Results for “triton-inference-server”

Serve LLMs and VLMs on NVIDIA Jetson devices using vLLM or SGLang with optimized Docker containers and quantization presets.

Start, query, and stop a TAO inference microservice for a specific network architecture by delegating container execution to the appropriate platform skill.

Flash a promoted BSP image to a Jetson device in RCM mode using NVIDIA's flash.sh or l4t_initrd_flash.sh toolchain.

Recommends an inference runtime and memory-related launch flags for LLM/VLM workloads on NVIDIA Jetson devices, based on a live memory audit snapshot.

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.

Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers.

Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI.

Selects Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes based on Orin SM 8.7 vs Thor SM 11.0 and JetPack version.

Provides a comprehensive reference and usage guide for the rclone command-line cloud storage manager, covering configuration, core commands, filtering, and safety practices.

Scan container images, IaC, and SBOMs for vulnerabilities and misconfigurations in CI/CD with Trivy.

Provides code examples and best practices for using Pinecone, a managed vector database for production RAG, recommendation, and semantic search applications.

Provisions third-party services and retrieves API keys using the Stripe Projects CLI plugin, with catalog search and project initialization.

Processes STIX 2.1 threat intelligence bundles from TAXII 2.1 servers, normalizing objects into platform-native schemas and routing them to consuming systems.

Generates setup table and page objects for Business Central following singleton pattern. Creates setup tables with single-record pattern, primary key field, setup page with auto-initialization on OnOpenPage, GetRecordOnce codeunit helper for performance, and common setup field patterns (Enable/Disable toggles, Default values, Number Series references, Path fields, User IDs). Handles DrillDownPageID and LookupPageID for seamless navigation. Supports multi-tenant and cloud-ready patterns. Use when creating setup tables, implementing module configuration, adding settings tables, creating admin configuration pages, building extension setup, or implementing singleton setup patterns for Business Central.

Stand up a self-hostable, typo-tolerant search environment with Typesense — the open-source Algolia / ElasticSearch alternative (single C++ binary, <50ms instant search, no runtime deps). One routing-first skill: pick a server mode (binary download, official Docker image, or managed Typesense Cloud), install an API client (Python/JS/PHP/Ruby official; Go/Dart/C# community), design a collection schema, index documents, and run searches with typo tolerance, faceting/filtering, geo-search, sorting, grouping, synonyms, curation, scoped API keys, and federated multi-search — then wire an InstantSearch.js UI and a Raft-based HA cluster for production. Use when the user wants to build or operate an installable search backend, add site/app/product search, or migrate off Algolia/Elasticsearch. Triggers on: typesense, search engine, typo-tolerant search, algolia alternative, elasticsearch alternative, instantsearch, faceted search, geo search, vector search, self-hosted search, site search, product search.