Performance skills
Free performance skills for AI coding agents, part of our developer tools collection.
13 skills
CuTile Autotuning
nvidia
Optimize CuTile kernels with automated tuning techniques.
RAG-Perf
nvidia
Benchmark performance of NVIDIA RAG Blueprint servers.
Omniverse USD Performance Tuning
nvidia
Optimize USD performance for better loading and rendering.
MoE Communication Overlap
nvidia
Optimize expert-parallel communication in Megatron Bridge.
MoE Expert-Parallel Overlap
nvidia
Optimize MoE model performance with expert-parallel communication.
CUDA Graphs
nvidia
Optimize GPU performance with CUDA graph capture.
CPU Offloading
nvidia
Optimize memory usage by offloading CPU tasks in Megatron Bridge.
Activation Recompute
nvidia
Optimize GPU memory usage with activation recompute.
NeMo Evaluator Plugin
nvidia
Evaluate models and datasets efficiently with NeMo.
Jetson Inference Memory Tuning
nvidia
Optimize memory settings for LLM/VLM on NVIDIA Jetson.
DeepStream Profiling
nvidia
Efficiently profile and tune DeepStream pipelines.
Accelerated Computing cuDF
nvidia
Efficient GPU DataFrame operations for pandas users.
Megatron FSDP
nvidia
Optimize distributed training with Megatron FSDP.
