SkillsAdd

togethercomputer/skills

together-dedicated-containers

Custom Dockerized inference workers on Together AI's managed GPU infrastructure.

First seen Mar 31, 2026

Installation

$ npx skills add togethercomputer/skills --skill together-dedicated-containers
View on skills.sh ↗ GitHub repository ↗

Summary

  • Custom Dockerized inference workers on Together AI's managed GPU infrastructure.
  • Build with Sprocket SDK, configure with Jig CLI, submit async queue jobs, and poll results.
  • Reach for it whenever the user needs container-level control rather than a standard model endpoint or raw cluster.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

frontend-design Same topic
anthropics/skills

Guidance for distinctive, intentional visual design when building new UI or reshaping an existi…

866.4K installs
agent-browser Same topic
vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, includ…

810.4K installs
vercel-react-best-practices Same topic
vercel-labs/agent-skills 697.8K installs
web-design-guidelines Same topic
vercel-labs/agent-skills

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…

617.3K installs
microsoft-foundry Same topic
microsoft/azure-skills

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …

576.5K installs
azure-diagnostics Same topic
microsoft/azure-skills

Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe …

568.9K installs

Also in this package

Other skills from togethercomputer/skills · top by installs.

npx skills add togethercomputer/skills
together-chat-completions 93 together-batch-inference 88 together-images 83 together-embeddings 78 together-fine-tuning 77 together-evaluations 76 together-audio 74 together-video 72 together-sandboxes 71 together-gpu-clusters 70

Browse all from togethercomputer/skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 34
License LICENSE
Default branch main
Open issues 0
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,241 B
  • docs SUMMARY.md 324 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 73 installs

SKILL.md

Together Dedicated Containers

Overview

Use Dedicated Container Inference when the user needs a custom runtime, not just managed model hosting.

Core building blocks:

  • Jig CLI for build and deployment
  • Sprocket SDK for request handling inside the container
  • Queue API for async jobs

When This Skill Wins

  • Deploy a custom inference worker
  • Bundle custom dependencies or runtime logic into a container
  • Use queue-based async processing with progress tracking
  • Run a specialized image, video, or multimodal pipeline

Hand Off To Another Skill

  • Use together-dedicated-model-inference for standard model hosting without custom containers
  • Use together-gpu-clusters for full cluster ownership and orchestration control
  • Use together-chat-completions, together-images, or together-video when a serverless product already covers the task

Quick Routing

  • Minimal worker template

- Start with [scripts/sprockethelloworld.py](scripts/sprockethelloworld.py) - Read [references/sprocket-sdk.md](references/sprocket-sdk.md)

  • Build, deploy, logs, queue, and secrets

- Read [references/jig-cli.md](references/jig-cli.md)

  • Queue submission and polling

- Start with [scripts/queueclient.py](scripts/queueclient.py) or [scripts/queueclient.ts](scripts/queueclient.ts)

Workflow

  1. Confirm that the user truly needs a custom container runtime.
  2. Implement the worker with Sprocket's request lifecycle.
  3. Configure pyproject.toml for image, runtime, autoscaling, and mounts.
  4. Deploy with Jig.
  5. Submit jobs through the queue API and poll until completion.

High-Signal Rules

  • Python scripts require the Together v2 SDK (together>=2.0.0). If the user is on an older version, they must upgrade first: uv pip install --upgrade "together>=2.0.0".
  • Prefer dedicated endpoints over containers unless the runtime or pipeline is genuinely custom.
  • Treat the worker contract and pyproject.toml as the source of truth for deployment behavior.
  • Parameterize deployment name, queue inputs, and resource sizing instead of hardcoding them.
  • Queue-based jobs are asynchronous by default; account for polling and result retrieval in client code.

Resource Map

  • Jig CLI: [references/jig-cli.md](references/jig-cli.md)
  • Sprocket SDK: [references/sprocket-sdk.md](references/sprocket-sdk.md)
  • Python queue client: [scripts/queueclient.py](scripts/queueclient.py)
  • TypeScript queue client: [scripts/queueclient.ts](scripts/queueclient.ts)
  • Worker template: [scripts/sprockethelloworld.py](scripts/sprockethelloworld.py)

Official Docs