Diagnoses wrong gradients in differentiable NVIDIA Warp programs by measuring first — comparing autodiff against finite differences on a shrunk reproduction before proposing any fix.
20 views 1 copies
NVIDIA
NVIDIA's accelerated computing stack — CUDA, cuDF, DALI, Dynamo and inference blueprints.
18 skills and 2 MCP servers tagged NVIDIA.
Skills
Skill: NVIDIA Skill Card Generator
by NVIDIA
Generates or refreshes an NVIDIA governance skill card for an existing agent skill — discovers assets, renders a deterministic markdown card, and blocks submission while human-review markers remain.
6 views
Skill: NVIDIA TAO RT-DETR
by NVIDIA
Trains, distils, quantises, evaluates, exports and runs inference for RT-DETR real-time object detection in NVIDIA TAO, routing training through AutoML hyperparameter search by default.
8 views
Skill: NVIDIA Holoscan SDK Setup
by NVIDIA
Inspects the host's hardware, OS, CUDA driver and existing tooling, recommends one Holoscan SDK install method with a reason, then hands off to the matching install skill.
6 views
Skill: NVIDIA NV-Reason-CXR
by NVIDIA
Runs NVIDIA's NV-Reason-CXR-3B chest X-ray reasoning model through a documented wrapper, locally on GPU or via the public Hugging Face Space, and returns the model's full reasoning trace as engineering evidence.
6 views
Skill: Jetson LLM Serve
by NVIDIA
Picks the right vLLM or SGLang runtime for your Jetson generation and JetPack version, then produces a working OpenAI-compatible serving command.
12 views
Skill: Portfolio Optimization with cuOpt
by NVIDIA
GPU-accelerated Mean-CVaR and Mean-Variance portfolio construction with NVIDIA cuOpt: scenario generation, variance-capped SOCP allocations, efficient frontiers, backtests and rebalancing.
11 views
Turns a plain-language weather question into a working Earth2Studio inference script — picks the AI forecast model, a compatible data source, an IO backend, and the step count.
8 views
Skill: NVIDIA VSS Video Q&A
by NVIDIA
NVIDIA's official skill for asking a vision-language model fresh questions about recorded video through the Video Search and Summarization blueprint — only when the pixels actually need looking at.
11 views
Skill: NVIDIA NeMo Data Designer
by NVIDIA
NVIDIA's official skill for building synthetic datasets with NeMo Data Designer — describe the data you want and the agent writes a declarative generation pipeline, column by column.
9 views
NVIDIA's official skill for deploying and operating Nemotron Speech (Riva) NIMs — ASR, text-to-speech and translation, cloud-hosted or self-hosted on your own GPUs.
9 views
Skill: NVIDIA DALI Dynamic Mode
by NVIDIA
NVIDIA's official skill for DALI's imperative dynamic-mode API — write GPU data loading as ordinary Python, or migrate an existing pipeline-mode graph across.
10 views
NVIDIA's official skill for generating and validating runnable gst-launch DeepStream pipelines from a plain-language description of the video inference you want.
12 views
Skill: NVIDIA CUDA-Q Onboarding
by NVIDIA
NVIDIA's official onboarding skill for CUDA-Q — installs the platform, writes your first quantum kernel, picks a GPU simulator and routes you to real QPU hardware.
11 views
Skill: Dynamo Router Starter
by NVIDIA
NVIDIA's official skill for bringing up Dynamo inference routing — pick a router mode, enable KV-aware routing, and smoke-test the frontend endpoint before claiming anything works.
12 views
Skill: NVIDIA RAG Blueprint
by NVIDIA
Deploy, configure and troubleshoot the NVIDIA RAG Blueprint from your agent — Docker Compose, Helm or library, with feature toggles for VLM, guardrails and agentic RAG.
26 views
Skill: NVIDIA cuDF Accelerated Computing
by NVIDIA
NVIDIA's own guidance for moving pandas workloads onto GPU DataFrames with cuDF and dask-cuDF — when it pays off, and how to keep results identical.
8 views
NVIDIA-verified skill that takes an agent from a problem described in prose to a correct LP, MILP, or QP formulation — concepts, not API calls.
12 views
MCP servers
NVIDIA's official MCP server for the Elements design system — component APIs, design tokens, icons and validated project scaffolding for AI/ML and robotics UIs.
3 views
NVIDIA's official remote MCP server for CUDA: grounds a coding agent in first-party CUDA documentation and code samples instead of its training data.
4 views
Related tags
Tags that appear alongside this one, ranked by how often.