Model Inference
=========================

.. toctree::
   :glob:
   :maxdepth: 1
   :hidden:
   :caption: MindSpore Inference

   ms_infer/llm_inference_overview
   ms_infer/weight_prepare
   ms_infer/model_dev
   ms_infer/parallel
   ms_infer/weight_split
   ms_infer/model_export
   ms_infer/quantization
   ms_infer/profiling
   ms_infer/custom_operator

.. toctree::
   :glob:
   :maxdepth: 1
   :hidden:
   :caption: MindSpore Lite Inference

   lite_infer/overview

.. raw:: html

   <div class="container">
         <div class="row">
            <div class="col-md-6">
               <div class="doc-article-list">
                  <div class="doc-article-item">
                     <a href="./ms_infer/llm_inference_overview.html" class="article-link">
                        <div>
                           <div class="doc-article-head">
                              <span class="doc-head-content">MindSpore Inference</span>
                           </div>
                           <div class="doc-article-desc">
                              Provides “out-of-the-box” deployment of large language models and inference capabilities to achieve optimal performance based on model characteristics.
                           </div>
                        </div>
                     </a>
                  </div>
               </div>
            </div>
            <div class="col-md-6">
               <div class="doc-article-list">
                  <div class="doc-article-item">
                     <a href="./lite_infer/overview.html" class="article-link">
                        <div>
                           <div class="doc-article-head">
                              <span class="doc-head-content">MindSpore Lite Inference</span>
                           </div>
                           <div class="doc-article-desc">
                              A lightweight inference engine focused on efficient inference deployment solutions for offline models and high performance inference for end-to-end devices.
                           </div>
                        </div>
                     </a>
                  </div>
               </div>
            </div>
         </div>
   </div>