SkillsAdd

zainhas/skills · Archived

together-dedicated-endpoints

Single-tenant GPU endpoints on Together AI with autoscaling and no rate limits.

First seen Mar 30, 2026

Installation

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

Summary

  • Single-tenant GPU endpoints on Together AI with autoscaling and no rate limits.
  • Deploy fine-tuned or uploaded models, size hardware, and manage endpoint lifecycle.
  • Reach for it whenever the user needs predictable always-on hosting rather than serverless inference, custom containers, or raw clusters.

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

together-code-interpreter Same source
zainhas/skills

Use this skill for Together AI Code Interpreter workflows: remote Python execution, session reu…

1 installs
together-video Same source
zainhas/skills

Text-to-video and image-to-video generation via Together AI, including keyframe control, model …

1 installs
together-images Same source
zainhas/skills

Text-to-image generation and image editing via Together AI, including FLUX and Kontext models, …

1 installs
together-gpu-clusters Same source
zainhas/skills

On-demand and reserved GPU clusters (H100, H200, B200) on Together AI with Kubernetes or Slurm …

1 installs

Similar popular skills

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

azure-dedicated-hsm Similar name
microsoftdocs/agent-skills

Expert knowledge for Azure Dedicated HSM development including troubleshooting, decision making…

119 installs

Also in this package

Other skills from zainhas/skills · top by installs.

npx skills add zainhas/skills
together-code-interpreter 1 together-video 1 together-images 1 together-gpu-clusters 1 together-fine-tuning 1 together-evaluations 1 together-embeddings 1 together-dedicated-containers 1 together-chat-completions 1 together-batch-inference 1

Browse all from zainhas/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 1
License LICENSE
Default branch main
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 4,005 B
  • docs SUMMARY.md 336 B

History

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

SKILL.md

Together Dedicated Endpoints

Overview

Use dedicated endpoints for managed single-tenant model hosting with predictable performance and no shared serverless pool.

Typical fits:

  • production inference with stable latency
  • fine-tuned model hosting
  • uploaded custom model hosting
  • autoscaled model APIs

When This Skill Wins

  • The user needs always-on or single-tenant hosting
  • The model is supported for dedicated deployment
  • Fine-tuned or uploaded models must be served as endpoints
  • Hardware, scaling, or idle-time settings need explicit control

Hand Off To Another Skill

  • Use together-chat-completions for serverless chat inference
  • Use together-dedicated-containers for custom runtimes or nonstandard inference pipelines
  • Use together-gpu-clusters for raw infrastructure or cluster orchestration

Quick Routing

  • Create and manage a standard endpoint

- Start with [scripts/manageendpoint.py](scripts/manageendpoint.py) or [scripts/manageendpoint.ts](scripts/manageendpoint.ts) - Read [references/api-reference.md](references/api-reference.md)

  • Lifecycle tuning or troubleshooting

- Read [references/api-reference.md](references/api-reference.md)

  • Deploy a fine-tuned model

- Start with [scripts/deployfinetuned.py](scripts/deployfinetuned.py) - Read [references/dedicated-models.md](references/dedicated-models.md)

  • Upload and deploy a custom model

- Start with [scripts/uploadcustommodel.py](scripts/uploadcustommodel.py) - Read [references/dedicated-models.md](references/dedicated-models.md)

  • Hardware and sizing choices

- Read [references/hardware-options.md](references/hardware-options.md)

Workflow

  1. Confirm that the task needs dedicated hosting instead of serverless or containers.
  2. Verify model eligibility and inspect available hardware.
  3. Create the endpoint with explicit scaling and timeout settings.
  4. Wait for readiness before sending inference traffic.
  5. Stop or delete the endpoint when the workload no longer needs to run.

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".
  • Model eligibility and hardware availability are gating constraints; check them early.
  • Endpoint management uses endpoint IDs, while inference usually uses the endpoint name as model.
  • Autoscaling, auto-shutdown, prompt caching, and speculative decoding materially affect operations and cost.
  • For custom or fine-tuned models, do not skip the intermediate verification steps before deployment.

Resource Map

  • API reference: [references/api-reference.md](references/api-reference.md)
  • Operational controls and troubleshooting: [references/api-reference.md](references/api-reference.md)
  • Dedicated model guide: [references/dedicated-models.md](references/dedicated-models.md)
  • Hardware guide: [references/hardware-options.md](references/hardware-options.md)
  • Python endpoint lifecycle: [scripts/manageendpoint.py](scripts/manageendpoint.py)
  • TypeScript endpoint lifecycle: [scripts/manageendpoint.ts](scripts/manageendpoint.ts)
  • Fine-tuned deployment: [scripts/deployfinetuned.py](scripts/deployfinetuned.py)
  • Custom model upload and deployment: [scripts/uploadcustommodel.py](scripts/uploadcustommodel.py)

Official Docs