“Model inference”

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs.

Use when a task would benefit from a secondary model call through the local MCP tool lane, especially for Hugging Face or OpenAI-compatible inference…

Signed-in OneInfer models, chat, media, Studio movies, music, GPUs, and credits.

Manage and fetch models from the Infip API.

Fast LLM inference API that is OpenAI-compatible, for running open models.

Use when a CTF challenge centers on AI or LLM security rather than a conventional web, crypto, or reverse-only path.

World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.

Subagent "transforms-backend-expert" from metabase/metabase: Metabase backend expert for write-back and materialization: actions and EE action_v2 data…

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace.

Scores binary predictions (Brier, log loss, ECE, MCE, AUROC, accuracy, reliability bins, per-cohort) or saved categorical outputs joined to retained targets…

Discover unlimited LLM inference pools, get USDC quotes, subscribe on Base, check key status.

Test availability, benchmark speed, and add a new model to any OpenAI-compatible provider in models.json.

QA financial models for formula errors, hardcodes, date logic, sign conventions, circularity, balance-sheet integrity, scenario switches, units, currencies…

Wrap any CLI as a Model Context Protocol server - schema auto-inferred from --help.

Author the TLA+ abstract behavioural spec for an rd-flow workspace.

Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl.

Create a reduced (fewer-layer) version of a large HuggingFace model for fast testing and debugging.

Team initialization flow (Phase 1 proposal + Phase 2 creation)

OpenAI-compatible agentic API server for inference, vector stores, files and skills, on any model or infrastructure.

Frontier

openfrontier.dev

Discover Frontier inference capabilities and read sanitized usage through read-only tools.

WPP semantic-model wrapper over Fabric semantic-model-authoring.