Add Efficient Online Training with GRPO and vLLM in TRL recipe

Author: sergiopaniego

notebooks/en/_toctree.yml

@@ -88,8 +88,9 @@
           title: Hyperparameter Optimization with Optuna and Transformers
         - local: function_calling_fine_tuning_llms_on_xlam
           title: Fine-tuning LLMs for Function Calling with the xLAM Dataset
-          
-        
+        - local: grpo_vllm_online_training
+          title: Efficient Online Training with GRPO and vLLM in TRL
+
 
     - title: Computer Vision Recipes
       isExpanded: false

notebooks/en/grpo_vllm_online_training.ipynb

@@ -7,11 +7,11 @@ applications and solving various machine learning tasks using open-source tools
 
 Check out the recently added notebooks:
 
+- [Efficient Online Training with GRPO and vLLM in TRL](grpo_vllm_online_training)
 - [Fine-tuning LLMs for Function Calling with the xLAM Dataset](function_calling_fine_tuning_llms_on_xlam)
 - [Post training an VLM for reasoning with GRPO using TRL](fine_tuning_vlm_grpo_trl)
 - [TRL GRPO Reasoning with Advanced Reward](trl_grpo_reasoning_advanced_reward)
 - [Fine-Tuning a Vision Language Model with TRL using MPO](fine_tuning_vlm_mpo)
-- [Fine tuning a VLM for Object Detection Grounding using TRL](fine_tuning_vlm_object_detection_grounding)
 
 You can also check out the notebooks in the cookbook's [GitHub repo](https://github.com/huggingface/cookbook).