ipex-llm 2.2.0 post-release update (#13053)

* Update ollama/llama.cpp release link to 2.2.0 (#13052)

* Post-update for releasing ipex-llm 2.2.0

README.md

@@ -9,6 +9,7 @@
 > - ***70+ models** have been optimized/verified on `ipex-llm` (e.g., Llama, Phi, Mistral, Mixtral, DeepSeek, Qwen, ChatGLM, MiniCPM, Qwen-VL, MiniCPM-V and more), with state-of-art **LLM optimizations**, **XPU acceleration** and **low-bit (FP8/FP6/FP4/INT4) support**; see the complete list [here](#verified-models).*
 
 ## Latest Update 🔥 
+- [2025/04] We released `ipex-llm 2.2.0`, which includes [Ollama Portable Zip and llama.cpp Portable Zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0).
 - [2025/03] We added support for **Gemma3** model in the latest [llama.cpp Portable Zip](https://github.com/intel/ipex-llm/issues/12963#issuecomment-2724032898).
 - [2025/03] We can now run **DeepSeek-R1-671B-Q4_K_M** with 1 or 2 Arc A770 on Xeon using the latest [llama.cpp Portable Zip](docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.md#flashmoe-for-deepseek-v3r1).
 - [2025/02] We added support of [llama.cpp Portable Zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) for Intel **GPU** (both [Windows](docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.md#windows-quickstart) and [Linux](docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.md#linux-quickstart)) and **NPU** ([Windows](docs/mddocs/Quickstart/llama_cpp_npu_portable_zip_quickstart.md) only).

README.zh-CN.md

@@ -9,6 +9,7 @@
 > - ***70+** 模型已经在 `ipex-llm` 上得到优化和验证（如 Llama, Phi, Mistral, Mixtral, DeepSeek, Qwen, ChatGLM, MiniCPM, Qwen-VL, MiniCPM-V 等）, 以获得先进的 **大模型算法优化**, **XPU 加速** 以及 **低比特（FP8FP8/FP6/FP4/INT4）支持**；更多模型信息请参阅[这里](#模型验证)。*
 
 ## 最新更新 🔥 
+- [2025/04] 发布 `ipex-llm 2.2.0`, 其中包括 [Ollama Portable Zip 和 llama.cpp Portable Zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0)。
 - [2025/03] 通过最新 [llama.cpp Portable Zip](https://github.com/intel/ipex-llm/issues/12963#issuecomment-2724032898) 可运行 **Gemma3** 模型。
 - [2025/03] 使用最新 [llama.cpp Portable Zip](docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.zh-CN.md#flashmoe-运行-deepseek-v3r1), 可以在 Xeon 上通过1到2张 Arc A770 GPU 运行 **DeepSeek-R1-671B-Q4_K_M**。
 - [2025/02] 新增 [llama.cpp Portable Zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) 在 Intel **GPU** (包括 [Windows](docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.zh-CN.md#windows-用户指南) 和 [Linux](docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.zh-CN.md#linux-用户指南)) 和 **NPU** (仅 [Windows](docs/mddocs/Quickstart/llama_cpp_npu_portable_zip_quickstart.zh-CN.md)) 上直接**免安装运行 llama.cpp**。

docs/mddocs/Quickstart/llama_cpp_npu_portable_zip_quickstart.md

@@ -3,7 +3,7 @@
   <b>< English</b> | <a href='./llama_cpp_npu_portable_zip_quickstart.zh-CN.md'>中文</a> >
 </p>
 
-IPEX-LLM provides llama.cpp support for running GGUF models on Intel NPU. This guide demonstrates how to use [llama.cpp NPU portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) to directly run on Intel NPU (without the need of manual installations).
+IPEX-LLM provides llama.cpp support for running GGUF models on Intel NPU. This guide demonstrates how to use [llama.cpp NPU portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0) to directly run on Intel NPU (without the need of manual installations).
 
 > [!IMPORTANT]
 > 
@@ -29,7 +29,7 @@ Check your NPU driver version, and update it if needed:
 
 ## Step 1: Download and Unzip
 
-Download IPEX-LLM llama.cpp NPU portable zip for Windows users from the [link](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly).
+Download IPEX-LLM llama.cpp NPU portable zip for Windows users from the [link](https://github.com/intel/ipex-llm/releases/tag/v2.2.0).
 
 Then, extract the zip file to a folder.
 

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

@@ -3,7 +3,7 @@
    < <a href='./llama_cpp_npu_portable_zip_quickstart.md'>English</a> | <b>中文</b> >
 </p>
 
-IPEX-LLM 提供了 llama.cpp 的相关支持以在 Intel NPU 上运行 GGUF 模型。本指南演示如何使用 [llama.cpp NPU portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) 在 Intel NPU 上直接免安装运行。
+IPEX-LLM 提供了 llama.cpp 的相关支持以在 Intel NPU 上运行 GGUF 模型。本指南演示如何使用 [llama.cpp NPU portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0) 在 Intel NPU 上直接免安装运行。
 
 > [!IMPORTANT]
 > 
@@ -29,7 +29,7 @@ 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
 
-从此[链接](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly)下载 IPEX-LLM llama.cpp NPU portable zip。
+从此[链接](https://github.com/intel/ipex-llm/releases/tag/v2.2.0)下载 IPEX-LLM llama.cpp NPU portable zip。
 
 然后，将 zip 文件解压到一个文件夹中。
 

docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.md

@@ -6,7 +6,7 @@
 >[!Important]
 > You can now run **DeepSeek-R1-671B-Q4_K_M** with 1 or 2 Arc A770 on Xeon using the latest *llama.cpp Portable Zip*; see the [guide](#flashmoe-for-deepseek-v3r1) below.
 
-This guide demonstrates how to use [llama.cpp portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) to directly run llama.cpp on Intel GPU with `ipex-llm` (without the need of manual installations).
+This guide demonstrates how to use [llama.cpp portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0) to directly run llama.cpp on Intel GPU with `ipex-llm` (without the need of manual installations).
 
 > [!NOTE]
 > llama.cpp portable zip has been verified on:
@@ -42,7 +42,7 @@ We recommend updating your GPU driver to the [latest](https://www.intel.com/cont
 
 ### Step 1: Download and Unzip
 
-Download IPEX-LLM llama.cpp portable zip for Windows users from the [link](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly).
+Download IPEX-LLM llama.cpp portable zip for Windows users from the [link](https://github.com/intel/ipex-llm/releases/tag/v2.2.0).
 
 Then, extract the zip file to a folder.
 
@@ -126,7 +126,7 @@ Check your GPU driver version, and update it if needed; we recommend following [
 
 ### Step 1: Download and Extract
 
-Download IPEX-LLM llama.cpp portable tgz for Linux users from the [link](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly).
+Download IPEX-LLM llama.cpp portable tgz for Linux users from the [link](https://github.com/intel/ipex-llm/releases/tag/v2.2.0).
 
 Then, extract the tgz file to a folder.
 

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

@@ -3,7 +3,7 @@
    < <a href='./llamacpp_portable_zip_gpu_quickstart.md'>English</a> | <b>中文</b> >
 </p>
      
-本指南演示如何使用 [llama.cpp portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) 通过 `ipex-llm` 在 Intel GPU 上直接免安装运行。
+本指南演示如何使用 [llama.cpp portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0) 通过 `ipex-llm` 在 Intel GPU 上直接免安装运行。
 
 > [!Important]
 > 使用最新版 *llama.cpp Portable Zip* 可以在 Xeon 上通过1到2张 Arc A770 GPU 运行 **DeepSeek-R1-671B-Q4_K_M**；详见如下[指南](#flashmoe-运行-deepseek-v3r1)。
@@ -42,7 +42,7 @@
 
 ### 步骤 1：下载与解压
 
-对于 Windows 用户，请从此[链接](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly)下载 IPEX-LLM llama.cpp portable zip。
+对于 Windows 用户，请从此[链接](https://github.com/intel/ipex-llm/releases/tag/v2.2.0)下载 IPEX-LLM llama.cpp portable zip。
 
 然后，将 zip 文件解压到一个文件夹中。
 
@@ -128,7 +128,7 @@ llama_perf_context_print:       total time =   xxxxx.xx ms /  1385 tokens
 
 ### 步骤 1：下载与解压
 
-对于 Linux 用户，从此[链接](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly)下载 IPEX-LLM llama.cpp portable tgz。
+对于 Linux 用户，从此[链接](https://github.com/intel/ipex-llm/releases/tag/v2.2.0)下载 IPEX-LLM llama.cpp portable tgz。
 
 然后，将 tgz 文件解压到一个文件夹中。
 

docs/mddocs/Quickstart/ollama_portable_zip_quickstart.md

@@ -3,7 +3,7 @@
   <b>< English</b> | <a href='./ollama_portable_zip_quickstart.zh-CN.md'>中文</a> >
 </p>
 
-This guide demonstrates how to use [Ollama portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) to directly run Ollama on Intel GPU with `ipex-llm` (without the need of manual installations).
+This guide demonstrates how to use [Ollama portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0) to directly run Ollama on Intel GPU with `ipex-llm` (without the need of manual installations).
 
 > [!NOTE]
 > Ollama portable zip has been verified on:
@@ -43,7 +43,7 @@ We recommend updating your GPU driver to the [latest](https://www.intel.com/cont
 
 ### Step 1: Download and Unzip
 
-Download IPEX-LLM Ollama portable zip for Windows users from the [link](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly).
+Download IPEX-LLM Ollama portable zip for Windows users from the [link](https://github.com/intel/ipex-llm/releases/tag/v2.2.0).
 
 Then, extract the zip file to a folder.
 
@@ -74,7 +74,7 @@ Check your GPU driver version, and update it if needed; we recommend following [
 
 ### Step 1: Download and Extract
 
-Download IPEX-LLM Ollama portable tgz for Ubuntu users from the [link](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly).
+Download IPEX-LLM Ollama portable tgz for Ubuntu users from the [link](https://github.com/intel/ipex-llm/releases/tag/v2.2.0).
 
 Then open a terminal, extract the tgz file to a folder.
 

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

@@ -3,7 +3,7 @@
    < <a href='./ollama_portable_zip_quickstart.md'>English</a> | <b>中文</b> >
 </p>
 
-本指南演示如何使用 [Ollama portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) 通过 `ipex-llm` 在 Intel GPU 上直接免安装运行 Ollama。
+本指南演示如何使用 [Ollama portable zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0) 通过 `ipex-llm` 在 Intel GPU 上直接免安装运行 Ollama。
 
 > [!NOTE]
 > Ollama portable zip 在如下设备上进行了验证:
@@ -43,7 +43,7 @@
 
 ### 步骤 1：下载和解压
 
-从此[链接](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly)下载 IPEX-LLM Ollama portable zip。
+从此[链接](https://github.com/intel/ipex-llm/releases/tag/v2.2.0)下载 IPEX-LLM Ollama portable zip。
 
 然后，将 zip 文件解压到一个文件夹中。
 
@@ -76,7 +76,7 @@
 
 ### 步骤 1：下载和解压
 
-从此[链接](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly)下载 IPEX-LLM Ollama portable tgz。
+从此[链接](https://github.com/intel/ipex-llm/releases/tag/v2.2.0)下载 IPEX-LLM Ollama portable tgz。
 
 然后，开启一个终端，输入如下命令将 tgz 文件解压到一个文件夹中。
 ```bash

docs/mddocs/README.md

@@ -6,6 +6,7 @@
 **`IPEX-LLM`** is an LLM acceleration library for Intel [GPU](Quickstart/install_windows_gpu.md) *(e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max)*, [NPU](Quickstart/npu_quickstart.md) and CPU [^1].
 
 ## Latest Update 🔥 
+- [2025/04] We released `ipex-llm 2.2.0`, which includes [Ollama Portable Zip and llama.cpp Portable Zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0).
 - [2025/03] We can now run **DeepSeek-R1-671B-Q4_K_M** with 1 or 2 Arc A770 on Xeon using the latest [llama.cpp Portable Zip](Quickstart/llamacpp_portable_zip_gpu_quickstart.md#flashmoe-for-deepseek-v3r1).
 - [2025/02] We added support of [llama.cpp Portable Zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) for Intel **GPU** (both [Windows](Quickstart/llamacpp_portable_zip_gpu_quickstart.md#windows-quickstart) and [Linux](Quickstart/llamacpp_portable_zip_gpu_quickstart.md#linux-quickstart)) and **NPU** ([Windows](Quickstart/llama_cpp_npu_portable_zip_quickstart.md) only).
 - [2025/02] We added support of [Ollama Portable Zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) to directly run Ollama on Intel **GPU** for both [Windows](Quickstart/ollama_portable_zip_quickstart.md#windows-quickstart) and [Linux](Quickstart/ollama_portable_zip_quickstart.md#linux-quickstart) (***without the need of manual installations***).

docs/mddocs/README.zh-CN.md

@@ -6,6 +6,7 @@
 **`ipex-llm`** 是一个将大语言模型高效地运行于 Intel [GPU](docs/mddocs/Quickstart/install_windows_gpu.md) *(如搭载集成显卡的个人电脑，Arc 独立显卡、Flex 及 Max 数据中心 GPU 等)*、[NPU](docs/mddocs/Quickstart/npu_quickstart.md) 和 CPU 上的大模型 XPU 加速库[^1]。 
 
 ## 最新更新 🔥 
+- [2025/04] 发布 `ipex-llm 2.2.0`, 其中包括 [Ollama Portable Zip 和 llama.cpp Portable Zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0)。
 - [2025/03] 使用最新 [llama.cpp Portable Zip](Quickstart/llamacpp_portable_zip_gpu_quickstart.zh-CN.md#flashmoe-运行-deepseek-v3r1), 可以在 Xeon 上通过1到2张 Arc A770 GPU 运行 **DeepSeek-R1-671B-Q4_K_M**。
 - [2025/02] 新增 [llama.cpp Portable Zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) 在 Intel **GPU** (包括 [Windows](Quickstart/llamacpp_portable_zip_gpu_quickstart.zh-CN.md#windows-用户指南) 和 [Linux](Quickstart/llamacpp_portable_zip_gpu_quickstart.zh-CN.md#linux-用户指南)) 和 **NPU** (仅 [Windows](Quickstart/llama_cpp_npu_portable_zip_quickstart.zh-CN.md)) 上直接**免安装运行 llama.cpp**。
 - [2025/02] 新增 [Ollama Portable Zip](https://github.com/intel/ipex-llm/releases/tag/v2.2.0-nightly) 在 Intel **GPU** 上直接**免安装运行 Ollama** (包括 [Windows](Quickstart/ollama_portable_zip_quickstart.zh-CN.md#windows用户指南) 和 [Linux](Quickstart/ollama_portable_zip_quickstart.zh-CN.md#linux用户指南))。

python/llm/setup.py

@@ -46,7 +46,7 @@ exclude_patterns = ["*__pycache__*", "*ipynb_checkpoints*"]
 IPEX_LLM_PYTHON_HOME = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 VERSION = open(os.path.join(IPEX_LLM_PYTHON_HOME,
                './llm/version.txt'), 'r').read().strip()
-CORE_XE_VERSION = VERSION.replace("2.2.0", "2.6.0")
+CORE_XE_VERSION = VERSION.replace("2.3.0", "2.7.0")
 llm_home = os.path.join(os.path.dirname(os.path.abspath(__file__)), "src")
 github_artifact_dir = os.path.join(llm_home, '../llm-binary')
 libs_dir = os.path.join(llm_home, "ipex_llm", "libs")

python/llm/version.txt

@@ -1 +1 @@
-2.2.0.dev0
+2.3.0.dev0