Results for “proto-loader”

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production". (gstack)

Collects launch inputs and runs preflight checks before executing TAO workflows such as AutoML, training, evaluation, inference, export, TensorRT engine generation, or DEFT jobs on supported platforms.

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA, including picking the right base pipeline, designing a tailored UI, and publishing the Space.

Provides guidance on enabling and optimizing GKE Cluster Autoscaler, including Node Auto Provisioning, troubleshooting scale-up/down issues, and best practices for capacity management.

Pull and verify the official Holoscan SDK container from NGC, selecting the correct CUDA/arch tag for the host GPU and validating with bundled Python and C++ examples.

Sets up Microsoft Testing Platform hot reload to iterate fixes on failing tests without rebuilding, covering package installation, environment configuration, and the iterative workflow.

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.

Author or debug Kubernetes manifests with distinct probes, right-sized resources, autoscaling, and safe reversible rollouts.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Load pre-trained models from Hugging Face Hub, run pipeline inference, generate text, and fine-tune models on NLP, vision, audio, and multimodal tasks using the Transformers library.

Deploy applications to Heroku with safe, read-only inspection first. Use when the agent needs to assess Heroku readiness, choose between Heroku Git and container deployment, create or target an app, wire a Heroku remote, or perform a controlled Heroku deployment.

Detects the project stack and generates production-ready multi-stage Dockerfiles with compose services, .dockerignore, non-root users, health checks, layer caching, and optional dev hot-reload profiles.

Generates and runs load tests for API endpoints using k6, Locust, or Artillery. Detects the API framework, creates realistic user behavior flows, executes ramp-up, sustained, spike, and stress profiles, and produces a bottleneck analysis with optimization recommendations.

Designs and executes load tests, covering scenario design, baseline capture, execution configuration, results analysis, and reporting for k6, Locust, Gatling, and JMeter.

Delegates a bounded repository task to an allowlisted external coding CLI through a guarded runner, with provider selection, timeout handling, and independent local review.

Provisions free LLM API keys from 20+ providers, health-checks existing keys, opens signup pages, validates new keys, and saves them to your project.

Land and deploy workflow. (gstack)

Scans a project for stack signals and pain points, searches the skills-hub registry and local skills, scores candidates, and presents a ranked shortlist with install commands.

Diagnoses and operates Kubernetes clusters: pods, deployments, ingress, HPA, PVC, StorageClass, NetworkPolicy, Secrets, Helm, ArgoCD, cert-manager. Reads before changing; mutations require confirmation and diff review.

Diagnose and eliminate performance bottlenecks across web, API, database, and code with load testing, profiling, and optimization techniques.