merge main, resolve conflicts

Signed-off-by: Hung-Yueh Chiang <hungyuehc@nvidia.com>

Author: hychiang-git

.pre-commit-config.yaml

@@ -68,6 +68,8 @@ repos:
         entry: python tools/precommit/check_modelopt_recipes.py
         language: system
         files: ^modelopt_recipes/
+        # configs/ contains reusable snippets (not full recipes) — skip recipe validation
+        exclude: ^modelopt_recipes/configs/
 
   # Instructions to change license file if ever needed:
   # https://github.com/Lucas-C/pre-commit-hooks#removing-old-license-and-replacing-it-with-a-new-one

CHANGELOG.rst

@@ -17,6 +17,7 @@ Changelog
 
 **New Features**
 
+- Add composable ``$import`` system for recipe YAML configs, enabling reusable config snippets referenced via ``{$import: name}`` markers. All built-in PTQ recipes converted to use imports with shared snippets under ``modelopt_recipes/configs/`` (numeric formats, quant_cfg building blocks, presets). See :ref:`composable-imports`.
 - 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 ``--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.
@@ -39,7 +40,7 @@ Changelog
 - Add support for vLLM fakequant reload using ModelOpt state for HF models. See `examples/vllm_serve/README.md <https://github.com/NVIDIA/Model-Optimizer/tree/main/examples/vllm_serve#load-qatptq-model-and-serve-in-vllm-wip>`_ for more details.
 - [Early Testing] Add Claude Code PTQ skill (``.claude/skills/ptq/``) for agent-assisted post-training quantization. The skill guides the agent through environment detection, model support checking, format selection, and execution via the launcher or manual SLURM/Docker/bare GPU paths. Includes handling for unlisted models with custom module patching. This feature is in early testing — use with caution.
 - [Early Testing] Polish Claude Code evaluation skill (``.claude/skills/evaluation/``) for agent-assisted LLM accuracy benchmarking via NeMo Evaluator Launcher. Adds two companion skills vendored verbatim from `NVIDIA-NeMo/Evaluator <https://github.com/NVIDIA-NeMo/Evaluator>`_: ``launching-evals`` (run/check/debug/analyze NEL evaluations) and ``accessing-mlflow`` (query MLflow runs, compare metrics, fetch artifacts). Re-sync at a pinned upstream SHA via ``.claude/scripts/sync-upstream-skills.sh``. Also adds a shared ``skills/common/credentials.md`` covering HF / NGC / Docker token setup referenced by multiple skills. This feature is in early testing — use with caution.
-- Add performant layerwise calibration for large models that don't fit on GPU (e.g. DeepSeek-R1, Kimi-K2). See `modelopt_recipes/general/ptq/nvfp4_experts_only-fp8_kv.yaml <https://github.com/NVIDIA/Model-Optimizer/blob/main/modelopt_recipes/general/ptq/nvfp4_experts_only-fp8_kv.yaml>`_ for usage. Layerwise calibration also supports PTQ with intermediate progress saving — useful when long PTQ runs get hit with Slurm timeouts. See `modelopt_recipes/general/ptq/nvfp4_default-none_kv_gptq.yaml <https://github.com/NVIDIA/Model-Optimizer/blob/main/modelopt_recipes/general/ptq/nvfp4_default-none_kv_gptq.yaml>`_ for usage.
+- Add performant layerwise calibration for large models that don't fit on GPU (e.g. DeepSeek-R1, Kimi-K2). See `modelopt_recipes/general/ptq/nvfp4_experts_only-kv_fp8.yaml <https://github.com/NVIDIA/Model-Optimizer/blob/main/modelopt_recipes/general/ptq/nvfp4_experts_only-kv_fp8.yaml>`_ for usage. Layerwise calibration also supports PTQ with intermediate progress saving — useful when long PTQ runs get hit with Slurm timeouts. See `modelopt_recipes/general/ptq/nvfp4_default-kv_none-gptq.yaml <https://github.com/NVIDIA/Model-Optimizer/blob/main/modelopt_recipes/general/ptq/nvfp4_default-kv_none-gptq.yaml>`_ for usage.
 - Add implicit GEMM CUDA kernel for Conv3D with fused NVFP4 fake quantization (``modelopt.torch.quantization.src.conv``). When NVFP4 quantization is applied to an ``nn.Conv3d`` layer via ModelOpt PTQ, the implicit GEMM path is used automatically instead of cuDNN. Uses BF16 WMMA tensor cores (SM80+) with FP32 accumulation and in-kernel FP4 (E2M1) activation quantization. Grouped convolution (``groups > 1``) falls back to the default cuDNN path. Inference only — training mode falls back to cuDNN with a warning.
 - Add FP8 MHA quantization support for vision transformers. Adds an attention-aware ONNX post-processing pass (scale Mul / K-transpose move before Q, Q→DQ insertion on softmax output) in :class:`FP8QuantExporter <modelopt.onnx.export.fp8_exporter.FP8QuantExporter>`, per-instance nested-attention-wrapper skipping in the HF plugin, and ``nn.LayerNorm`` registration in ``QuantModuleRegistry`` so BMM input quantizers and LayerNorm output quantizers defined in FP8_DEFAULT_CFG are honored end-to-end. See `examples/torch_onnx/torch_quant_to_onnx.py <https://github.com/NVIDIA/Model-Optimizer/tree/main/examples/torch_onnx/torch_quant_to_onnx.py>`_ for the general timm-model quantize→ONNX workflow.