Add NVFP4 + QAD to the Nemotron-3-Nano-30B-A3B tutorial

- Add an NVFP4 PTQ -> QAD -> export section to the Nemotron-3-Nano-30B-A3B
  tutorial to recover the NVFP4 accuracy drop, and migrate the existing FP8
  quantization section to the examples/megatron_bridge quantize.py / export.py
  scripts. Add placeholder rows for the NVFP4 / NVFP4+QAD accuracy and NVFP4
  vLLM throughput numbers (to be filled in once the experiments land).
- Wrap all tutorial commands in collapsible <details> blocks.
- Reframe the tutorial as NVFP4 + QAD (instead of FP8) in the root README
  "Latest News", CHANGELOG, and the pruning / minitron-vs-puzzletron references.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>

Author: kevalmorabia97

CHANGELOG.rst

@@ -29,7 +29,7 @@ Changelog
 - Add offline DFlash speculative decoding training. Train the draft module from pre-computed base-model hidden states dumped by ``examples/speculative_decoding/collect_hidden_states/compute_hidden_states_hf.py``; base-model transformer layers are deleted after conversion to save memory. Controlled by the auto-derived ``dflash_offline`` flag on ``DFlashConfig`` (derived from ``data_args.offline_data_path``). The dump scripts now share ``collect_hidden_states/common.py`` for aux-layer selection (``--aux-layers eagle|dflash|<list>``) and optional assistant-token ``loss_mask`` for answer-only-loss training.
 - Add support for ``active_params`` (for MoE models) and ``memory_mb`` constraints in Minitron pruning on top of existing ``params`` constraint. You can also provide multiple constraints. See `examples/pruning/README.md <https://github.com/NVIDIA/Model-Optimizer/tree/main/examples/pruning>`_ for more details. The underlying utility functions ``mcore_param_count``, ``mcore_memory_footprint_mb``, and ``print_mcore_model_stats`` in ``modelopt.torch.nas.plugins.megatron_model_stats`` are also available for standalone use to compute parameter counts and memory footprints (weights + KV-cache + Mamba state) for any Megatron-Core model.
 - Add Minitron pruning support for Megatron-Bridge Gemma3 models.
-- Add end-to-end tutorial for Minitron pruning + two-phase distillation (80B @ 8K + 20B @ 32K long-context = 100B tokens) + FP8 PTQ + vLLM deployment for Nemotron-3-Nano-30B-A3B-BF16 (MoE + Mamba-Transformer hybrid) → Pruned 22B/A3.0B active params, along with data blend preparation steps (with tool-calling data) and detailed pruning / data-blend / long-context ablations. See `examples/pruning/minitron/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/README.md <https://github.com/NVIDIA/Model-Optimizer/tree/main/examples/pruning/minitron/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/>`_ for details.
+- Add end-to-end optimization tutorial for Minitron pruning + two-phase distillation (80B @ 8K + 20B @ 32K long-context = 100B tokens) + NVFP4 PTQ + QAD + vLLM deployment for Nemotron-3-Nano-30B-A3B-BF16 (MoE + Mamba-Transformer hybrid) → Pruned 22B/A3.0B active params, along with data blend preparation steps (with tool-calling data) and detailed pruning / data-blend / long-context ablations. See `examples/pruning/minitron/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/README.md <https://github.com/NVIDIA/Model-Optimizer/tree/main/examples/pruning/minitron/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/>`_ for details.
 - Add ``--cast_mxfp4_to_nvfp4`` flag to ``examples/llm_ptq/hf_ptq.py`` for closed-form, bit-exact MXFP4 → NVFP4 weight conversion. Supports the GPT-OSS family (``openai/gpt-oss-20b``, ``openai/gpt-oss-120b``). See `examples/llm_ptq/README.md <https://github.com/NVIDIA/Model-Optimizer/tree/main/examples/llm_ptq#mxfp4--nvfp4-cast-for-gpt-oss>`__ for usage.
 - DeepSeek PTQ (``examples/deepseek/ptq.py``) now defaults to native top-k calibration with post-hoc per-layer peer-max sync of expert ``input_quantizer.amax``; the all-experts path is preserved behind ``--calib_all_experts``.
 - Add NVFP4 W4A16 weight-only quantization (``w4a16_nvfp4``): FP4 weights with group_size=16, BF16 activations, no calibration forward pass required. Use ``mtq.W4A16_NVFP4_CFG`` or ``--qformat w4a16_nvfp4`` in ``hf_ptq.py``. vLLM deployment support is in progress.

README.md

@@ -26,7 +26,7 @@ Model Optimizer is also integrated with [NVIDIA Megatron-Bridge](https://github.
 
 ## Latest News
 
-- [2026/05/27] [**End-to-end Minitron workflow for Nemotron-3-Nano-30B-A3B**](./examples/pruning/minitron/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16): Pruning + two-phase distillation + FP8 quantization achieving 1.64× vLLM throughput and 2.6× memory reduction.
+- [2026/05/27] [**End-to-end Optimization workflow for Nemotron-3-Nano-30B-A3B**](./examples/pruning/minitron/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16): Pruning + two-phase distillation + NVFP4 quantization + QAD - achieving ?× vLLM throughput and ?× memory reduction.
 - [2026/05/13] [**Puzzletron**](./examples/puzzletron): A new algorithm for heterogeneous pruning & NAS of LLM and VLM models.
 - [2026/04/15] Customer story: [Domyn compresses Colosseum-355B → 260B using ModelOpt's Minitron pruning + distillation](https://www.domyn.com/blog/domyn-large-the-journey-of-a-european-sovereign-ai-model-for-regulated-industries)
 - [2026/03/17] Customer story: [Bielik.AI builds Bielik Minitron 7B (33% smaller, 50% faster, 90% quality retained) using ModelOpt's Minitron pruning + distillation](https://bielik.ai/en/nvidia-gtc-bielik-minitron-premiere/)

examples/pruning/README.md

@@ -294,7 +294,7 @@ After pruning, distillation is required to recover model accuracy. Below are rec
 
 End-to-end distillation results with Megatron-Bridge after Minitron and Puzzletron pruning:
 
-- **[Minitron — Nemotron-3-Nano-30B-A3B-BF16](minitron/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/README.md)** ⭐ *recommended — newer and most comprehensive*: End-to-end tutorial of structured pruning for Nemotron-3-Nano-30B-A3B-BF16 (31.6B/A3.6B) to 22B/A3.0B active parameters followed by two-phase knowledge distillation (80B tokens @ 8K seq length + 20B tokens @ 32K seq length = 100B tokens total), quantization, and vLLM deployment. Covers MoE + Mamba-Transformer hybrid, tool-calling data, and a long-context fine-tuning phase. Achieves near-parity with the official 30B model across popular pretraining and reasoning benchmarks while delivering up to 1.64× throughput speedup and 2.6× memory reduction when combined with FP8 quantization.
+- **[Minitron — Nemotron-3-Nano-30B-A3B-BF16](minitron/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/README.md)** ⭐ *recommended — newer and most comprehensive*: End-to-end tutorial of structured pruning for Nemotron-3-Nano-30B-A3B-BF16 (31.6B/A3.6B) to 22B/A3.0B active parameters followed by two-phase knowledge distillation (80B tokens @ 8K seq length + 20B tokens @ 32K seq length = 100B tokens total), quantization, and vLLM deployment. Covers MoE + Mamba-Transformer hybrid, tool-calling data, and a long-context fine-tuning phase. Achieves near-parity with the official 30B model across popular pretraining and reasoning benchmarks while delivering significant throughput speedup and memory reduction when combined with NVFP4 quantization + QAD.
 - **[Minitron — Nemotron-Nano-9B-v2](minitron/NVIDIA-Nemotron-Nano-9B-v2/README.md)**: Earlier end-to-end tutorial covering structured pruning of the dense Mamba-Transformer Nemotron-Nano-9B-v2 to 7B followed by knowledge distillation up to 80B tokens, quantization, and vLLM deployment. Simpler architecture, single-phase 8K seq length distillation, no tool-calling or long-context phase.
 - **[Puzzletron — Qwen3-8B and Llama-3.1-8B-Instruct](puzzletron/Llama-3.1-8B-Instruct.md)**: MIP-based compression followed by short distillation runs on WikiText-103. Shows MMLU recovery and illustrates the importance of using larger datasets to avoid overfitting.