“Model inference”

Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss.

vLLM-Copilot

System-Sciences

vLLM (& OpenRouter) integration for GitHub Copilot & Agents window on self-hosted and remote servers (supports full featureset of vLLM, OpenRouter and Copilot).

Cloud platform for deploying and observing voice, video and physical AI agents, built on an open-source agents framework.

Use AlphaFold 3 PyTorch for protein and biomolecular structure-prediction workflows, heterogeneous molecule inputs, PDB/mmCIF/MSA/template preparation…

Show or set the models max-speed workers run on.

Model and inspect a software product spanning multiple repositories using explicit members and contract relationships, without inferring architecture from…

Use synthetic data and back-translation with quality filters and held-out protection.

Opinionated Bayesian modeling workflow with PyMC and ArviZ.

Benchmark and A/B-test multiple LLMs or systems-under-test on one evaluation dataset.

Detect and resolve incoherence in documentation, code, specs vs implementation.

Search and study curated marketing videos and their timestamped moments, and save them to boards.

Run Gemini batch inference on Google Cloud Vertex AI.

Running AI models locally with Ollama and llama.cpp.

Bayesian modeling with PyMC.

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference.

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub.

Use when the user asks to "design an experiment", "build a predictive model", "run A/B test analysis", "perform causal inference", "engineer features"…

This skill should be used when the user asks to "implement a DiD regression", "write a causal inference pipeline", "set up an event study", "implement…

Route GeoAI geospatial data, inference, training, foundation-model, and integration workflows.

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID…

Run a 3-leg evaluation against a newly released LLM.

Influence

influence-so

Plan social campaigns, draft and review posts, schedule approved publishing, and read Insights.

Use when predicting molecular structures (proteins, nucleic acids, small molecules, and complexes) with the Chai-1 foundation model via local inference or the…