Loading…
hyperloom-workload-optimizer
Cursor Skill
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-wo
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom, and analyze GPU kernel and PyTorch trace performance.
Created by AMDView Source
Skills5
local-ai-useMakes this agent generate images, transcribe audio, and synthesize speech on the user's own machine through a local Lemonade Server instead of a paid cloud API. Use it above all to change that routing persistently, from now on — keep generating pictures locally while chat stays o
local-ai-app-integrationIntegrates local AI capabilities into applications using Embeddable Lemonade. Use when the user wants to add local AI, offline AI, private AI, on-device AI, a local LLM, local chat, embeddings, image generation, speech-to-text, or text-to-speech to an existing app; replace or sup
serving-llms-on-instinctServes 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 AM
tracelens-analysis-orchestratorOrchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf reports, prepares category data, runs system-level and compute-kernel subagents in parallel, validates outputs, and writes a prioritized stakeholder report (analysis.md). Use when the user asks to
hyperloom-workload-optimizerAutonomously 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-wo
Related plugins
SenseLab
Continual learning for your agents. What one works out carries across sessions, tools and machines, is reinforced by how the work turned out, and is shared through team rooms.
Grimoire's Tome
The full AI Prompt Spellbook: vibecoding dev flows, the Grim Council of advisors, AutoDocs, and workbench artifacts.
UserTesting
Bring real customer feedback into Cursor — create, launch, and retrieve UserTesting results without leaving your editor.
Dash Security
Discover your AI estate, assess supply-chain and shadow AI risk, investigate agent sessions, and track AI spend through the Dash MCP.
Transcend Agent Governance
Connect Cursor to Transcend Agent Governance for policy-enforced MCP tool access via browser sign-in.
Bird
Drive Bird from your coding agent: operate the Bird API from the terminal with the `bird` CLI, send across email, SMS, and WhatsApp, and audit a domain's email authentication.