Add doc for client usage (#1914)

Signed-off-by: yiliu30 <[email protected]>

Author: yiliu30

README.md

@@ -26,6 +26,7 @@ In particular, the tool provides the key features, typical examples, and open co
 * Collaborate with cloud marketplaces such as [Google Cloud Platform](https://console.cloud.google.com/marketplace/product/bitnami-launchpad/inc-tensorflow-intel?project=verdant-sensor-286207), [Amazon Web Services](https://aws.amazon.com/marketplace/pp/prodview-yjyh2xmggbmga#pdp-support), and [Azure](https://azuremarketplace.microsoft.com/en-us/marketplace/apps/bitnami.inc-tensorflow-intel), software platforms such as [Alibaba Cloud](https://www.intel.com/content/www/us/en/developer/articles/technical/quantize-ai-by-oneapi-analytics-on-alibaba-cloud.html), [Tencent TACO](https://new.qq.com/rain/a/20221202A00B9S00) and [Microsoft Olive](https://github.com/microsoft/Olive), and open AI ecosystem such as [Hugging Face](https://huggingface.co/blog/intel), [PyTorch](https://pytorch.org/tutorials/recipes/intel_neural_compressor_for_pytorch.html), [ONNX](https://github.com/onnx/models#models), [ONNX Runtime](https://github.com/microsoft/onnxruntime), and [Lightning AI](https://github.com/Lightning-AI/lightning/blob/master/docs/source-pytorch/advanced/post_training_quantization.rst)
 
 ## What's New
+* [2024/07] Performance optimizations and usability improvements on [client-side](https://github.com/intel/neural-compressor/blob/master/docs/3x/client_quant.md).
 * [2024/03] A new SOTA approach [AutoRound](https://github.com/intel/auto-round) Weight-Only Quantization on [Intel Gaudi2 AI accelerator](https://habana.ai/products/gaudi2/) is available for LLMs.
 
 ## Installation

docs/3x/PT_WeightOnlyQuant.md

@@ -15,6 +15,7 @@ PyTorch Weight Only Quantization
     - [HQQ](#hqq)
   - [Specify Quantization Rules](#specify-quantization-rules)
   - [Saving and Loading](#saving-and-loading)
+- [Efficient Usage on Client-Side](#efficient-usage-on-client-side)
 - [Examples](#examples)
 
 ## Introduction
@@ -276,6 +277,11 @@ loaded_model = load(
 )  # Please note that the original_model parameter passes the original model.
 ```
 
+## Efficient Usage on Client-Side
+
+For client machines with limited RAM and cores, we offer optimizations to reduce computational overhead and minimize memory usage. For detailed information, please refer to [Quantization on Client](https://github.com/intel/neural-compressor/blob/master/docs/3x/client_quant.md).
+
+
 ## Examples
 
 Users can also refer to [examples](https://github.com/intel/neural-compressor/blob/master/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/weight_only) on how to quantize a  model with WeightOnlyQuant.

docs/3x/client_quant.md

@@ -0,0 +1,50 @@
+Quantization on Client
+==========================================
+
+1. [Introduction](#introduction)
+2. [Get Started](#get-started) \
+   2.1 [Get Default Algorithm Configuration](#get-default-algorithm-configuration)\
+   2.2 [Optimal Performance and Peak Memory Usage](#optimal-performance-and-peak-memory-usage)
+
+
+## Introduction
+
+For `RTN`, `GPTQ`, and `Auto-Round` algorithms, we provide default algorithm configurations for different processor types (`client` and `sever`). Generally, lightweight configurations are tailored specifically for client devices to enhance performance and efficiency.
+
+
+## Get Started
+
+### Get Default Algorithm Configuration
+
+Here, we take the `RTN` algorithm as example to demonstrate the usage on a client machine.
+
+```python
+from neural_compressor.torch.quantization import get_default_rtn_config, convert, prepare
+from neural_compressor.torch import load_empty_model
+
+model_state_dict_path = "/path/to/model/state/dict"
+float_model = load_empty_model(model_state_dict_path)
+quant_config = get_default_rtn_config()
+prepared_model = prepare(float_model, quant_config)
+quantized_model = convert(prepared_model)
+```
+
+> [!TIP]
+> By default, the appropriate configuration is determined based on hardware information, but users can explicitly specify `processor_type` as either `client` or `server` when calling `get_default_rtn_config`.
+
+
+For Windows machines, run the following command to utilize all available cores automatically:
+
+```bash
+python main.py
+```
+
+> [!TIP]
+> For Linux systems, users need to configure the environment variables appropriately to achieve optimal performance. For example, set the `OMP_NUM_THREADS` explicitly. For processors with hybrid architecture (including both P-cores and E-cores), it is recommended to bind tasks to all P-cores using `taskset`.
+
+### Optimal Performance and Peak Memory Usage
+
+Below are approximate performance and memory usage figures conducted on a client machine with 24 cores and 32GB of RAM. These figures provide a rough estimate for quick reference and may vary based on specific hardware and configurations.
+
+- 7B models (e.g., [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)): the quantization process takes about 65 seconds, with a peak memory usage of around 6GB.
+- 1.5B models (e.g., [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct)),  the quantization process takes about 20 seconds, with a peak memory usage of around 5GB.