From ed531df8fc11c9c06e411da81fd28eafc5d4d456 Mon Sep 17 00:00:00 2001 From: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com> Date: Mon, 22 Jun 2026 23:20:22 +0000 Subject: [PATCH] Deprecate examples/llm_autodeploy Mark the AutoQuant + TensorRT-LLM AutoDeploy example as deprecated per the deprecation policy: add a deprecation banner to the example README and a note under the 0.45 Deprecations section of the changelog. The example will be removed in a future release; users should use TensorRT-LLM's AutoDeploy directly together with ModelOpt PTQ in examples/llm_ptq. Co-Authored-By: Claude Opus 4.8 (1M context) Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com> --- CHANGELOG.rst | 4 ++++ examples/llm_autodeploy/README.md | 7 +++++++ 2 files changed, 11 insertions(+) diff --git a/CHANGELOG.rst b/CHANGELOG.rst index 20a2d37540a..cf117623910 100755 --- a/CHANGELOG.rst +++ b/CHANGELOG.rst @@ -93,6 +93,10 @@ Changelog **Deprecations** - Deprecate the public ``QuantizationArgumentsWithConfig`` name in ``modelopt.torch.quantization.plugins.transformers_trainer``; it now aliases ``QuantizationArguments`` and will be removed in a future release. +- Deprecate ``examples/llm_autodeploy``. The AutoQuant + TensorRT-LLM AutoDeploy + workflow it demonstrates will be removed in a future release; use TensorRT-LLM's + `AutoDeploy `_ + directly together with ModelOpt PTQ in ``examples/llm_ptq``. **Bug Fixes** diff --git a/examples/llm_autodeploy/README.md b/examples/llm_autodeploy/README.md index c21f8c203f4..f477f80d778 100644 --- a/examples/llm_autodeploy/README.md +++ b/examples/llm_autodeploy/README.md @@ -1,5 +1,12 @@ # Deploy AutoQuant Models with AutoDeploy +> [!WARNING] +> **Deprecated (ModelOpt 0.45).** This example is deprecated and will be removed in +> a future release (0.46). For mixed-precision deployment, use TensorRT-LLM's +> [AutoDeploy](https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/auto_deploy) +> directly, combined with ModelOpt PTQ/AutoQuant from +> [`examples/llm_ptq`](../llm_ptq/README.md). + This guide demonstrates how to deploy mixed-precision models using ModelOpt's AutoQuant and TRT-LLM's AutoDeploy. [ModelOpt's AutoQuant](https://nvidia.github.io/Model-Optimizer/reference/generated/modelopt.torch.quantization.model_quant.html#modelopt.torch.quantization.model_quant.auto_quantize) is a post-training quantization (PTQ) algorithm that optimizes model quantization by selecting the best quantization format for each layer while adhering to user-defined compression constraints. This approach allows users to balance model accuracy and performance effectively.