Nvidia Model Optimizer Ptq

ModelOpt Post-Training Quantization

Produce a quantized checkpoint from a pretrained model. Read examples/llm_ptq/README.md first — it has the support matrix, CLI flags, and accuracy guidance.

Step 1 — Environment

Read common/environment-setup.md and common/workspace-management.md. After completing them you should know:

• ModelOpt source is available
• Local or remote (+ cluster config if remote)
• SLURM / Docker+GPU / bare GPU
• Launcher available?
• Which workspace to use

Step 2 — Is the model supported?

Check the support table in examples/llm_ptq/README.md for verified HF models.

• Listed → supported, use hf_ptq.py (step 4A/4B)
• Not listed → read references/unsupported-models.md to determine if hf_ptq.py can still work or if a custom script is needed (step 4C)

Step 2.5 — Check for model-specific dependencies

If the model uses trust_remote_code (check config.json for auto_map), inspect its custom Python files for imports not present in the container:

grep -h "^from \|^import " <model_path>/modeling_*.py | sort -u

Known dependency patterns:

If extra deps are needed:

• Launcher (4B): set EXTRA_PIP_DEPS in the task's environment section — ptq.sh installs them automatically
• Manual (4A): unset PIP_CONSTRAINT && pip install <deps> before running hf_ptq.py

Step 3 — Choose quantization format

First, check for a model-specific recipe:

ls modelopt_recipes/models/ 2>/dev/null

If a model-specific recipe exists, use --recipe <path> — it may contain tuned settings.

If no model-specific recipe, choose a format based on GPU (details in examples/llm_ptq/README.md):

• Blackwell (B100/B200/GB200): nvfp4 variants
• Hopper (H100/H200) or older: fp8 or int4_awq

Use --qformat <name> (e.g., --qformat nvfp4). Format definitions: modelopt/torch/quantization/config.py. General PTQ recipes in modelopt_recipes/general/ptq/ correspond to the same formats — --qformat is the simpler way to use them.

NVFP4 can be calibrated on Hopper but requires Blackwell for inference.

Step 4 — Run PTQ

Goal: checkpoint on disk (.safetensors + config.json).

For listed models (4A/4B): run full calibration directly (--calib_size 512). For unlisted models (4C): run a smoke test first (--calib_size 4), wait for success, then full calibration.

Which path?

In README table? ─→ YES ──→ SLURM (local or remote)? ──→ LAUNCHER (4B)
                  │          Local Docker + GPU? ────────→ LAUNCHER (4B)
                  │          Remote Docker (no SLURM)? ──→ MANUAL (4A)
                  │          Bare GPU (local or remote)? → MANUAL (4A)
                  │
                  └→ NOT LISTED ──→ UNLISTED MODEL (4C)

4A — Direct: supported model, manual execution

pip install --no-build-isolation "nvidia-modelopt[hf]"
pip install -r examples/llm_ptq/requirements.txt

python examples/llm_ptq/hf_ptq.py \
    --pyt_ckpt_path <model> \
    --qformat <format> \
    --calib_size 512 \
    --export_path <output>

Run --help for all options.

For remote: use remote_run from remote_exec.sh (see common/remote-execution.md).

4B — Launcher: supported model on SLURM or local Docker

Write a YAML config using common/hf_ptq/hf_ptq.sh. See references/launcher-guide.md for the full template.

cd tools/launcher
# SLURM (remote or local):
SLURM_HOST=<host> SLURM_ACCOUNT=<acct> uv run launch.py --yaml <config.yaml> user=<ssh_user> identity=<ssh_key> --yes
# Local Docker:
uv run launch.py --yaml <config.yaml> hf_local=<hf_cache> --yes

The launcher blocks and tails logs until the job completes. If the launcher fails (missing deps, config errors), fall back to path 4A (manual execution).

4C — Unlisted model

Follow references/unsupported-models.md. It walks through investigating the model, patching ModelOpt if needed, and running hf_ptq.py. Run manually (like 4A) for easier monitoring and debugging.

For SLURM, see common/slurm-setup.md and references/slurm-setup-ptq.md.

Monitoring

After job submission, register the job and set up monitoring per the monitor skill.

Step 5 — Verify output

ls -lh <output_path>/
# Expect: config.json, tokenizer files, model-*.safetensors

Report the path and size to the user.

Post-quantization validation

Validate the exported checkpoint's quantization pattern matches the recipe. Quantization config patterns can silently miss layers if the model uses non-standard naming (e.g., Gemma4 experts.* missed by *mlp* patterns) — this only surfaces later as deployment failures. Read references/checkpoint-validation.md for the validation script, expected patterns per recipe, and common pattern gaps.

Next steps: If the user wants to deploy or evaluate the quantized checkpoint, use the deployment or evaluation skill. The checkpoint workspace carries over. If the model required patches during PTQ (e.g., transformers upgrade), the same fixes will likely be needed at deployment and evaluation time.

Key API Rules

• mtq.register() classes must define _setup() and call it from __init__
• Call mto.enable_huggingface_checkpointing() before quantization
• Wildcard *gate* matches too broadly — use *mlp.gate* or *router*
• VLMs: hf_ptq.py auto-extracts the language model via extract_and_prepare_language_model_from_vl() — no manual VLM handling needed in most cases
• FP8 checkpoints: prefer _QuantFP8Linear (lazy dequant) over FineGrainedFP8Config(dequantize=True) which wastes ~2x memory. See references/unsupported-models.md for details
• Custom quantizer names must end with _input_quantizer or _weight_quantizer

Common Pitfalls

• Model-specific dependencies: Models with trust_remote_code may import packages not in the container (e.g., mamba-ssm for hybrid Mamba models). See Step 2.5. Use EXTRA_PIP_DEPS env var with the launcher, or install manually before running hf_ptq.py
• Transformers version: New models may need a newer version of transformers than what's installed. Check config.json for transformers_version. In containers, beware of PIP_CONSTRAINT blocking upgrades — see references/slurm-setup-ptq.md for workarounds
• Gated datasets: Some calibration datasets require HF authentication. Ensure HF_TOKEN is set in the job environment, or use --dataset cnn_dailymail as a non-gated alternative
• NFS root_squash + Docker: See common/slurm-setup.md section 5

References