skills.rest
Toqsick
ToqsickCOMMUNITY
Explore all skills by this author →
GitHub

mlops-suite

Serve models, run local inference, and track experiments in MLOps workflows.

Updated Jul 3, 2026
Search Tags:#mlops#inference#experiment tracking#ml ops#model serving
One-click install
npx skills add https://github.com/Toqsick/MaxClaw --skill mlops-suite
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mlops-suite
Source: https://github.com/Toqsick/MaxClaw/tree/main/.claude/skills/mlops-suite
Command: npx skills add https://github.com/Toqsick/MaxClaw --skill mlops-suite

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, llama.cpp, gguf, huggingface, wandb, audiocraft, sam, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Streamlines end-to-end Machine Learning operations by providing a suite of tools for model serving, inference, tracking, and more, enabling efficient experimentation and deployment.

Core Features & Use Cases

  • Model Serving: Utilizes OpenAI API for high-throughput LLM serving.
  • Local Inference: Supports local inference with llama.cpp and GGUF.
  • Model Hub: Integrates with HuggingFace Hub for model sharing.
  • Experiment Tracking: Offers integration with Weights & Biases.
  • Audio Generation: Includes support for text-to-sound via AudioCraft.
  • Image Segmentation: Supports image segmentation using SAM.
  • Use Case: Imagine you have a large dataset with a trained ML model and want to perform local inference with fine-grained control over model parameters, track your experiments, and serve the model on a server.

Quick Start

Load the skill and start the vLLM server with: mlops-suite serve-vllm.

Frequently Asked Questions about mlops-suite

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I serve large LLMs locally using llama.cpp and GGUF?▼

You can serve large LLMs locally by running inference with llama.cpp using GGUF formatted models. This approach provides fine-grained control over model parameters without relying on external APIs.

Can I track ML experiments with Weights and Biases during local inference?▼

Yes, you can track ML experiments with Weights and Biases. The suite integrates directly with Weights and Biases to log, monitor, and evaluate experiments during local inference or model serving.

What is the best way to perform zero-shot image segmentation via points or boxes?▼

The best way to perform zero-shot image segmentation is using SAM. It supports segmenting images based on input points or bounding boxes across Linux, Mac, and Windows environments.

Do I need a local model server to perform high-throughput LLM serving?▼

Yes, you need a local model server for high-throughput LLM serving. The suite utilizes the OpenAI API for serving but requires local installations of model servers to handle the deployment.

Does this MLOps workflow support text-to-sound audio generation?▼

Yes, this MLOps workflow supports text-to-sound audio generation. It includes integration with AudioCraft to generate audio directly from text inputs within your machine learning pipeline.

How do I share trained models using the HuggingFace Hub?▼

You can share trained models by integrating with the HuggingFace Hub. The suite connects to the hub to upload, manage, and share your models directly from the deployment workflow.

Related Skills

Explore More Software Engineering Skills→
ToqsickToqsick

llama-cpp

Run local GGUF inference for llama.cpp models with quantization selection and Hugging Face Hub discovery.

Community
Advanced
shuff57shuff57

weights-and-biases

Automate ML experiment logging and model management with Weights & Biases.

Community
Advanced
ZurybrZurybr

sam-cell-seg

Segment cells in images using MobileSAM and SAM, then convert masks to polygons.

Community
Intermediate
kwcantrellkwcantrell

llama-server

Serve local GGUF LLMs with an OpenAI-compatible HTTP API.

Community
Advanced