---
title: "2026-08-27 ve2e ClearML checkpoint loading audit"
description: "Audited ve2e model-ID loading, checkpoint formats, config recovery, and main/EMA conventions."
image: "https://docs.virdx.dev/img/virdx-social-card.png"
---

> Documentation Index
> Fetch the complete documentation index at: https://docs.virdx.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# 2026-08-27 ve2e ClearML checkpoint loading audit

## Work Done

- Inspected `ve2e` main at `ec5d24c6` without changing it.
- Traced ClearML `OutputModel` uploads and `InputModel.get_local_copy()` loading.
- Documented Lightning main checkpoints, custom self-contained EMA payloads, slim DINO filtering, embedded configs, architecture construction, and EMA loading.
- Identified gaps in the current model-ID inference loader and proposed one shared loader for main and EMA checkpoints.

## Lessons Learned: Pitfalls

- The knowledge base has no `clinical` workstream directory even though the required skill lists it. Infrastructure was used because this task centered on ClearML storage.
- Similar inference loading logic is duplicated across scripts, but some copies omit key migration and load validation.

## Lessons Learned: Improvements

- Add a durable ve2e checkpoint contract that states key prefixes, required payload fields, main/EMA dispatch, and legacy compatibility.
- Centralize ClearML fetch and architecture-weight loading in production code, then make inference scripts use it.

Source: https://docs.virdx.dev/knowledge/inbox/2026-08-27-infrastructure-ve2e-clearml-checkpoint-loading-audit/index.mdx