Plugins

1 plugin

Deploy AI Inference on GKE

Deploy and optimize AI/ML inference workloads on GKE using GPUs, TPUs, and model servers.

3 skills · plugin

Results for “gpu”

16 skills

cupynumeric-install

Install and verify cuPyNumeric for Python using conda or pip, including GPU usage checks.

dynamo-recipe-runner

Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes for model serving with GPU support.

Deploy and scale Python AI/ML workloads on Modal's serverless cloud, including GPU compute, web endpoints, scheduled jobs, and persistent storage.

huggingface-zerogpu

Build ML demos on Hugging Face Spaces with ZeroGPU hardware, covering @spaces.GPU decorator usage, duration and quota tuning, process isolation, CUDA availability model, concurrency safety, and build constraints.

10.8k · bundle

jetson-init-image

Extract Jetson Linux BSP and sample-rootfs tarballs, run apply_binaries.sh with the correct GPU stack flag, and record the image metadata in the active target profile.

Build, deploy, evaluate, debug, and measure latency for a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection and VLM classification.

More results

vss-deploy-video-embedding

Deploy and operate the VSS 3.2 GA RT-Embed Video Embedding microservice using Docker Compose, covering GPU prerequisites, REST API usage for file uploads, text/video embeddings, live RTSP streams, Redis/Kafka/OTel integration, and troubleshooting.

holoscan-install-wheel

Install the Holoscan SDK Python wheel via pip into a virtual environment and verify with example scripts.

amc-setup-calibration-stack

Deploy the AutoMagicCalib microservice and web UI from pre-built NGC release images using Docker Compose.

holoscan-install-debian

Install the Holoscan SDK C++ runtime and headers on Ubuntu using NVIDIA's apt repository, with automatic CUDA variant detection and verification via bundled examples.

vss-deploy-profile

Selects, configures, deploys, verifies, debugs, or tears down a VSS profile (base, search, lvs, warehouse, edge) for NVIDIA's video search and summarization stack.

jetson-customize-clocks

Lock, cap, or customize CPU, GPU, and EMC clock behavior on NVIDIA Jetson devices by editing BPMP DTB and nvpower.sh before flashing.

building-inferencesh-apps

Build and deploy applications on the inference.sh platform using Python or Node.js, with CLI scaffolding, local testing, and cloud deployment.

vss-deploy-dense-captioning

Deploy a standalone RT-VLM dense-captioning microservice and exercise its REST API endpoints for file upload, caption generation, streaming, chat completions, and Kafka integration.

mcore-run-on-slurm

Launch distributed Megatron-LM training jobs on a SLURM cluster with a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules, container conventions, monitoring, and per-rank failure diagnosis.

dynamo-interconnect-check

Validates that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after deploying a disagg or multi-node recipe to confirm KV transport is correct, or use troubleshoot for already-failed pods.