neuron-framework-autoport-vllm-agent

neuron-framework-autoport-vllm-agent is an agent for coding agents from aws-neuron/neuron-agentic-development. It costs 170 tokens per session (1,463 once invoked), scanned B, original, Apache-2.0.

An automated tool for porting Hugging Face machine-learning models to vLLM-Neuron, the Trainium2 backend for running models on AWS Neuron hardware. It researches the model, generates code, registers it, and validates the result.

In plain words
What is it for?
Porting a named Hugging Face model, such as Yi, to vLLM-Neuron. It also supports deep equivalence validation of a completed port.
Why use it?
It removes much of the manual work needed to adapt a model to a different hardware backend and helps check whether the port behaves equivalently.

Agent

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 agents/aws-neuron/neuron-agentic-development/neuron-framework-autoport-vllm-agent
Clone the repo
git clone --depth 1 https://github.com/aws-neuron/neuron-agentic-development

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for neuron-framework-autoport-vllm-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/aws-neuron/neuron-agentic-development/neuron-framework-autoport-vllm-agent.svg)](https://agentmods.dev/agents/aws-neuron/neuron-agentic-development/neuron-framework-autoport-vllm-agent)
Your own site
<a href="https://agentmods.dev/agents/aws-neuron/neuron-agentic-development/neuron-framework-autoport-vllm-agent"><img src="https://agentmods.dev/badge/agents/aws-neuron/neuron-agentic-development/neuron-framework-autoport-vllm-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 170 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,463 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00170 $0.01463
Opus 5 $0.00085 $0.00732
Sonnet 5 $0.00034 $0.00293
Haiku 4.5 $0.00017 $0.00146

Measured 4d ago against content hash 65e829fc1895, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

neuron-framework-autoport-vllm-agent scanned grade B with 1 finding 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 4d ago.

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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- Do not import, reference, or run any code from `transformers_neuronx`. It is an old API library.
agents/neuron-framework-autoport-vllm-agent.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vLLM-Neuron Autoport Agent

You are an autonomous model porting agent for the vLLM-Neuron Trainium2 backend. You accept a model name and HuggingFace model ID, then execute the full porting workflow end-to-end.

IMPORTANT: Do NOT validate or check if tools are available. Just use them directly. All required tools (Read, Write, Edit, Bash, Grep, Glob, etc.) are pre-configured and available.

Workflow Routing

Request Type Skill
Port a HuggingFace model to vLLM-Neuron /neuron-framework-autoport-vllm-neuron
Deep equivalence validation of a completed port /neuron-framework-equivalence

Final Validation: Equivalence

Every port ends with deep equivalence validation (Step 11 of the autoport skill). Invoke the neuron-framework-equivalence skill against the generated port, and use the vLLM-Neuron adapter: pass --target-stack vllm_neuron to every equivalence stage script that accepts it. The adapter handles vLLM-specific distributed init, from_configs() instantiation, weight transpositions/QKV fusion, and the vllm.LLM API. Map the port's outputs (modeling file, config class, ForCausalLM class, venv, TP size) to the equivalence skill's required inputs as described in the autoport skill's Step 11. The port is not complete until the equivalence report (EQUIVALENCE_REPORT.md) is generated.

Prerequisites

Before starting any porting workflow, verify the environment:

  1. Check for virtual environment:
echo $NXDI_VENV_PATH

If set, activate it before running any Python commands:

source $NXDI_VENV_PATH/bin/activate

If not set, check for a local config at .kiro/local.md or .claude/local.md with nxdi_venv_path in YAML frontmatter. If neither is found, report: "NXDI_VENV_PATH not configured" as a warning and continue without a venv.

  1. Verify required packages. If anything fails, report what's missing and STOP — do not proceed with the port.
import sys

missing = []
for m in ["vllm_neuron", "transformers"]:
    try: __import__(m); print(f"  OK: {m}")
    except ImportError: print(f"  MISSING: {m}"); missing.append(m)
if missing: print(f"\nSTOP: {len(missing)} missing packages."); sys.exit(1)
print("\nPackage check complete.")

Read the full file on GitHub · 116 lines

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. 4d ago First seen · 116 lines · 170 tokens per session scan B 65e829fc1895

Subscribe to this mod's changes

neuron-framework-autoport-vllm-agent is an agent published in the GitHub repository aws-neuron/neuron-agentic-development (56 stars, last pushed 15d ago), licensed Apache-2.0. It adds 170 tokens to every session and 1,463 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

timing-analysis-agent

Analyzes real-time constraints, ISR latency, DMA transfer times, and LED protocol timing for embedded systems.

FastLED/FastLED · 25 tokens

apple-neural-performance-expert

Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…

FluidInference/FluidAudio · 0 tokens

grader

You are the quality grader for a gen-tb eval run. The mechanical assertions (compileexitzero, simpasses, logcontains, …) have already been judged by scripts/runevals.py and saved to assertionsresult.json. Do not re-judge them. Your job is to evaluate dimensions those assertions can't catch.

gokeshenzhen/gen-tb-skill · 0 tokens

backend-neutral-adapter-runtime

This document defines the production boundary introduced for Issue #83. The backend-neutral runtime lives in src/runtime/hardwareadapterruntime.py; backend-specific construction lives in src/runtime/hardwareadapterregistrations.py.

pome223/missionos · 0 tokens

turtlebot3-recovery-contracts

This document specifies the first Issue #34 extraction from src/runtime/turtlebot3homemission.py. The extracted module is src/runtime/turtlebot3recoverycontracts.py. It is a pure contract module and must not perform route selection, approval minting, Nav2 dispatch, or completion claims.

pome223/missionos · 0 tokens

robium-architect

Optional heavy-research architect for a new robotics application or genuine re-architecture when stack selection remains ambiguous after lightweight discussion. Takes requirements (robot type, task, hardware, sim-vs-real, GPU/budget, local/remote), researches current primary sources, and writes a concise decision…

robium-ai/robium · 87 tokens