“Model inference”

Start and test the prime-rl inference server.

Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal…

Use CausalML for causal inference, uplift modeling, matching, validation, interpretation, and treatment optimization workflows.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT.

Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation.

Reverse-engineers any app into a recon map: screen inventory, user flows, component list, inferred data model and a feature matrix, from public pages…

Run 150+ AI apps via inference.sh CLI (infsh) — image generation, video creation, LLMs, search, 3D, social automation.

THE skill for running a trained policy (INFERENCE) in Newton on the Jetson Thor: play / watch / test / evaluate / benchmark a robot policy.

Inspect a pinned model revision and produce an evidence-backed ModelSupportCard for vLLM-Kunlun adaptation.

The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API.

Containerized inference microservices for foundation models, sold as part of NVIDIA AI Enterprise and deployable on any cloud or data center.

Uses the Biohub esm Python SDK for ESM3 protein generation, ESMC embeddings, and ESMFold2 all-atom folding.

Supports local computational pathology research with PathML: slide loading and tiling, preprocessing and QC, h5path storage, multiplex quantification, spatial…

Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics.

Find and rank useful goals from world, science, collective, and agent needs.

Use when reducing model size, improving inference speed, or deploying to edge devices - covers quantization, pruning, knowledge distillation, ONNX export, and…

CLAUDE.md from cheaper-inference/OmniRoute: 72 lines covering Worktree isolation — Claude Code specifics, Cross-session safety — Claude Code specifics…

Open-source inference framework for LLMs and multimodal models, built for agentic workloads and large-scale serving.

Local LLM inference setup and optimization for agentic workflows.

Create or maintain a source-grounded kpopper knowledge model as a versioned plugin.

llama.cpp local GGUF inference + HF Hub model discovery.

AGENTS.md from cheaper-inference/OmniRoute: 448 lines covering Quick Start, Project at a Glance, Request Pipeline, Resilience Runtime State and more.

Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.