# Kermt Infer

Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV.

- Repository: https://github.com/NVIDIA/skills (3812 stars)
- Category: Engineering
- License: Apache-2.0
- Last updated: 2026-10-30
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add NVIDIA/skills --skill kermt-infer -g -a claude-code -y`
Codex: `npx skills add NVIDIA/skills --skill kermt-infer -g -a codex -y`
Cursor: `npx skills add NVIDIA/skills --skill kermt-infer -g -a cursor -y`
Gemini CLI: `npx skills add NVIDIA/skills --skill kermt-infer -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add NVIDIA/skills`

## Description

Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has task FFN heads (refuses pretrain ckpts with a redirect to kermt-finetune), validates the CSV, prepares the data (clean + rdkit_2d features), then launches main.py predict inside the kermt container (blocking, minutes-scale).

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# kermt-infer

Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The
skill is the workflow orchestrator: validate ckpt, validate CSV, prepare data,
launch the runner blocking, return the predictions CSV.

## Skill and runtime paths

Set `SKILL_DIR` to the absolute path of this installed skill directory. Export
`KERMT_REPO` as the absolute path to the KERMT checkout used for model
execution. The bundled container helper mounts that checkout at
`/workspace` and this skill at `/skill` (read-only). Commands inside
the container use `/skill/scripts/`; defaults are bundled in `config/`.

## Hardware requirements

- **GPUs**: 1 (single-GPU). Multi-GPU inference is not currently supported.
- **VRAM**: ≥ 4 GB for the default `batch_size 32`.
- **Disk**: a few hundred MB per run (cleaned CSV + features + predictions).
- **Driver / CUDA**: any host supporting CUDA 12.6 (the kermt image base).

## Inputs

Required:

- `--ckpt <path>`, finetuned checkpoint (must have task FFN heads). The
  validator refuses pretrain ckpts with a redirect to `kermt-finetune`.
- `--csv <path>`, SMILES-only CSV. First column is `smiles`; other columns
  are ignored.

Optional:

- `--batch-size N`, override the configured default (32).
- `--seed N`, random seed for inference (deterministic featurization paths).
- `--gpus 0`, single GPU id (default 0). Multi-GPU rejected.
- `--from-prepare <dir>`, skip the prepare step and reuse an existing
  `prepare_data.json` in `<dir>`.

## Workflow

Let `$KERMT_REPO` be the path to your kermt repo checkout, and assume
`kermt-setup` has built `kermt:latest`.

1. **Pre-flight: ensure container + system probe.**
   ```
   "$SKILL_DIR/scripts/kermt_container.sh" check_system
   ```
   Refuse to proceed on `ok: false`.

2. **Compute run directory.**
   ```
   RUN_DIR=$KERMT_REPO/runs/infer_$(date -u +%Y-%m-%dT%H-%M-%SZ)
   ```

The rest: https://github.com/NVIDIA/skills/blob/HEAD/skills/bionemo-kermt-infer/SKILL.md