Loading...
Loading...
Found 317 Skills
Profiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.
NVIDIA copyright header requirements for NeMo-RL. Covers which files need headers and the exact header text.
Produce video analysis reports by discovering the deployed VSS agent, querying POST /generate for a timestamped captioned summary of the clip, then formatting the agent reply as the standard Video Analysis Report markdown.
ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must involve Triton explicitly. Covers Triton-specific patterns: fused elementwise, reductions (softmax, LayerNorm, RMSNorm), tiled GEMM with triton.autotune, and flash attention. Workflow: design, write, verify (with fast-path for explicit requests).
Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.
Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from single RGB images. Use when training, evaluating, exporting, or running inference for a TAO monocular depth model. Trigger phrases include "train monocular depth", "DepthAnything v2", "metric depth from single image", "monocular depth estimation".
SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction, efficient for real-time segmentation tasks. Use when training, evaluating, exporting, quantizing, or running inference for a TAO SegFormer model. Trigger phrases include "train SegFormer", "semantic segmentation", "lightweight transformer segmenter", "real-time semantic segmentation".
Pick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM 11.0 and JetPack-specific package choices.