|

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster...

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization...

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code....

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for...

Guidance for asking clarifying questions when user requests are ambiguous, have multiple valid approaches, or require critical decisions. Use when implementation choices exist that could...

Create production-grade frontend interfaces with strong UX and visual craft. Use when building web components, pages, dashboards, forms, landing pages, or any UI. Use when user says 'build a...

Comprehensive on-page SEO and content quality audit covering title tags, meta descriptions, header structure, keyword optimization, E-E-A-T signals, readability, and content scoring. Use when...

Interact with a web browser. Can start a browser, connect to it, evaluate JavaScript, make screenshots, read console logs and let the user select DOM elements. Use when interacting with unknown...

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture...

Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical...

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange...

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...

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or...

|

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring...

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4,...

The Ultimate Collection of 200+ Agentic Skills for Claude Code/Antigravity/Cursor. Battle-tested, high-performance skills for AI agents including official skills from Anthropic and Vercel.

Web fuzzing with ffuf