deployment

A deployment workflow for serving a language model checkpoint as an API compatible with OpenAI-style requests. A checkpoint is the saved model data, and vLLM, SGLang, and TRT-LLM are tools that run models for inference.

In plain words
What is it for?
Use it to launch local or remote model servers, serve quantized or unquantized checkpoints, check their status, and test their throughput or API.
Why use it?
It handles model format detection, server startup and shutdown, health checks, and API testing so you do not have to assemble those steps manually.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nvidia/model-optimizer/deployment
Any agent
npx skills add NVIDIA/Model-Optimizer --skill deployment
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/Model-Optimizer

Made for: Claude Code, Codex.

Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,555 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00117 $0.03555
Opus 5 $0.00059 $0.01777
Sonnet 5 $0.00023 $0.00711
Haiku 4.5 $0.00012 $0.00356

Measured yesterday against content hash 7decd6aab2c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

deployment scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/deploy.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s http://localhost:8000/v1/models | python -m json.tool

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:8000/health
plugins/modelopt/skills/deployment/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deployment Skill

Serve a model checkpoint as an OpenAI-compatible inference endpoint. Supports vLLM, SGLang, and TRT-LLM (including AutoDeploy).

Quick Start

Prefer $SKILL_DIR/scripts/deploy.sh for standard local deployments — it handles quant detection, health checks, and server lifecycle. Use the raw framework commands in Step 4 when you need flags the script doesn't support, or for remote deployment.

# Start vLLM server with a ModelOpt checkpoint
"$SKILL_DIR/scripts/deploy.sh" start --model ./qwen3-0.6b-fp8

# Start with SGLang and tensor parallelism
"$SKILL_DIR/scripts/deploy.sh" start --model ./llama-70b-nvfp4 --framework sglang --tp 4

# Start from HuggingFace hub
"$SKILL_DIR/scripts/deploy.sh" start --model nvidia/Llama-3.1-8B-Instruct-FP8

# Test the API
"$SKILL_DIR/scripts/deploy.sh" test

# Check status
"$SKILL_DIR/scripts/deploy.sh" status

# Stop
"$SKILL_DIR/scripts/deploy.sh" stop

The script handles: GPU detection, quantization flag auto-detection (FP8 vs FP4), server lifecycle (start/stop/restart/status), health check polling, and API testing.

Decision Flow

0. Check workspace (multi-user / Slack bot)

If MODELOPT_WORKSPACE_ROOT is set, use the common skill's workspace-management.md. Before creating a new workspace, check the current session for existing model workspaces — especially if deploying a checkpoint from a prior PTQ run:

ls "$MODELOPT_WORKSPACE_ROOT/<session_id>/" 2>/dev/null

If the user says "deploy the model I just quantized" or references a previous PTQ, find the matching workspace and cd into it. The checkpoint should be in that workspace's output directory.

1. Identify the checkpoint

Determine what the user wants to deploy:

  • Local quantized checkpoint (from ptq skill or manual export): look for hf_quant_config.json in the directory. If coming from a prior PTQ run in the same workspace, check common output locations: output/, outputs/, exported_model/, or the --export_path used in the PTQ command.
  • HuggingFace model hub (e.g., nvidia/Llama-3.1-8B-Instruct-FP8): use directly
  • Unquantized model: deploy as-is (BF16) or suggest quantizing first with the ptq skill

Read the full file on GitHub · 277 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 277 lines · 117 tokens per session scan C 7decd6aab2c7

Subscribe to this mod's changes

deployment is a skill published in the GitHub repository NVIDIA/Model-Optimizer (3,612 stars, last pushed yesterday), licensed Apache-2.0. It adds 117 tokens to every session and 3,555 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens