changelog

Signed-off-by: Shengliang Xu <shengliangx@nvidia.com>

Author: shengliangxu

CHANGELOG.rst

@@ -14,6 +14,7 @@ Changelog
 - Enable PTQ workflow for the Step3.5-Flash MoE model with NVFP4 W4A4 + FP8 KV cache quantization. See `modelopt_recipes/models/Step3.5-Flash/nvfp4-mlp-only.yaml <https://github.com/NVIDIA/Model-Optimizer/blob/main/modelopt_recipes/models/Step3.5-Flash/nvfp4-mlp-only.yaml>`_ for more details.
 - 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.
+- Add composable ``$import`` system for recipe YAML configs. Recipes can now declare an ``imports`` section mapping names to reusable config snippet files. The ``{$import: name}`` marker resolves at load time — as a dict value it replaces the content (with optional extend and multi-import via ``$import: [a, b]``), as a list element it splices the snippet entries. Key conflicts between imports or inline keys raise errors. Resolution is recursive with circular import detection. All built-in PTQ recipes converted to use imports with shared snippets under ``modelopt_recipes/configs/``. See :ref:`composable-imports` for the full specification.
 
 **Backward Breaking Changes**