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...
458 results
(6.0ms)
page 3 / 23
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,...
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,...
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory...
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory...
swiftui-animation
0.00
This skill provides comprehensive guidance for implementing advanced SwiftUI animations, transitions, matched geometry effects, and Metal shader integration. Use when building animations, view...
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON...
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON...
rocky-virtualization
0.00
KVM/QEMU virtualization on Rocky Linux 8/9 including libvirt, virsh, virt-manager, virt-install, VM lifecycle management, storage pools, network configuration (NAT/bridged/macvtap), snapshots,...
hugging-face-jobs
0.00
This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with...
webgpu-threejs-tsl
0.00
Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders,...
awq-quantization
0.00
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster...
Expert in script-to-video production pipelines for Apple Silicon Macs. Specializes in hybrid local/cloud workflows, LoRA training for character consistency, motion graphics generation, and artist...
webgl-expert
0.00
Expert guide for WebGL API development including 3D graphics, shaders (GLSL), rendering pipeline, textures, buffers, performance optimization, and canvas rendering. Use when working with WebGL, 3D...
drone-cv-expert
0.00
Expert in drone systems, computer vision, and autonomous navigation. Specializes in flight control, SLAM, object detection, sensor fusion, and path planning. Activate on "drone", "UAV", "SLAM",...
peft-fine-tuning
0.00
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with...
Mine ALL past Claude conversations to build a living 'User Manual About You'. Extract writing style, business context, goals, preferences, and patterns. Make all other skills smarter with context.
Generate optimized scripts that utilize the specific hardware (cores, GPU, OS) of the execution environment.
interpolation
0.00
Techniques for 1D and 2D data interpolation using SciPy (CPU) and JAX/Interpax (GPU/Differentiable).
nemo-guardrails
0.00
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses...