ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Add PyTorch 2.6 support in Latest Update (#13144)

Browse source
This commit is contained in:
Yuwen Hu 2025-05-09 13:26:49 +08:00 committed by GitHub
parent 45f7bf6688
commit 0438e39f3e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 4 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
README.md
View file

@ -10,6 +10,7 @@
## Latest Update 🔥 ## Latest Update 🔥
- [2025/04] We released `ipex-llm 2.2.0`, which includes [Ollama Portable Zip](docs/mddocs/Quickstart/ollama_portable_zip_quickstart.md) and [llama.cpp Portable Zip](docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.md). - [2025/04] We released `ipex-llm 2.2.0`, which includes [Ollama Portable Zip](docs/mddocs/Quickstart/ollama_portable_zip_quickstart.md) and [llama.cpp Portable Zip](docs/mddocs/Quickstart/llamacpp_portable_zip_gpu_quickstart.md).
- [2025/04] We added support of [PyTorch 2.6](docs/mddocs/Quickstart/install_pytorch26_gpu.md) for Intel GPU.
- [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 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). - [2025/03] 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/ipex-llm/ipex-llm/releases/tag/v2.3.0-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). - [2025/02] We added support of [llama.cpp Portable Zip](https://github.com/ipex-llm/ipex-llm/releases/tag/v2.3.0-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).

1
README.zh-CN.md
View file

@ -10,6 +10,7 @@
## 最新更新 🔥 ## 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/ipex-llm/ipex-llm/releases/tag/v2.2.0)。 - [2025/04] 发布 `ipex-llm 2.2.0`, 其中包括 [Ollama Portable Zip 和 llama.cpp Portable Zip](https://github.com/ipex-llm/ipex-llm/releases/tag/v2.2.0)。
- [2025/04] 新增在 Intel GPU 上对于 [PyTorch 2.6](docs/mddocs/Quickstart/install_pytorch26_gpu.md) 的支持。
- [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] 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**。 - [2025/03] 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**。 - [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**。

1
docs/mddocs/README.md
View file

@ -7,6 +7,7 @@
## Latest Update 🔥 ## Latest Update 🔥
- [2025/04] We released `ipex-llm 2.2.0`, which includes [Ollama Portable Zip and llama.cpp Portable Zip](https://github.com/ipex-llm/ipex-llm/releases/tag/v2.2.0). - [2025/04] We released `ipex-llm 2.2.0`, which includes [Ollama Portable Zip and llama.cpp Portable Zip](https://github.com/ipex-llm/ipex-llm/releases/tag/v2.2.0).
- [2025/04] We added support of [PyTorch 2.6](docs/mddocs/Quickstart/install_pytorch26_gpu.md) for Intel GPU.
- [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). - [2025/03] 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 [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***). - [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***).

1
docs/mddocs/README.zh-CN.md
View file

@ -7,6 +7,7 @@
## 最新更新 🔥 ## 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/ipex-llm/ipex-llm/releases/tag/v2.2.0)。 - [2025/04] 发布 `ipex-llm 2.2.0`, 其中包括 [Ollama Portable Zip 和 llama.cpp Portable Zip](https://github.com/ipex-llm/ipex-llm/releases/tag/v2.2.0)。
- [2025/04] 新增在 Intel GPU 上对于 [PyTorch 2.6](docs/mddocs/Quickstart/install_pytorch26_gpu.md) 的支持。
- [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**。 - [2025/03] 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 [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))。 - [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))。