Skill UI

Orchestrates PyTorch-native TorchTitan 4D parallelism (FSDP2, TP, PP, CP) for large-scale LLM pretraining, scaling from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing to boot Llama 3.1, DeepSeek V3, or custom models.

Execute complex and compute-intensive workloads directly on fully managed Hugging Face cloud infrastructure. This skill eliminates the need for local setup, allowing users to run jobs using cloud CPUs, GPUs, or TPUs. Ideal for large-scale data processing, batch inference, reproducible model training, and scheduled automation tasks, while persisting results to the Hugging Face Hub.

This skill provides comprehensive guidance on training Mixture of Experts (MoE) models, including architectures like Mixtral and DeepSeek-V3. It details techniques for achieving large-scale model capacity with significantly reduced computational costs (e.g., 5x reduction vs. dense models). Topics covered include top-k routing, load balancing, expert parallelism, and integration with frameworks like DeepSpeed and HuggingFace for efficient, resource-constrained training.

torchforge is Meta's advanced PyTorch-native library designed for agentic Reinforcement Learning (RL). It fundamentally separates core RL algorithms from complex distributed infrastructure concerns. This allows researchers to rapidly prototype and experiment with novel RL methods (like GRPO) using clean, PyTorch-native abstractions, while automatically handling large-scale tasks like distributed training across thousands of GPUs using Monarch and TorchTitan.

This advanced workflow orchestrates complex, multi-node GPU clusters on Vast.ai. It is designed for large-scale distributed machine learning training, automatically handling spot instance preemption and resuming jobs from checkpoints. Furthermore, it provides comprehensive cost analysis by tracking billing history, allowing users to optimize GPU spending and manage cluster teardown efficiently.

This guide details how to set up and execute large-scale, distributed GPU training jobs on the CoreWeave platform. It covers both single-node multi-GPU setups and multi-node training utilizing PyTorch DDP and Kubernetes resources (A100/H100). This workflow is ideal for fine-tuning large language models (LLMs) or running complex deep learning models that require high-performance, shared-storage compute clusters.

This skill guides the secure handling and lifecycle management of large-scale data artifacts, including training datasets, model weights, and checkpoint snapshots, within GPU cloud environments. It provides best practices for data pipelines, covering secure import via Kubernetes PVCs, compliant export, and stringent data validation, ensuring adherence to encryption standards (AES-256) and regulatory requirements (PII masking, RBAC).

This guide provides expert strategies for optimizing GPU inference performance on CoreWeave infrastructure. It covers GPU selection based on workload (LLM, image generation, training), advanced techniques like continuous batching (using vLLM), autoscaling setup (HPA), and benchmarking data. Use this to maximize GPU utilization, minimize latency, and optimize large-scale AI model deployment.

A comprehensive solution for monitoring CoreWeave cluster events and GPU workload status using webhooks. It tracks critical lifecycle events such as pod readiness, job completion, volume attachment, and node health. Essential for building automated scaling, alerting, and recovery pipelines for large-scale GPU-accelerated inference and training workloads.

This skill dispatches computationally intensive quantitative trading jobs (such as multi-year walk-forward analysis, large Monte-Carlo simulations, parameter sweeping, or deep model training) to a managed cloud agent runtime. It is designed for large-scale, production-grade backtesting that exceeds local machine capacity, ensuring robust execution and artifact management via Anthropic's cloud services.

Expert guidance for implementing distributed training with DeepSpeed, covering ZeRO optimization stages, pipeline parallelism, mixed precision (FP16/BF16/FP8), and I/O optimizations like DeepNVMe. Helps with debugging, API usage, and best practices for large-scale model training on NVIDIA GPUs.

Megatron-Core is a production-ready framework for training large language models ranging from 2B to 462B parameters. It utilizes advanced parallelism strategies like tensor, pipeline, and expert parallelism to maximize GPU efficiency on NVIDIA H100 hardware. Ideal for scaling models beyond 1B parameters with high MFU performance.