Results for “layernorm”

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

NLVR2: A Visual Reasoning Benchmark for Natural Language

Scales reinforcement learning with PufferLib — high-throughput parallel training (PuffeRL), vectorized environments, and native multi-agent systems achieving 2-10x speedups over standard implementations. Use when scaling RL to millions of steps per second, running vectorized or multi-agent setups, building custom PufferEnv tasks, or integrating game environments (Atari, Procgen, NetHack, PettingZoo). For standard single-agent algorithm implementations (PPO/SAC/DQN) or quick prototyping prefer alterlab-stable-baselines3. Part of the AlterLab Academic Skills suite.

Wraps RDKit in a high-level, pandas-friendly datamol interface with sensible defaults for everyday drug discovery — SMILES/SDF loading into DataFrames, molecule standardization, descriptors, fingerprints, Butina clustering, 3D conformer generation, scaffold analysis, and parallel batch processing, returning native rdkit.Chem.Mol objects. Use when running standard cheminformatics pipelines on molecule tables with minimal boilerplate; for low-level control, custom sanitization, or specialized algorithms prefer alterlab-rdkit. Part of the AlterLab Academic Skills suite.

DCLM: DataComp for Language Models

ImageNet: A Large-Scale Hierarchical Image Database

GLaMM: Pixel Grounding Large Multimodal Model

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.

Create landscape materials with layer blending, texture setup, and layer info objects (LandscapeMaterialService). Use when the user asks to build a landscape/terrain material, set up paint layers (grass/rock/dirt), create layer info objects, add a grass output, or assign a material to a landscape. For production master-material+RVT systems, load landscape-auto-material.

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.

ByteDance's open-source super agent harness — spawns parallel sub-agents, Docker sandbox execution, persistent long-term memory, modular skills (research/report/slides). Built on LangChain + LangGraph. Triggers on: 'deerflow', 'deer-flow', 'bytedance agent', 'super agent harness', 'LangGraph agent orchestration', 'multi-hour agent tasks', 'spawn sub-agents', 'agent sandbox docker', 'persistent agent memory', 'agent skills system', 'AI research orchestrator', 'long-running agent tasks', 'agent with memory', 'langgraph orchestrator', 'IM channel agent integration'.

Design, select, and analyze waveforms for radar, sonar, and active sensing using the Phased Array System Toolbox. Covers LFM, NLFM, FMCW, phase-coded, CW, stepped FM, custom IQ, ambiguity functions, sidelobe reduction, and Doppler tolerance. Key objects: phased.LinearFMWaveform, phased.NonlinearFMWaveform, phased.CustomFMWaveform, phased.PhaseCodedWaveform, phased.FMCWWaveform, phased.SteppedFMWaveform, phased.MFSKWaveform, phased.RectangularWaveform, nlfmspec2freq, shapespectrum, ambgfun, pambgfun, sidelobelevel, legendreseq, mlseq, radarWaveformGenerator.

Applies medicinal-chemistry filters with the medchem library — drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, and molecular complexity metrics for compound prioritization and library cleanup. Use when filtering or triaging a compound library, flagging PAINS or reactive groups, or assessing drug-likeness of candidate molecules. Part of the AlterLab Academic Skills suite.

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when "langgraph, langchain agent, stateful agent, agent graph, react agent, agent workflow, multi-step agent, langgraph, langchain, agents, state-machine, workflow, graph, ai-agents, orchestration" mentioned.

Build production-grade stateful AI agents using LangGraph, covering graph construction, state management, persistence, and human-in-the-loop patterns.

Use when building stateful multi-step agents, agent graphs, or workflows with LLMs. Triggers on: 'langgraph', 'state graph', 'stateful agent', 'agent workflow', 'agent loop', 'multi-step agent', 'persistent agent', 'human-in-the-loop agent', 'agent with memory', 'graph-based agent'.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Documents Linear's dark-canvas marketing design system with near-black backgrounds, lavender-blue accent, four-step surface hierarchy, aggressive negative tracking on display type, and product UI screenshots as the primary visual rhythm.

Creates, analyzes, and visualizes complex networks and graphs in Python with NetworkX. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing topologies — applicable to social, biological, transportation, citation, and any pairwise-relationship networks. This is classical graph analytics, not deep learning — for training graph neural networks (GCN/message passing, node/edge/graph classification on Cora-style data) use alterlab-torch-geometric instead. Part of the AlterLab Academic Skills suite.

Linting, formatting, and encoding standards for the AegisNex codebase. Covers ruff, mypy, eslint, editorconfig, pre-commit hooks, and how to add new quality checks.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

LoRA: Low-Rank Adaptation of Large Language Models

Liquid Network: federated sidechain by Blockstream. Confidential Transactions, asset issuance (LBTC, USDt-Liquid, others), 2-min blocks, n-of-m federation peg-out. Elements codebase. USE WHEN: building on Liquid, peg-in/peg-out integrations, designing CT-based privacy.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.

Expert skill for building LLM applications with LangChain — LCEL chains, RAG pipelines, agent orchestration, LangGraph integration, LangSmith observability, and production deployment via LangServe. Use when working with LangChain or comparing LLM application frameworks.

Nocaps: Novel Object Captioning at Scale

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern.

嵌入式网络调试工具，用于发现接口、抓包、分析 pcap/pcapng、做连通性测试、端口扫描和流量统计。 当用户提到 Wireshark、tshark、Npcap、抓包、网络联调、端口扫描、连通性排查、pcap 分析、 网络接口、ping 测试、traceroute、流量统计、Modbus TCP、EtherNet/IP 等网络协议调试时自动触发， 也兼容 /net 显式调用。即使用户只是说"抓个包看看"、"扫一下端口"、"网络通不通"或"分析一下这个 pcap"， 只要上下文中出现具体工具名（tshark、Wireshark、Npcap）、协议名（Modbus TCP、EtherNet/IP、ICMP 等）、 调试动作（抓包、端口扫描、连通性测试、ping、traceroute、流量统计、pcap 分析）或网络接口操作，就应触发此 skill。

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support