mirror of https://github.com/NVIDIA/Model-Optimizer.git synced 2026-10-02 03:14:52 +08:00

Files

T

Chad Voegele d3fe8117ff Add ModelOpt agent plugin marketplace (#2025 )

### What does this PR do?

Type of change: new feature

Packages the existing ModelOpt agent skills as installable Codex and
Claude plugins:

- Adds a repo-scoped Codex marketplace and Claude-compatible
marketplace.
- Adds the canonical `plugins/modelopt/` plugin tree and manifests.
- Moves the skill tree into the plugin and keeps `.agents/skills` as a
compatibility symlink.
- Adds a minimal `common` placeholder skill required by Codex
validation.
- Documents installation from this repository.

### Usage

```bash
codex plugin marketplace add NVIDIA/Model-Optimizer
```

Then open `/plugins`, select the `modelopt` marketplace, and install
`modelopt`.

For Claude Code:

```bash
claude plugin marketplace add https://github.com/NVIDIA/Model-Optimizer.git
claude plugin install modelopt@modelopt
```

### Testing

- Codex plugin validator
- `claude plugin validate . --strict`
- `claude plugin validate plugins/modelopt --strict`

1. Install the marketplace plugin with Codex and Claude from an
unrelated temporary workspace.
2. Exercise packaged evaluation helpers, a day-0 gate, and the shared
remote helper from that workspace.
3. Run `uv run --frozen --extra dev python -m pytest -q
plugins/modelopt/skills/day0-release/tests/test_gates.py
plugins/modelopt/skills/benchmark-model-kernels/tests`.
4. Run pre-commit hooks for all changed files.

### Before your PR is "*Ready for review*"

- Is this change backward compatible?: ✅
- If you copied code from any other sources or added a new PIP
dependency, did you follow guidance in `CONTRIBUTING.md`: N/A
- Did you write any new necessary tests?: ✅ — added a plugin-path
validator; existing focused skill tests and installed-plugin smoke tests
pass.
- Did you update Changelog?: N/A — agent tooling and distribution only.
- Did you get Claude approval on this PR?: N/A

### Additional Information

Skills remain available through `.agents/skills`; bundled helpers are
packaged under the plugin and resolved from `$SKILL_DIR` so installed
workflows do not depend on the current workspace.

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **New Features**
  * Added installable ModelOpt plugins for Claude Code and Codex.
* Added skills for PTQ, deployment, evaluation, monitoring, debugging,
benchmarking, MLflow access, EAGLE3 workflows, and release management.
* Added deployment helpers, evaluation recipes, checkpoint validation,
and release-gating tools.
* **Documentation**
* Expanded setup, credential, SLURM, benchmarking, deployment,
evaluation, troubleshooting, and workspace guidance.
* Added installation instructions and updated agent-skill discovery
guidance.
* **Maintenance**
* Updated skill references and compatibility links for reliable use
across supported plugin environments.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Chad Voegele <cvoegele@nvidia.com>

2026-08-12 11:33:17 -05:00

1.1 KiB

Raw Blame History

Run the evaluation

Follow the three phases and track your progress in the output.

INPUT -> EXPLORE -> ACT
~~INPUT~~ -> EXPLORE -> ACT
~~INPUT~~ -> ~~EXPLORE~~ -> ACT

1. INPUT

Gather requirements from the user:

Config path: The YAML config file to run. NOTE: You might already have the config path in your memory from the previous step.
Credentials: Some tasks require environment variables (e.g., AWS_ACCESS_KEY_ID, HF_TOKEN). Check if there is a .env file in the workspace root. If not, ask the user to create one with the credentials exported in it.
Task filter (optional): Specific tasks to run via -t <task_name>.
Overrides (optional): Any -o key=value overrides.
Dry-run first? (optional): Preview with --dry-run before submitting.

2. EXPLORE

Preview the resolved config and the sbatch script by adding --dry-run flag to the final command.

3. ACT

Submit the evaluation: uv run nemo-evaluator-launcher run --config <path.yaml> ...
- NEL automatically reads .env from the workspace root — no need to source it manually.

1.1 KiB Raw Blame History

Run the evaluation

1. INPUT

2. EXPLORE

3. ACT

1.1 KiB

Raw Blame History