Update portable zip QuickStart regarding signature verification (#13050)

* Update portable zip QuickStart regarding sigurature verification

* Small fix

* Small fix

docs/mddocs/Quickstart/llama_cpp_npu_portable_zip_quickstart.md

@@ -16,8 +16,8 @@ IPEX-LLM provides llama.cpp support for running GGUF models on Intel NPU. This g
 - [Step 1: Download and Unzip](#step-1-download-and-unzip)
 - [Step 2: Setup](#step-2-setup)
 - [Step 3: Run GGUF Model](#step-3-run-gguf-model)
+- [Tips & Troubleshooting](#tips--troubleshooting)
 - [More details](npu_quickstart.md)
-- [Troubleshooting](#troubleshooting)
 
 
 ## Prerequisites
@@ -69,8 +69,19 @@ llama-cli-npu.exe -m DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf -n 32 --prompt "What
 > 
 > - The supported maximum number of input tokens is 960, and maximum sequence length for both input and output tokens is 1024 currently.
 
-## Troubleshooting
+## Tips & Troubleshooting
 
 ### `L0 pfnCreate2 result: ZE_RESULT_ERROR_INVALID_ARGUMENT, code 0x78000004` error
 
 First, verify that your NPU driver version meets the requirement. Then, check the runtime configuration based on your device. And please attention the difference between **Command Prompt** and **Windows PowerShell**. Take Arrow Lake for example, you need to use `set IPEX_LLM_NPU_ARL=1` in **Command Prompt** while `$env:IPEX_LLM_NPU_ARL = "1"` in **Windows PowerShell**.
+
+### Signature Verification
+
+For portable zip version 2.2.0, you could verify its signature with the following command:
+
+```
+openssl cms -verify -in <portable-zip-file-name>.pkcs1.sig -inform DER -content <portable-zip-file-name> -out nul -noverify
+```
+
+> [!NOTE]
+> Please ensure that `openssl` is installed on your system before verifying signature.

docs/mddocs/Quickstart/llama_cpp_npu_portable_zip_quickstart.zh-CN.md

@@ -16,8 +16,8 @@ IPEX-LLM 提供了 llama.cpp 的相关支持以在 Intel NPU 上运行 GGUF 模
 - [步骤 1：下载和解压](#步骤-1下载和解压)
 - [步骤 2：启动](#步骤-2启动)
 - [步骤 3：运行 GGUF 模型](#步骤-3运行-gguf-模型)
+- [提示与故障排除](#提示与故障排除)
 - [更多信息](npu_quickstart.md)
-- [故障排除](#故障排除)
 
 
 ## 系统环境准备
@@ -69,9 +69,20 @@ llama-cli-npu.exe -m DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf -n 32 --prompt "What
 > 
 > - 目前支持的输入token数上限是960，输入和输出总token数上限是1024。
 
-## 故障排除
+## 提示与故障排除
 
 ### `L0 pfnCreate2 result: ZE_RESULT_ERROR_INVALID_ARGUMENT, code 0x78000004` 报错
 
 首先确认你的 NPU 驱动版本是否符合要求，然后根据你的设备检查运行时配置，请注意 **命令提示符** 和 **Windows PowerShell** 的区别。
 以 Arrow Lake 为例，在 **命令提示符** 中需要设置 `set IPEX_LLM_NPU_ARL=1`，而在 **Windows PowerShell** 中是 `$env:IPEX_LLM_NPU_ARL = "1"`。
+
+### 签名验证
+
+针对 2.2.0 版本的 portable zip, 可以使用如下命令验证其签名：
+
+```
+openssl cms -verify -in <portable-zip-file-name>.pkcs1.sig -inform DER -content <portable-zip-file-name> -out nul -noverify
+```
+
+> [!NOTE]
+> 在验证签名之前，请确保已在系统上安装 `openssl`。

docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.md

@@ -31,6 +31,7 @@ This guide demonstrates how to use [llama.cpp portable zip](https://github.com/i
   - [Error: Detected different sycl devices](#error-detected-different-sycl-devices)
   - [Multi-GPUs usage](#multi-gpus-usage)
   - [Performance Environment](#performance-environment)
+  - [Signature Verification](#signature-verification)
 - [More Details](llama_cpp_quickstart.md)
 
 ## Windows Quickstart
@@ -331,3 +332,14 @@ To enable SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS, you can run below comma
 - `export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1`(Linux user)
 > [!NOTE]
 > The environment variable SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS determines the usage of immediate command lists for task submission to the GPU. While this mode typically enhances performance, exceptions may occur. Please consider experimenting with and without this environment variable for best performance. For more details, you can refer to [this article](https://www.intel.com/content/www/us/en/developer/articles/guide/level-zero-immediate-command-lists.html).  
+
+### Signature Verification
+
+For portable zip/tgz version 2.2.0, you could verify its signature with the following command:
+
+```
+openssl cms -verify -in <portable-zip-or-tgz-file-name>.pkcs1.sig -inform DER -content <portable-zip-or-tgz-file-name> -out nul -noverify
+```
+
+> [!NOTE]
+> Please ensure that `openssl` is installed on your system before verifying signature.

docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.zh-CN.md

@@ -31,6 +31,7 @@
   - [错误：检测到不同的 sycl 设备](#错误检测到不同的-sycl-设备)
   - [多 GPU 配置](#多-gpu-配置)
   - [性能环境](#性能环境)
+  - [签名验证](#签名验证)
 - [更多详情](llama_cpp_quickstart.md)
 
 ## Windows 用户指南
@@ -335,3 +336,15 @@ Found 3 SYCL devices:
 
 > [!NOTE]
 > 环境变量 `SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS` 用于控制是否使用即时命令列表将任务提交到 GPU。启动此变量通常可以提高性能，但也有例外情况。因此，建议你在启用和禁用该环境变量的情况下进行测试，以找到最佳的性能设置。更多相关细节请参考[此处文章](https://www.intel.com/content/www/us/en/developer/articles/guide/level-zero-immediate-command-lists.html)。  
+
+
+### 签名验证
+
+针对 2.2.0 版本的 portable zip/tgz, 可以使用如下命令验证其签名：
+
+```
+openssl cms -verify -in <portable-zip-or-tgz-file-name>.pkcs1.sig -inform DER -content <portable-zip-or-tgz-file-name> -out nul -noverify
+```
+
+> [!NOTE]
+> 在验证签名之前，请确保已在系统上安装 `openssl`。

docs/mddocs/Quickstart/ollama_portable_zip_quickstart.md

@@ -29,6 +29,7 @@ This guide demonstrates how to use [Ollama portable zip](https://github.com/inte
   - [Select specific GPU(s) to run Ollama when multiple ones are available](#select-specific-gpus-to-run-ollama-when-multiple-ones-are-available)
   - [Tune performance](#tune-performance)
   - [Additional models supported after Ollama v0.5.4](#additional-models-supported-after-ollama-v054)
+  - [Signature Verification](#signature-verification)
 - [More details](ollama_quickstart.md)
 
 ## Windows Quickstart
@@ -220,3 +221,14 @@ The currently Ollama Portable Zip is based on Ollama v0.5.4; in addition, the fo
 | Granite3.1-Dense |  `ollama run granite3-dense` | `./ollama run granite3-dense` | [granite3.1-dense](https://ollama.com/library/granite3.1-dense) |
 | Granite3.1-Moe-3B | `ollama run granite3-moe` | `./ollama run granite3-moe` | [granite3.1-moe](https://ollama.com/library/granite3.1-moe) |
 | Gemma 3 1B | `set IPEX_LLM_MODEL_SOURCE=modelscope` <br> `ollama run gemma3:1b` | `export IPEX_LLM_MODEL_SOURCE=modelscope` <br> `./ollama run gemma3:1b`|  [gemma3:1b](https://www.modelscope.cn/models/lmstudio-community/gemma-3-1b-it-GGUF) |
+
+### Signature Verification
+
+For portable zip/tgz version 2.2.0, you could verify its signature with the following command:
+
+```
+openssl cms -verify -in <portable-zip-or-tgz-file-name>.pkcs1.sig -inform DER -content <portable-zip-or-tgz-file-name> -out nul -noverify
+```
+
+> [!NOTE]
+> Please ensure that `openssl` is installed on your system before verifying signature.

docs/mddocs/Quickstart/ollama_portable_zip_quickstart.zh-CN.md

@@ -29,6 +29,7 @@
   - [在多块 GPU 可用时选择特定的 GPU 来运行 Ollama](#在多块-gpu-可用时选择特定的-gpu-来运行-ollama)
   - [性能调优](#性能调优)
   - [Ollama v0.5.4 之后新增模型支持](#ollama-v054-之后新增模型支持)
+  - [签名验证](#签名验证)
 - [更多信息](ollama_quickstart.zh-CN.md)
 
 ## Windows用户指南
@@ -218,4 +219,15 @@ Ollama 默认从 Ollama 库下载模型。通过在**运行 Ollama 之前**设
 | Smallthinker | `ollama run smallthinker` |`./ollama run smallthinker` | [smallthinker](https://ollama.com/library/smallthinker) |
 | Granite3.1-Dense |  `ollama run granite3-dense` | `./ollama run granite3-dense` | [granite3.1-dense](https://ollama.com/library/granite3.1-dense) |
 | Granite3.1-Moe-3B | `ollama run granite3-moe` | `./ollama run granite3-moe` | [granite3.1-moe](https://ollama.com/library/granite3.1-moe) |
-| Gemma 3 1B | `set IPEX_LLM_MODEL_SOURCE=modelscope` <br> `ollama run gemma3:1b` | `export IPEX_LLM_MODEL_SOURCE=modelscope` <br> `./ollama run gemma3:1b`|  [gemma3:1b](https://www.modelscope.cn/models/lmstudio-community/gemma-3-1b-it-GGUF) |
+| Gemma 3 1B | `set IPEX_LLM_MODEL_SOURCE=modelscope` <br> `ollama run gemma3:1b` | `export IPEX_LLM_MODEL_SOURCE=modelscope` <br> `./ollama run gemma3:1b`|  [gemma3:1b](https://www.modelscope.cn/models/lmstudio-community/gemma-3-1b-it-GGUF) |
+
+### 签名验证
+
+针对 2.2.0 版本的 portable zip/tgz, 可以使用如下命令验证其签名：
+
+```
+openssl cms -verify -in <portable-zip-or-tgz-file-name>.pkcs1.sig -inform DER -content <portable-zip-or-tgz-file-name> -out nul -noverify
+```
+
+> [!NOTE]
+> 在验证签名之前，请确保已在系统上安装 `openssl`。