via the Runpod MCP server's structured tool calls. Use when the Runpod MCP tools (create-pod, list-endpoints, …) are connected in this session, or to connect them (hosted OAuth or local npx). Prefer this over runpodctl for plain infra CRUD when MCP is available; use runpodctl for the terminal, file transfer, or SSH setup.
Novita AI: LLM, Image Generation & Editing, Video Generation, Audio (TTS/ASR), and GPU Cloud. Use this skill whenever the user wants to call Novita AI APIs — chat with LLMs (DeepSeek, Llama, Qwen), generate images (FLUX, Stable Diffusion, Seedream, Hunyuan Image), edit images (remove background, upscale, inpainting, img2img, outpainting, reimagine, merge face, replace background, remove text), generate videos (Kling, Wan, Hunyuan, Minimax Hailuo, Vidu, PixVerse, Seedance), do text-to-speech or speech-to-text (MiniMax TTS, GLM TTS, Fish Audio, ASR, voice cloning), run OpenAI-compatible batch jobs, manage GPU cloud instances and serverless endpoints, or check account balance and billing. Also trigger when the user mentions novita.ai, Novita AI, Novita API key, or wants to use any Novita platform service — even if they just say "generate an image" or "run an LLM" and Novita is available as a provider.