Best GPU agent skills
Accelerated computing on GPUs, from CUDA workloads to rented inference and training capacity. The 15 highest-ranked of the 17 agent skills tagged GPU in the Onei AI catalogue.
Everything tagged GPU: apps, skills and MCP servers
-
by NVIDIA
Diagnoses wrong gradients in differentiable NVIDIA Warp programs by measuring first — comparing autodiff against finite differences on a shrunk reproduction before proposing any fix.
Also: NVIDIA, Python, Simulation · Editor's pick · Copied 1 time
-
by NVIDIA
Picks the right vLLM or SGLang runtime for your Jetson generation and JetPack version, then produces a working OpenAI-compatible serving command.
Also: Deployment, Inference, NVIDIA
-
by AMD
AMD's official skill for benchmarking vLLM/SGLang inference and driving GPU kernel optimization with Magpie and TraceLens trace analysis.
Also: Official
-
by Hugging Face
Fine-tune object detection, image classification and SAM/SAM2 segmentation models on Hugging Face Jobs cloud GPUs, with dataset validation before you spend GPU minutes.
Also: Fine-tuning, Python
-
by Hugging Face
Fine-tune language and vision models with TRL or Unsloth — supervised, preference, and reinforcement training methods.
Also: Fine-tuning, Python
-
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.
Also: Fine-tuning, Inference, NVIDIA
-
by AWS Labs
Read-only diagnostics for cluster-wide SageMaker HyperPod failures on EKS or Slurm — CloudFormation errors, EFA health checks, lifecycle scripts, capacity, dangling nodes and autoscaler conflicts.
Also: Official
-
by Hugging Face
Deploy and maintain applications on Hugging Face Spaces — SDK choice, GPU hardware, model loading, and debugging.
Also: Deployment, Python
-
by NVIDIA
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.
-
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.
-
by NVIDIA
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.
-
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.
Also: NVIDIA
-
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.
Also: NVIDIA, Simulation
-
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.
Also: NVIDIA
-
by AMD
AMD's official skill for standing up a vLLM endpoint on Instinct MI300X/MI325X/MI350X/MI355X GPUs — detection, recipe lookup, launch and health check in one flow.
Also: Deployment, Inference, Official
How this list is ranked
Ranked by 20 points for an editor's pick, plus 4 points per copy of the install command or SKILL.md up to 10, plus a point per 5 page views up to 100; ties go to the most recently updated. Discontinued skills are never ranked.