What is neuron-framework-equivalence?

A tool for checking whether two implementations of the same machine-learning model behave the same. It compares the model structure, individual components, complete outputs, and output distributions.

Use it to compare a reference model with a ported or compiled version, diagnose mismatches, and save the comparison results in an experiment directory.

It helps find differences when moving a model between software frameworks, hardware types, or numerical precision settings.

neuron-framework-equivalence — Skill by aws-neuron

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/aws-neuron/neuron-agentic-development/neuron-framework-equivalence

Any agent

npx skills add aws-neuron/neuron-agentic-development --skill neuron-framework-equivalence

Clone the repo

git clone --depth 1 https://github.com/aws-neuron/neuron-agentic-development

Made for: Claude Code, Codex.

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,582 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5	$0.00100	$0.03582
Opus 5	$0.00050	$0.01791
Sonnet 5	$0.00020	$0.00716
Haiku 4.5	$0.00010	$0.00358

Measured 2d ago against content hash 361dcc6e607a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

neuron-framework-equivalence scanned grade A with 0 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 2d ago.

The scan reads SKILL.md. This mod also ships 26 executable files (scripts/adapters/__init__.py, scripts/adapters/base.py, scripts/adapters/nxdi.py, …), 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/neuron-framework-equivalence/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Equivalence Framework

Verify and diagnose functional equivalence between a source (reference) and a target (ported) implementation of the same model.

Required Inputs

Before starting, collect these from the user. Ask for any missing ones.

Input	Description	Example
`SOURCE_MODEL_PATH`	Path to source model weights (HF format)	`/path/to/hf_models/Qwen3-0.6B`
`COMPILED_MODEL_PATH`	Path to compiled target model	`/path/to/neuron_models/Qwen3-0.6B`
`TARGET_MODELING_FILE`	Path to target's modeling .py file	`/path/to/modeling_qwen3.py`
`TARGET_INNER_CLASS`	Inner model class (extends NeuronBaseModel)	`NeuronQwen3Model`
`TARGET_CAUSAL_CLASS`	ForCausalLM wrapper class	`NeuronQwen3ForCausalLM`
`TARGET_CONFIG_CLASS`	InferenceConfig class	`Qwen3InferenceConfig`
`VENV`	Path to Python venv with torch + neuronx	`/opt/aws_neuronx_venv_pytorch_2_8_nxd_inference`
`EXP_DIR`	Experiment output directory	`agent_artifacts/equiv_qwen3`
`VLLM_NEURON_DIR`	vLLM-Neuron targets only. Project root of the `vllm-neuron` editable install	`/path/to/vllm-neuron`

Set SCRIPTS_DIR to the absolute path of this skill's scripts/ directory.

vLLM-Neuron Targets: Version Pin + PYTHONPATH

This skill's vllm_neuron adapter is pinned to vLLM 0.24.0 and the vLLM-Neuron plugin 0.24.0 line (two independently-versioned packages; the pins live in scripts/adapters/vllm_neuron.py as PINNED_VLLM_VERSION and PINNED_VLLM_NEURON_VERSION). When the target stack is vLLM-Neuron:

Version check is automatic. get_adapter() calls adapter.check_environment() immediately after construction. If the installed vllm or vllm-neuron plugin is not on the 0.24 line, or vllm_neuron is not importable, the run exits early with a clear message — no cryptic mid-stage AssertionError: Current vLLM config is not set.
Editable install must be on PYTHONPATH. vllm_neuron is a local editable install, and vLLM's plugin entry point (vllm_neuron:register) imports it. Prepend VLLM_NEURON_DIR to PYTHONPATH on every stage command for vLLM-Neuron targets:

Read the full file on GitHub · 257 lines

Files

What ships with it

60 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.

2d ago First seen · 257 lines · 100 tokens per session scan A 361dcc6e607a

Subscribe to this mod's changes

neuron-framework-equivalence is a skill published in the GitHub repository aws-neuron/neuron-agentic-development (56 stars, last pushed 14d ago), licensed Apache-2.0. It adds 100 tokens to every session and 3,582 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Testing

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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