NVIDIA/Model-Optimizer 0.37.0

ModelOpt 0.37.0 Release

Repository: NVIDIA/Model-Optimizer

Tag: 0.37.0

Published: 2025-10-08T16:43:57Z

Prerelease: no

Release notes:

Deprecations

• Deprecated ModelOpt's custom docker images. Please use the PyTorch, TensorRT-LLM, or TensorRT docker image directly or refer to the installation guide for more details.
• Deprecated quantize_mode argument in `examples/onnx_ptq/evaluate.py` to support strong typing. Use engine_precision instead.
• Deprecated TRT-LLM's TRT backend in `examples/llm_ptq` and `examples/vlm_ptq`. Tasks build and benchmark support are removed and replaced with quant. engine_dir is replaced with checkpoint_dir in `examples/llm_ptq` and `examples/vlm_ptq`. For performance evaluation, please use trtllm-bench directly.
• The --export_fmt flag in `examples/llm_ptq` is removed. By default, we export to the unified Hugging Face checkpoint format.
• Deprecated `examples/vlm_eval` as it depends on the deprecated TRT-LLM's TRT backend.

New Features

• high_precision_dtype defaults to fp16 in ONNX quantization, i.e., quantized output model weights are now FP16 by default.
• Upgraded TensorRT-LLM dependency to 1.1.0rc2.
• Support for Phi-4-multimodal and Qwen2.5-VL quantized HF checkpoint export in `examples/vlm_ptq`.
• Support storing and restoring Minitron pruning activations and scores for re-pruning without running the forward loop again.
• Added Minitron pruning example for the Megatron-LM framework. See `examples/megatron-lm` for more details.