New to Claude Skills? Learn how to install them →

Performance skills

Free performance skills for AI coding agents, part of our developer tools collection.

C

cuTile Kernel Performance Optimization

nvidia

Optimize cuTile kernel performance iteratively and systematically.

Developer ToolsintermediateShell2.8k repo

RAG-Perf

nvidia

Benchmark performance of NVIDIA RAG Blueprint servers.

Developer ToolsintermediatePython · Shell2.8k repo

PhysicsNeMo ShardTensor

nvidia

Optimize domain parallelism for PyTorch models.

Developer ToolsadvancedShell2.8k repo
O

Omniverse USD Performance Tuning

nvidia

Optimize USD performance for better loading and rendering.

Developer ToolsintermediatePython · Shell2.8k repo
M

Megatron Bridge Resiliency

nvidia

Enhance fault tolerance and performance in distributed training.

Developer ToolsintermediateShell2.8k repo
S

Sequence Packing

nvidia

Optimize sequence packing for LLMs and VLMs in Megatron-Bridge.

Developer ToolsintermediateShell2.8k repo
P

Parallelism Strategy Selection

nvidia

Optimize parallelism for Megatron Bridge models effectively.

Developer ToolsintermediateShell2.8k repo
M

MoE Hardware Configurations

nvidia

Optimize your MoE training across hardware platforms.

Developer ToolsintermediateShell2.8k repo
M

MoE Dispatcher Selection

nvidia

Optimize your MoE token dispatcher for peak performance.

Developer ToolsintermediateShell2.8k repo
M

MoE Communication Overlap

nvidia

Optimize expert-parallel communication in Megatron Bridge.

Developer ToolsadvancedPython · Shell2.8k repo

Memory Tuning

nvidia

Optimize GPU memory usage during training runs.

Developer ToolsintermediateShell2.8k repo
H

Hierarchical Context Parallel

nvidia

Optimize Megatron-Bridge for hierarchical context parallelism.

Developer ToolsintermediateShell2.8k repo

MoE Expert-Parallel Overlap

nvidia

Optimize MoE model performance with expert-parallel communication.

Developer ToolsintermediatePython · Shell2.8k repo

CUDA Graphs

nvidia

Optimize GPU performance with CUDA graph capture.

Developer ToolsintermediatePython · Shell2.8k repo
C

CPU Offloading

nvidia

Optimize memory usage by offloading CPU tasks in Megatron Bridge.

Developer ToolsintermediatePython · Shell2.8k repo

Activation Recompute

nvidia

Optimize GPU memory usage with activation recompute.

Developer ToolsintermediatePython · Shell2.8k repo

NeMo Evaluator Plugin

nvidia

Evaluate models and datasets efficiently with NeMo.

Developer ToolsintermediatePython · Shell2.8k repo

Jetson Print Device Info

nvidia

Capture essential Jetson device details effortlessly.

Developer ToolsbeginnerShell2.8k repo
J

Jetson Memory Optimizer

nvidia

Optimize DRAM usage for Jetson devices.

Developer ToolsintermediateShell2.8k repo
J

Jetson Inference Memory Tuning

nvidia

Optimize memory settings for LLM/VLM on NVIDIA Jetson.

Developer ToolsintermediatePython · Shell2.8k repo

DeepStream Profiling

nvidia

Efficiently profile and tune DeepStream pipelines.

Developer ToolsintermediatePython · Shell2.8k repo

Accelerated Computing cuDF

nvidia

Efficient GPU DataFrame operations for pandas users.

Developer ToolsintermediatePython · Shell2.8k repo
T

TP DP PP Communication Overlap

nvidia

Optimize Megatron-Bridge for efficient communication overlap.

Developer ToolsintermediateShell2.8k repo

Megatron FSDP

nvidia

Optimize distributed training with Megatron FSDP.

Developer ToolsintermediatePython · Shell2.8k repo