update README.md

README.md

@@ -1,3 +1,118 @@
 ---
 license: llama2
+pipeline_tag: text-generation
+tags:
+- text-generation-inference
 ---
+
+<div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/64ccdc322e592905f922a06e/VhwQtaklohkUXFWkjA-3M.png" width="450"/>
+
+English | [简体中文](README_zh-CN.md)
+
+</div>
+
+<p align="center">
+    👋 join us on <a href="https://twitter.com/intern_lm" target="_blank">Twitter</a>, <a href="https://discord.gg/xa29JuW87d" target="_blank">Discord</a> and <a href="https://r.vansin.top/?r=internwx" target="_blank">WeChat</a>
+</p>
+
+
+# W4A16 LLM Model Deployment
+
+LMDeploy supports LLM model inference of 4-bit weight, with the minimum requirement for NVIDIA graphics cards being sm80.
+
+Before proceeding with the inference, please ensure that lmdeploy(>=v0.0.14) is installed.
+
+```shell
+pip install 'lmdeploy>=0.0.14'
+```
+
+## 4-bit LLM model Inference
+
+You can download the pre-quantized 4-bit weight models from LMDeploy's [model zoo](https://huggingface.co/lmdeploy) and conduct inference using the following command.
+
+Alternatively, you can quantize 16-bit weights to 4-bit weights following the ["4-bit Weight Quantization"](#4-bit-weight-quantization) section, and then perform inference as per the below instructions.
+
+Take the 4-bit Llama-2-70B model from the model zoo as an example:
+
+```shell
+git-lfs install
+git clone https://huggingface.co/lmdeploy/llama2-chat-70b-4bit
+```
+
+As demonstrated in the command below, first convert the model's layout using `turbomind.deploy`, and then you can interact with the AI assistant in the terminal
+
+```shell
+
+## Convert the model's layout and store it in the default path, ./workspace.
+lmdeploy convert \
+    --model-name llama2 \
+    --model-path ./llama2-chat-70b-w4 \
+    --model-format awq \
+    --group-size 128
+
+## inference
+lmdeploy chat ./workspace
+```
+
+## Serve with gradio
+
+If you wish to interact with the model via web ui, please initiate the gradio server as indicated below:
+
+```shell
+lmdeploy serve gradio ./workspace --server_name {ip_addr} --server_port {port}
+```
+
+Subsequently, you can open the website `http://{ip_addr}:{port}` in your browser and interact with the model
+
+## Inference Performance
+
+We benchmarked the Llama 2 7B and 13B with 4-bit quantization on NVIDIA GeForce RTX 4090 using [profile_generation.py](https://github.com/InternLM/lmdeploy/blob/main/benchmark/profile_generation.py). And we measure the token generation throughput (tokens/s) by setting a single prompt token and generating 512 tokens. All the results are measured for single batch inference.
+
+| model       | llm-awq | mlc-llm | turbomind |
+| ----------- | ------- | ------- | --------- |
+| Llama 2 7B  | 112.9   | 159.4   | 206.4     |
+| Llama 2 13B | N/A     | 90.7    | 115.8     |
+
+```shell
+pip install nvidia-ml-py
+```
+
+```bash
+python profile_generation.py \
+ --model-path /path/to/your/model \
+ --concurrency 1 8 --prompt-tokens 0 512 --completion-tokens 2048 512
+```
+
+## 4-bit Weight Quantization
+
+It includes two steps:
+
+- generate quantization parameter
+- quantize model according to the parameter
+
+### Step 1: Generate Quantization Parameter
+
+```shell
+lmdeploy lite calibrate \
+  --model $HF_MODEL \
+  --calib_dataset 'c4' \             # Calibration dataset, supports c4, ptb, wikitext2, pileval
+  --calib_samples 128 \              # Number of samples in the calibration set, if memory is insufficient, you can appropriately reduce this
+  --calib_seqlen 2048 \              # Length of a single piece of text, if memory is insufficient, you can appropriately reduce this
+  --work_dir $WORK_DIR \             # Folder storing Pytorch format quantization statistics parameters and post-quantization weight
+```
+
+### Step2: Quantize Weights
+
+LMDeploy employs AWQ algorithm for model weight quantization.
+
+```shell
+lmdeploy lite auto_awq \
+  --model $HF_MODEL \
+  --w_bits 4 \                       # Bit number for weight quantization
+  --w_sym False \                    # Whether to use symmetric quantization for weights
+  --w_group_size 128 \               # Group size for weight quantization statistics
+  --work_dir $WORK_DIR \             # Directory saving quantization parameters from Step 1
+```
+
+After the quantization is complete, the quantized model is saved to `$WORK_DIR`. Then you can proceed with model inference according to the instructions in the ["4-Bit Weight Model Inference"](#4-bit-llm-model-inference) section.

README_zh-CN.md

@@ -0,0 +1,90 @@
+# W4A16 LLM 模型部署
+
+LMDeploy 支持 4bit 权重模型的推理，**对 NVIDIA 显卡的最低要求是 sm80**。
+
+在推理之前，请确保安装了 lmdeploy，版本 >= v0.0.14
+
+```shell
+pip install 'lmdeploy>=0.0.14'
+```
+
+## 4bit 权重模型推理
+
+你可以直接从 LMDeploy 的 [model zoo](https://huggingface.co/lmdeploy) 下载已经量化好的 4bit 权重模型，直接使用下面的命令推理。也可以根据["4bit 权重量化"](#4bit-权重量化)章节的内容，把 16bit 权重量化为 4bit 权重，然后再按下述说明推理
+
+以 4bit 的 Llama-2-chat-70B 模型为例，可以从 model zoo 直接下载：
+
+```shell
+git-lfs install
+git clone https://huggingface.co/lmdeploy/llama2-chat-70b-4bit
+```
+
+执行以下命令，即可在终端与模型对话：
+
+```shell
+
+## 转换模型的layout，存放在默认路径 ./workspace 下
+lmdeploy convert \
+    --model-name llama2 \
+    --model-path ./llama2-chat-70b-4bit \
+    --model-format awq \
+    --group-size 128
+
+## 推理
+lmdeploy chat ./workspace
+```
+
+## 启动 gradio 服务
+
+如果想通过 webui 与模型对话，请执行以下命令启动 gradio 服务
+
+```shell
+lmdeploy serve gradio ./workspace --server_name {ip_addr} --server_port {port}
+```
+
+然后，在浏览器中打开 http://{ip_addr}:{port}，即可在线对话
+
+## 推理速度
+
+我们在 NVIDIA GeForce RTX 4090 上使用 [profile_generation.py](https://github.com/InternLM/lmdeploy/blob/main/benchmark/profile_generation.py)，分别测试了 4-bit Llama-2-7B 和 Llama-2-13B 模型的 token 生成速度。测试配置为 batch size = 1，(prompt_tokens, completion_tokens) = (1, 512)
+
+| model       | llm-awq | mlc-llm | turbomind |
+| ----------- | ------- | ------- | --------- |
+| Llama 2 7B  | 112.9   | 159.4   | 206.4     |
+| Llama 2 13B | N/A     | 90.7    | 115.8     |
+
+```shell
+python benchmark/profile_generation.py \
+  ./workspace \
+  --concurrency 1 --input_seqlen 1 --output_seqlen 512
+```
+
+## 4bit 权重量化
+
+4bit 权重量化包括 2 步：
+
+- 生成量化参数
+- 根据量化参数，量化模型权重
+
+### 第一步：生成量化参数
+
+```shell
+lmdeploy lite calibrate \
+  --model $HF_MODEL \
+  --calib_dataset 'c4' \             # 校准数据集，支持 c4, ptb, wikitext2, pileval
+  --calib_samples 128 \              # 校准集的样本数，如果显存不够，可以适当调小
+  --calib_seqlen 2048 \              # 单条的文本长度，如果显存不够，可以适当调小
+  --work_dir $WORK_DIR \             # 保存 Pytorch 格式量化统计参数和量化后权重的文件夹
+```
+
+### 第二步：量化权重模型
+
+LMDeploy 使用 AWQ 算法对模型权重进行量化。在执行下面的命令时，需要把步骤1的`$WORK_DIR`传入。量化结束后，权重文件也会存放在这个目录中。然后就可以根据 ["4bit权重模型推理"](#4bit-权重模型推理)章节的说明，进行模型推理。
+
+```shell
+lmdeploy lite auto_awq \
+  --model $HF_MODEL \
+  --w_bits 4 \                       # 权重量化的 bit 数
+  --w_group_size 128 \               # 权重量化分组统计尺寸
+  --work_dir $WORK_DIR \             # 步骤 1 保存量化参数的目录
+```