From 4344a420f2c98b2065551dd0f3ad621a064897d4 Mon Sep 17 00:00:00 2001
From: Pia Papanna <ppapanna@meta.com>
Date: Wed, 26 Jun 2024 17:09:11 -0700
Subject: [PATCH] recipes/quickstart folder updated

---
 UPDATES.md                                           | 12 ++++++------
 docs/FAQ.md                                          |  2 +-
 docs/multi_gpu.md                                    |  2 +-
 .../model_servers => 3p_integrations}/README.md      |  0
 .../hf_text_generation_inference/README.md           |  8 +-------
 .../merge_lora_weights.py                            |  0
 .../llama-on-prem.md                                 |  9 ++++-----
 .../vllm/inference.py                                |  0
 recipes/README.md                                    |  4 ++--
 .../RAG/hello_llama_cloud.ipynb}                     |  0
 .../finetuning/LLM_finetuning_overview.md            |  0
 recipes/{ => quickstart}/finetuning/README.md        |  0
 .../{ => quickstart}/finetuning/datasets/README.md   |  2 +-
 .../finetuning/datasets/custom_dataset.py            |  0
 recipes/{ => quickstart}/finetuning/finetuning.py    |  0
 recipes/{ => quickstart}/finetuning/multi_node.slurm |  0
 .../finetuning/multigpu_finetuning.md                |  0
 .../finetuning/quickstart_peft_finetuning.ipynb      |  0
 .../finetuning/singlegpu_finetuning.md               |  0
 .../{ => quickstart/inference}/code_llama/README.md  |  0
 .../inference}/code_llama/code_completion_example.py |  0
 .../inference}/code_llama/code_completion_prompt.txt |  0
 .../inference}/code_llama/code_infilling_example.py  |  0
 .../inference}/code_llama/code_infilling_prompt.txt  |  0
 .../inference}/code_llama/code_instruct_example.py   |  0
 .../inference/local_inference/README.md              |  6 +++---
 .../chat_completion/chat_completion.py               |  0
 .../local_inference/chat_completion/chats.json       |  0
 .../inference/local_inference/inference.py           |  0
 .../inference/local_inference/samsum_prompt.txt      |  0
 .../mobile_inference/android_inference/README.md     |  0
 .../android_inference/mlc-package-config.json        |  0
 .../android_inference/requirements.txt               |  0
 src/tests/datasets/test_custom_dataset.py            |  4 ++--
 tools/benchmarks/inference/on_prem/README.md         |  2 +-
 35 files changed, 22 insertions(+), 29 deletions(-)
 rename recipes/{inference/model_servers => 3p_integrations}/README.md (100%)
 rename recipes/{inference/model_servers => 3p_integrations}/hf_text_generation_inference/README.md (99%)
 rename recipes/{inference/model_servers => 3p_integrations}/hf_text_generation_inference/merge_lora_weights.py (100%)
 rename recipes/{inference/model_servers => 3p_integrations}/llama-on-prem.md (96%)
 rename recipes/{inference/model_servers => 3p_integrations}/vllm/inference.py (100%)
 rename recipes/{use_cases/RAG/HelloLlamaCloud.ipynb => quickstart/RAG/hello_llama_cloud.ipynb} (100%)
 rename recipes/{ => quickstart}/finetuning/LLM_finetuning_overview.md (100%)
 rename recipes/{ => quickstart}/finetuning/README.md (100%)
 rename recipes/{ => quickstart}/finetuning/datasets/README.md (94%)
 rename recipes/{ => quickstart}/finetuning/datasets/custom_dataset.py (100%)
 rename recipes/{ => quickstart}/finetuning/finetuning.py (100%)
 rename recipes/{ => quickstart}/finetuning/multi_node.slurm (100%)
 rename recipes/{ => quickstart}/finetuning/multigpu_finetuning.md (100%)
 rename recipes/{ => quickstart}/finetuning/quickstart_peft_finetuning.ipynb (100%)
 rename recipes/{ => quickstart}/finetuning/singlegpu_finetuning.md (100%)
 rename recipes/{ => quickstart/inference}/code_llama/README.md (100%)
 rename recipes/{ => quickstart/inference}/code_llama/code_completion_example.py (100%)
 rename recipes/{ => quickstart/inference}/code_llama/code_completion_prompt.txt (100%)
 rename recipes/{ => quickstart/inference}/code_llama/code_infilling_example.py (100%)
 rename recipes/{ => quickstart/inference}/code_llama/code_infilling_prompt.txt (100%)
 rename recipes/{ => quickstart/inference}/code_llama/code_instruct_example.py (100%)
 rename recipes/{ => quickstart}/inference/local_inference/README.md (94%)
 rename recipes/{ => quickstart}/inference/local_inference/chat_completion/chat_completion.py (100%)
 rename recipes/{ => quickstart}/inference/local_inference/chat_completion/chats.json (100%)
 rename recipes/{ => quickstart}/inference/local_inference/inference.py (100%)
 rename recipes/{ => quickstart}/inference/local_inference/samsum_prompt.txt (100%)
 rename recipes/{ => quickstart}/inference/mobile_inference/android_inference/README.md (100%)
 rename recipes/{ => quickstart}/inference/mobile_inference/android_inference/mlc-package-config.json (100%)
 rename recipes/{ => quickstart}/inference/mobile_inference/android_inference/requirements.txt (100%)

diff --git a/UPDATES.md b/UPDATES.md
index 9124ec65..fcd45559 100644
--- a/UPDATES.md
+++ b/UPDATES.md
@@ -1,19 +1,19 @@
 ## System Prompt Update
 
 ### Observed Issue
-We received feedback from the community on our prompt template and we are providing an update to reduce the false refusal rates seen. False refusals occur when the model incorrectly refuses to answer a question that it should, for example due to overly broad instructions to be cautious in how it provides responses. 
+We received feedback from the community on our prompt template and we are providing an update to reduce the false refusal rates seen. False refusals occur when the model incorrectly refuses to answer a question that it should, for example due to overly broad instructions to be cautious in how it provides responses.
 
 ### Updated approach
-Based on evaluation and analysis, we recommend the removal of the system prompt as the default setting.  Pull request [#626](https://github.com/facebookresearch/llama/pull/626) removes the system prompt as the default option, but still provides an example to help enable experimentation for those using it. 
+Based on evaluation and analysis, we recommend the removal of the system prompt as the default setting.  Pull request [#626](https://github.com/facebookresearch/llama/pull/626) removes the system prompt as the default option, but still provides an example to help enable experimentation for those using it.
 
 ## Token Sanitization Update
 
 ### Observed Issue
-The PyTorch scripts currently provided for tokenization and model inference allow for direct prompt injection via string concatenation. Prompt injections allow for the addition of special system and instruction prompt strings from user-provided prompts. 
+The PyTorch scripts currently provided for tokenization and model inference allow for direct prompt injection via string concatenation. Prompt injections allow for the addition of special system and instruction prompt strings from user-provided prompts.
 
-As noted in the documentation, these strings are required to use the fine-tuned chat models. However, prompt injections have also been used for manipulating or abusing models by bypassing their safeguards, allowing for the creation of content or behaviors otherwise outside the bounds of acceptable use. 
+As noted in the documentation, these strings are required to use the fine-tuned chat models. However, prompt injections have also been used for manipulating or abusing models by bypassing their safeguards, allowing for the creation of content or behaviors otherwise outside the bounds of acceptable use.
 
 ### Updated approach
-We recommend sanitizing [these strings](https://github.com/meta-llama/llama?tab=readme-ov-file#fine-tuned-chat-models) from any user provided prompts. Sanitization of user prompts mitigates malicious or accidental abuse of these strings. The provided scripts have been updated to do this. 
+We recommend sanitizing [these strings](https://github.com/meta-llama/llama?tab=readme-ov-file#fine-tuned-chat-models) from any user provided prompts. Sanitization of user prompts mitigates malicious or accidental abuse of these strings. The provided scripts have been updated to do this.
 
-Note: even with this update safety classifiers should still be applied to catch unsafe behaviors or content produced by the model. An [example](./recipes/inference/local_inference/inference.py) of how to deploy such a classifier can be found in the llama-recipes repository.
+Note: even with this update safety classifiers should still be applied to catch unsafe behaviors or content produced by the model. An [example](./recipes/quickstart/inference/local_inference/inference.py) of how to deploy such a classifier can be found in the llama-recipes repository.
diff --git a/docs/FAQ.md b/docs/FAQ.md
index 4229bedf..6dc3fd91 100644
--- a/docs/FAQ.md
+++ b/docs/FAQ.md
@@ -16,7 +16,7 @@ Here we discuss frequently asked questions that may occur and we found useful al
 
 4. Can I add custom datasets?
 
-    Yes, you can find more information on how to do that [here](../recipes/finetuning/datasets/README.md).
+    Yes, you can find more information on how to do that [here](../recipes/quickstart/finetuning/datasets/README.md).
 
 5. What are the hardware SKU requirements for deploying these models?
 
diff --git a/docs/multi_gpu.md b/docs/multi_gpu.md
index 56913103..63ee9b97 100644
--- a/docs/multi_gpu.md
+++ b/docs/multi_gpu.md
@@ -9,7 +9,7 @@ To run fine-tuning on multi-GPUs, we will  make use of two packages:
 Given the combination of PEFT and FSDP, we would be able to fine tune a Meta Llama 3 8B model on multiple GPUs in one node or multi-node.
 
 ## Requirements
-To run the examples, make sure to install the llama-recipes package and clone the github repository in order to use the provided [`finetuning.py`](../recipes/finetuning/finetuning.py) script with torchrun (See [README.md](../README.md) for details).
+To run the examples, make sure to install the llama-recipes package and clone the github repository in order to use the provided [`finetuning.py`](../recipes/quickstart/finetuning/finetuning.py) script with torchrun (See [README.md](../README.md) for details).
 
 **Please note that the llama_recipes package will install PyTorch 2.0.1 version, in case you want to run FSDP + PEFT, please make sure to install PyTorch nightlies.**
 
diff --git a/recipes/inference/model_servers/README.md b/recipes/3p_integrations/README.md
similarity index 100%
rename from recipes/inference/model_servers/README.md
rename to recipes/3p_integrations/README.md
diff --git a/recipes/inference/model_servers/hf_text_generation_inference/README.md b/recipes/3p_integrations/hf_text_generation_inference/README.md
similarity index 99%
rename from recipes/inference/model_servers/hf_text_generation_inference/README.md
rename to recipes/3p_integrations/hf_text_generation_inference/README.md
index 7db1e00e..0f794214 100644
--- a/recipes/inference/model_servers/hf_text_generation_inference/README.md
+++ b/recipes/3p_integrations/hf_text_generation_inference/README.md
@@ -2,7 +2,7 @@
 
 This document shows how to serve a fine tuned Llama mode with HuggingFace's text-generation-inference server. This option is currently only available for models that were trained using the LoRA method or without using the `--use_peft` argument.
 
-## Step 0: Merging the weights (Only required if LoRA method was used) 
+## Step 0: Merging the weights (Only required if LoRA method was used)
 
 In case the model was fine tuned with LoRA method we need to merge the weights of the base model with the adapter weight. For this we can use the script `merge_lora_weights.py` which is located in the same folder as this README file.
 
@@ -40,9 +40,3 @@ curl 127.0.0.1:8080/generate_stream \
 ```
 
 Further information can be found in the documentation of the [hf text-generation-inference](https://github.com/huggingface/text-generation-inference) solution.
-
-
-
-
-
-
diff --git a/recipes/inference/model_servers/hf_text_generation_inference/merge_lora_weights.py b/recipes/3p_integrations/hf_text_generation_inference/merge_lora_weights.py
similarity index 100%
rename from recipes/inference/model_servers/hf_text_generation_inference/merge_lora_weights.py
rename to recipes/3p_integrations/hf_text_generation_inference/merge_lora_weights.py
diff --git a/recipes/inference/model_servers/llama-on-prem.md b/recipes/3p_integrations/llama-on-prem.md
similarity index 96%
rename from recipes/inference/model_servers/llama-on-prem.md
rename to recipes/3p_integrations/llama-on-prem.md
index 7f8232cf..d43649a2 100644
--- a/recipes/inference/model_servers/llama-on-prem.md
+++ b/recipes/3p_integrations/llama-on-prem.md
@@ -1,6 +1,6 @@
 # Llama 3 On-Prem Inference Using vLLM and TGI
 
-Enterprise customers may prefer to deploy Llama 3 on-prem and run Llama in their own servers. This tutorial shows how to use Llama 3 with [vLLM](https://github.com/vllm-project/vllm) and Hugging Face [TGI](https://github.com/huggingface/text-generation-inference), two leading open-source tools to deploy and serve LLMs, and how to create vLLM and TGI hosted Llama 3 instances with [LangChain](https://www.langchain.com/), an open-source LLM app development framework which we used for our other demo apps: [Getting to Know Llama](https://github.com/meta-llama/llama-recipes/blob/main/recipes/quickstart/Getting_to_know_Llama.ipynb), Running Llama 3 <!-- markdown-link-check-disable -->[locally](https://github.com/meta-llama/llama-recipes/blob/main/recipes/quickstart/Running_Llama3_Anywhere/Running_Llama_on_Mac_Windows_Linux.ipynb) <!-- markdown-link-check-disable --> and [in the cloud](https://github.com/meta-llama/llama-recipes/blob/main/recipes/use_cases/RAG/HelloLlamaCloud.ipynb). See [here](https://medium.com/@rohit.k/tgi-vs-vllm-making-informed-choices-for-llm-deployment-37c56d7ff705) for a detailed comparison of vLLM and TGI.
+Enterprise customers may prefer to deploy Llama 3 on-prem and run Llama in their own servers. This tutorial shows how to use Llama 3 with [vLLM](https://github.com/vllm-project/vllm) and Hugging Face [TGI](https://github.com/huggingface/text-generation-inference), two leading open-source tools to deploy and serve LLMs, and how to create vLLM and TGI hosted Llama 3 instances with [LangChain](https://www.langchain.com/), an open-source LLM app development framework which we used for our other demo apps: [Getting to Know Llama](https://github.com/meta-llama/llama-recipes/blob/main/recipes/quickstart/Getting_to_know_Llama.ipynb), Running Llama 3 <!-- markdown-link-check-disable -->[locally](https://github.com/meta-llama/llama-recipes/blob/main/recipes/quickstart/Running_Llama3_Anywhere/Running_Llama_on_Mac_Windows_Linux.ipynb) <!-- markdown-link-check-disable --> and [in the cloud](https://github.com/meta-llama/llama-recipes/blob/main/recipes/quickstart/RAG/hello_llama_cloud.ipynb). See [here](https://medium.com/@rohit.k/tgi-vs-vllm-making-informed-choices-for-llm-deployment-37c56d7ff705) for a detailed comparison of vLLM and TGI.
 
 For [Ollama](https://ollama.com) based on-prem inference with Llama 3, see the Running Llama 3 locally notebook above.
 
@@ -8,7 +8,7 @@ We'll use the Amazon EC2 instance running Ubuntu with an A10G 24GB GPU as an exa
 
 The Colab notebook to connect via LangChain with Llama 3 hosted as the vLLM and TGI API services is [here](https://colab.research.google.com/drive/1rYWLdgTGIU1yCHmRpAOB2D-84fPzmOJg), also shown in the sections below.
 
-This tutorial assumes that you you have been granted access to the Meta Llama 3 on Hugging Face - you can open a Hugging Face Meta model page [here](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) to confirm that you see "Gated model You have been granted access to this model"; if you see "You need to agree to share your contact information to access this model", simply complete and submit the form in the page. 
+This tutorial assumes that you you have been granted access to the Meta Llama 3 on Hugging Face - you can open a Hugging Face Meta model page [here](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) to confirm that you see "Gated model You have been granted access to this model"; if you see "You need to agree to share your contact information to access this model", simply complete and submit the form in the page.
 
 You'll also need your Hugging Face access token which you can get at your Settings page [here](https://huggingface.co/settings/tokens).
 
@@ -108,7 +108,7 @@ On a Google Colab notebook, first install two packages:
 !pip install langchain openai
 ```
 
-Note that you only need to install the `openai` package with an `EMPTY` OpenAI API key to complete the LangChain integration with the OpenAI-compatible vLLM deployment of Llama 3. 
+Note that you only need to install the `openai` package with an `EMPTY` OpenAI API key to complete the LangChain integration with the OpenAI-compatible vLLM deployment of Llama 3.
 
 Then replace the <vllm_server_ip_address> below and run the code:
 
@@ -165,7 +165,7 @@ curl 127.0.0.1:8080/generate_stream -X POST -H 'Content-Type: application/json'
         "parameters": {
             "max_new_tokens":200
         }
-    }'     
+    }'
 ```
 
 and see the answer generated by Llama 3 via TGI like below:
@@ -199,4 +199,3 @@ llm("What wrote the book innovators dilemma?")
 ```
 
 With the Llama 3 instance `llm` created this way, you can integrate seamlessly with LangChain to build powerful on-prem Llama 3 apps.
-
diff --git a/recipes/inference/model_servers/vllm/inference.py b/recipes/3p_integrations/vllm/inference.py
similarity index 100%
rename from recipes/inference/model_servers/vllm/inference.py
rename to recipes/3p_integrations/vllm/inference.py
diff --git a/recipes/README.md b/recipes/README.md
index 000e4e39..2bcbbdcb 100644
--- a/recipes/README.md
+++ b/recipes/README.md
@@ -4,8 +4,8 @@ This folder contains examples organized by topic:
 |---|---|
 [quickstart](./quickstart)|The "Hello World" of using Llama 3, start here if you are new to using Llama 3
 [multilingual](./multilingual)|Scripts to add a new language to Llama
-[finetuning](./finetuning)|Scripts to finetune Llama 3 on single-GPU and multi-GPU setups
-[inference](./inference)|Scripts to deploy Llama 3 for inference [locally](./inference/local_inference/), on mobile [Android](./inference/mobile_inference/android_inference/) and using [model servers](./inference/mobile_inference/)
+[finetuning](./quickstart/finetuning)|Scripts to finetune Llama 3 on single-GPU and multi-GPU setups
+[inference](./quickstart/inference)|Scripts to deploy Llama 3 for inference [locally](./quickstart/inference/local_inference/), on mobile [Android](./quickstart/inference/mobile_inference/android_inference/) and using [model servers](./quickstart/inference/mobile_inference/)
 [use_cases](./use_cases)|Scripts showing common applications of Llama 3
 [responsible_ai](./responsible_ai)|Scripts to use PurpleLlama for safeguarding model outputs
 [llama_api_providers](./llama_api_providers)|Scripts to run inference on Llama via hosted endpoints
diff --git a/recipes/use_cases/RAG/HelloLlamaCloud.ipynb b/recipes/quickstart/RAG/hello_llama_cloud.ipynb
similarity index 100%
rename from recipes/use_cases/RAG/HelloLlamaCloud.ipynb
rename to recipes/quickstart/RAG/hello_llama_cloud.ipynb
diff --git a/recipes/finetuning/LLM_finetuning_overview.md b/recipes/quickstart/finetuning/LLM_finetuning_overview.md
similarity index 100%
rename from recipes/finetuning/LLM_finetuning_overview.md
rename to recipes/quickstart/finetuning/LLM_finetuning_overview.md
diff --git a/recipes/finetuning/README.md b/recipes/quickstart/finetuning/README.md
similarity index 100%
rename from recipes/finetuning/README.md
rename to recipes/quickstart/finetuning/README.md
diff --git a/recipes/finetuning/datasets/README.md b/recipes/quickstart/finetuning/datasets/README.md
similarity index 94%
rename from recipes/finetuning/datasets/README.md
rename to recipes/quickstart/finetuning/datasets/README.md
index ea2847f7..ae31bb81 100644
--- a/recipes/finetuning/datasets/README.md
+++ b/recipes/quickstart/finetuning/datasets/README.md
@@ -1,6 +1,6 @@
 # Datasets and Evaluation Metrics
 
-The provided fine tuning scripts allows you to select between three datasets by passing the `dataset` arg to the `llama_recipes.finetuning` module or [`recipes/finetuning/finetuning.py`](../finetuning.py) script. The current options are `grammar_dataset`, `alpaca_dataset`and `samsum_dataset`. Additionally, we integrate the OpenAssistant/oasst1 dataset as an [example for a custom dataset](custom_dataset.py) Note: Use of any of the datasets should be in compliance with the dataset's underlying licenses (including but not limited to non-commercial uses)
+The provided fine tuning scripts allows you to select between three datasets by passing the `dataset` arg to the `llama_recipes.finetuning` module or [`recipes/quickstart/finetuning/finetuning.py`](../finetuning.py) script. The current options are `grammar_dataset`, `alpaca_dataset`and `samsum_dataset`. Additionally, we integrate the OpenAssistant/oasst1 dataset as an [example for a custom dataset](custom_dataset.py) Note: Use of any of the datasets should be in compliance with the dataset's underlying licenses (including but not limited to non-commercial uses)
 
 * [grammar_dataset](https://huggingface.co/datasets/jfleg) contains 150K pairs of english sentences and possible corrections.
 * [alpaca_dataset](https://github.com/tatsu-lab/stanford_alpaca) provides 52K instruction-response pairs as generated by `text-davinci-003`.
diff --git a/recipes/finetuning/datasets/custom_dataset.py b/recipes/quickstart/finetuning/datasets/custom_dataset.py
similarity index 100%
rename from recipes/finetuning/datasets/custom_dataset.py
rename to recipes/quickstart/finetuning/datasets/custom_dataset.py
diff --git a/recipes/finetuning/finetuning.py b/recipes/quickstart/finetuning/finetuning.py
similarity index 100%
rename from recipes/finetuning/finetuning.py
rename to recipes/quickstart/finetuning/finetuning.py
diff --git a/recipes/finetuning/multi_node.slurm b/recipes/quickstart/finetuning/multi_node.slurm
similarity index 100%
rename from recipes/finetuning/multi_node.slurm
rename to recipes/quickstart/finetuning/multi_node.slurm
diff --git a/recipes/finetuning/multigpu_finetuning.md b/recipes/quickstart/finetuning/multigpu_finetuning.md
similarity index 100%
rename from recipes/finetuning/multigpu_finetuning.md
rename to recipes/quickstart/finetuning/multigpu_finetuning.md
diff --git a/recipes/finetuning/quickstart_peft_finetuning.ipynb b/recipes/quickstart/finetuning/quickstart_peft_finetuning.ipynb
similarity index 100%
rename from recipes/finetuning/quickstart_peft_finetuning.ipynb
rename to recipes/quickstart/finetuning/quickstart_peft_finetuning.ipynb
diff --git a/recipes/finetuning/singlegpu_finetuning.md b/recipes/quickstart/finetuning/singlegpu_finetuning.md
similarity index 100%
rename from recipes/finetuning/singlegpu_finetuning.md
rename to recipes/quickstart/finetuning/singlegpu_finetuning.md
diff --git a/recipes/code_llama/README.md b/recipes/quickstart/inference/code_llama/README.md
similarity index 100%
rename from recipes/code_llama/README.md
rename to recipes/quickstart/inference/code_llama/README.md
diff --git a/recipes/code_llama/code_completion_example.py b/recipes/quickstart/inference/code_llama/code_completion_example.py
similarity index 100%
rename from recipes/code_llama/code_completion_example.py
rename to recipes/quickstart/inference/code_llama/code_completion_example.py
diff --git a/recipes/code_llama/code_completion_prompt.txt b/recipes/quickstart/inference/code_llama/code_completion_prompt.txt
similarity index 100%
rename from recipes/code_llama/code_completion_prompt.txt
rename to recipes/quickstart/inference/code_llama/code_completion_prompt.txt
diff --git a/recipes/code_llama/code_infilling_example.py b/recipes/quickstart/inference/code_llama/code_infilling_example.py
similarity index 100%
rename from recipes/code_llama/code_infilling_example.py
rename to recipes/quickstart/inference/code_llama/code_infilling_example.py
diff --git a/recipes/code_llama/code_infilling_prompt.txt b/recipes/quickstart/inference/code_llama/code_infilling_prompt.txt
similarity index 100%
rename from recipes/code_llama/code_infilling_prompt.txt
rename to recipes/quickstart/inference/code_llama/code_infilling_prompt.txt
diff --git a/recipes/code_llama/code_instruct_example.py b/recipes/quickstart/inference/code_llama/code_instruct_example.py
similarity index 100%
rename from recipes/code_llama/code_instruct_example.py
rename to recipes/quickstart/inference/code_llama/code_instruct_example.py
diff --git a/recipes/inference/local_inference/README.md b/recipes/quickstart/inference/local_inference/README.md
similarity index 94%
rename from recipes/inference/local_inference/README.md
rename to recipes/quickstart/inference/local_inference/README.md
index 11c3dc5e..15d97008 100644
--- a/recipes/inference/local_inference/README.md
+++ b/recipes/quickstart/inference/local_inference/README.md
@@ -69,7 +69,7 @@ In case you have fine-tuned your model with pure FSDP and saved the checkpoints
 This is helpful if you have fine-tuned you model using FSDP only as follows:
 
 ```bash
-torchrun --nnodes 1 --nproc_per_node 8  recipes/finetuning/finetuning.py --enable_fsdp --model_name /path_of_model_folder/7B --dist_checkpoint_root_folder model_checkpoints --dist_checkpoint_folder fine-tuned --pure_bf16
+torchrun --nnodes 1 --nproc_per_node 8  recipes/quickstart/finetuning/finetuning.py --enable_fsdp --model_name /path_of_model_folder/7B --dist_checkpoint_root_folder model_checkpoints --dist_checkpoint_folder fine-tuned --pure_bf16
 ```
 Then convert your FSDP checkpoint to HuggingFace checkpoints using:
 ```bash
@@ -82,6 +82,6 @@ By default, training parameter are saved in `train_params.yaml` in the path wher
 Then run inference using:
 
 ```bash
-python inference.py --model_name <training_config.output_dir> --prompt_file <test_prompt_file> 
+python inference.py --model_name <training_config.output_dir> --prompt_file <test_prompt_file>
 
-```
\ No newline at end of file
+```
diff --git a/recipes/inference/local_inference/chat_completion/chat_completion.py b/recipes/quickstart/inference/local_inference/chat_completion/chat_completion.py
similarity index 100%
rename from recipes/inference/local_inference/chat_completion/chat_completion.py
rename to recipes/quickstart/inference/local_inference/chat_completion/chat_completion.py
diff --git a/recipes/inference/local_inference/chat_completion/chats.json b/recipes/quickstart/inference/local_inference/chat_completion/chats.json
similarity index 100%
rename from recipes/inference/local_inference/chat_completion/chats.json
rename to recipes/quickstart/inference/local_inference/chat_completion/chats.json
diff --git a/recipes/inference/local_inference/inference.py b/recipes/quickstart/inference/local_inference/inference.py
similarity index 100%
rename from recipes/inference/local_inference/inference.py
rename to recipes/quickstart/inference/local_inference/inference.py
diff --git a/recipes/inference/local_inference/samsum_prompt.txt b/recipes/quickstart/inference/local_inference/samsum_prompt.txt
similarity index 100%
rename from recipes/inference/local_inference/samsum_prompt.txt
rename to recipes/quickstart/inference/local_inference/samsum_prompt.txt
diff --git a/recipes/inference/mobile_inference/android_inference/README.md b/recipes/quickstart/inference/mobile_inference/android_inference/README.md
similarity index 100%
rename from recipes/inference/mobile_inference/android_inference/README.md
rename to recipes/quickstart/inference/mobile_inference/android_inference/README.md
diff --git a/recipes/inference/mobile_inference/android_inference/mlc-package-config.json b/recipes/quickstart/inference/mobile_inference/android_inference/mlc-package-config.json
similarity index 100%
rename from recipes/inference/mobile_inference/android_inference/mlc-package-config.json
rename to recipes/quickstart/inference/mobile_inference/android_inference/mlc-package-config.json
diff --git a/recipes/inference/mobile_inference/android_inference/requirements.txt b/recipes/quickstart/inference/mobile_inference/android_inference/requirements.txt
similarity index 100%
rename from recipes/inference/mobile_inference/android_inference/requirements.txt
rename to recipes/quickstart/inference/mobile_inference/android_inference/requirements.txt
diff --git a/src/tests/datasets/test_custom_dataset.py b/src/tests/datasets/test_custom_dataset.py
index c3fdc0f7..5b8028af 100644
--- a/src/tests/datasets/test_custom_dataset.py
+++ b/src/tests/datasets/test_custom_dataset.py
@@ -51,7 +51,7 @@ def test_custom_dataset(step_lr, optimizer, get_model, tokenizer, train, mocker,
     kwargs = {
         "dataset": "custom_dataset",
         "model_name": llama_version,
-        "custom_dataset.file": "recipes/finetuning/datasets/custom_dataset.py",
+        "custom_dataset.file": "recipes/quickstart/finetuning/datasets/custom_dataset.py",
         "custom_dataset.train_split": "validation",
         "batch_size_training": 2,
         "val_batch_size": 4,
@@ -108,7 +108,7 @@ def test_unknown_dataset_error(step_lr, optimizer, tokenizer, get_model, train,
 
     kwargs = {
         "dataset": "custom_dataset",
-        "custom_dataset.file": "recipes/finetuning/datasets/custom_dataset.py:get_unknown_dataset",
+        "custom_dataset.file": "recipes/quickstart/finetuning/datasets/custom_dataset.py:get_unknown_dataset",
         "batch_size_training": 1,
         "use_peft": False,
         }
diff --git a/tools/benchmarks/inference/on_prem/README.md b/tools/benchmarks/inference/on_prem/README.md
index 0d2053f5..8f0da859 100644
--- a/tools/benchmarks/inference/on_prem/README.md
+++ b/tools/benchmarks/inference/on_prem/README.md
@@ -7,7 +7,7 @@ We support benchmark on these serving framework:
 
 # vLLM - Getting Started
 
-To get started, we first need to deploy containers on-prem as a API host. Follow the guidance [here](../../../inference/model_servers/llama-on-prem.md#setting-up-vllm-with-llama-3) to deploy vLLM on-prem.
+To get started, we first need to deploy containers on-prem as a API host. Follow the guidance [here](../../../3p_integration/llama-on-prem.md#setting-up-vllm-with-llama-3) to deploy vLLM on-prem.
 
 Note that in common scenario which overall throughput is important, we suggest you prioritize deploying as many model replicas as possible to reach higher overall throughput and request-per-second (RPS), comparing to deploy one model container among multiple GPUs for model parallelism. Additionally, as deploying multiple model replicas, there is a need for a higher level wrapper to handle the load balancing which here has been simulated in the benchmark scripts.
 For example, we have an instance from Azure that has 8xA100 80G GPUs, and we want to deploy the Meta Llama 3 70B instruct model, which is around 140GB with FP16. So for deployment we can do:
-- 
GitLab