Results for “moead”

Solve single and multi-objective optimization problems using NSGA-II/III, MOEA/D, and other evolutionary algorithms with customizable operators, constraint handling, and benchmark problems.

Provides guidance for training Mixture-of-Experts models with long context windows, covering context parallelism sizing, selective recomputation, dispatcher choices, and practical patterns from recent experiments.

Optimizes MoE expert-parallel communication overlap in Megatron Bridge, covering dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace, covering architectures, routing, load balancing, and expert parallelism.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Orchestrates three frontier models to debate a question and synthesizes their best insights into a single superior answer.

Provides practical guidance for training Mixture-of-Experts Vision-Language Models in Megatron Bridge, comparing FSDP and 3D-parallel approaches with lessons from recent multimodal experiments.

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

This skill should be used when working with BMAD (BMad-CORE) v6-alpha projects. BMAD is a universal human-AI collaboration platform with specialized modules for software development (BMM), agent building (BMB), creative intelligence (CIS), and project management (BMD). Use this skill to understand agent workflows, command patterns, scale-adaptive methodology, and effective utilization of the four-phase development system.

Configure Cedar policy enforcement and Ed25519 signed receipts for Claude Code tool calls. Use when setting up projects that need cryptographic audit trails, policy-gated tool execution, or compliance-ready evidence of agent actions.

Build cross-platform AI chat interfaces with Makepad using MolyKit, including async utilities, chat widgets, and OpenAI-compatible client integration.

Implement Microsoft's Enhanced Security Admin Environment (ESAE) tiered administration model for Active Directory, covering Tier 0/1/2 separation, privileged access workstations, and credential theft mitigation.

AI-driven Game Development Studio (BMAD-GDS). Routes game projects through Pre-production, Design, Architecture, Production, and Game Testing phases using 6 specialized agents. Supports Unity, Unreal Engine, Godot, and custom engines.

Runs a Node.js CLI that sends a question to three frontier LLMs in parallel, then synthesizes their responses into a single answer via an aggregator model, with paid and free tiers.

Audits AGENTS.md and CLAUDE.md files for bloat, redundancy, and ineffective rules, then runs A/B evals to prove which instructions are dead weight.

Packet-first BMAD/BMM front door for idea notes, product briefs, PRDs, architecture drafts, review feedback, existing repo state, and milestone pressure. Use when the user wants to know what BMAD phase or artifact comes next, or needs a portable BMAD entrypoint before routing review, execution slicing, runtime setup, or game-production work outward.

Orchestrates group discussions between installed BMAD agents, enabling natural multi-agent conversations where each agent is a real subagent with independent thinking. Use when user requests party mode, wants multiple agent perspectives, group discussion, roundtable, or multi-agent conversation about their project.

Authors and updates customization overrides for installed BMad skills. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', or 'customize a workflow'.

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.

Solve single- and multi-objective optimization problems with NSGA-II/III, MOEA/D, and other evolutionary algorithms, including Pareto front analysis, constraint handling, and benchmarking on standard test problems.