Skip to content

docs: fix armv9 llama.cpp compile issue #1402

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
zifeng-radxa wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: fix armv9 llama.cpp compile issue #1402

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion .typos.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,8 @@ extend-ignore-identifiers-re = [
"noe",
"NOE",
"BA",
"lin2-rin2"
"lin2-rin2",
"SME"
]
extend-ignore-re = [
"lin2-rin2",
Expand Down
13 changes: 8 additions & 5 deletions docs/common/ai/_llama_cpp.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ llama.cpp 是一个基于纯 C/C++ 实现的高性能大模型推理框架，它
<NewCodeBlock tip="Device" type="device">

```bash
git clone https://github.com/ggml-org/llama.cpp.git
git clone https://github.com/ggml-org/llama.cpp.git && cd llama.cpp
```

</NewCodeBlock>
Expand All @@ -23,7 +23,7 @@ git clone https://github.com/ggml-org/llama.cpp.git
<NewCodeBlock tip="Device" type="device">

```bash
sudo apt install cmake gcc g++
sudo apt install cmake gcc g++ libcurl4-openssl-dev
```

</NewCodeBlock>
Expand All @@ -39,15 +39,18 @@ cmake --build build --config Release -j$(nproc)

</NewCodeBlock>

:::info[KleidiAI]
:::info[ARMv9]
对于采用 ARM-v9 架构的 [瑞莎星睿 O6 / O6N](/orion/o6) 设备，可以开启 armv9-a 和 KleidiAI 编译选项进行硬件级优化。

**请使用 `4aced7a` commit**
:::

<NewCodeBlock tip="Device" type="device">

```bash
git checkout 4aced7a
cmake -B build -DGGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv9-a+i8mm+dotprod -DGGML_CPU_KLEIDIAI=ON
cmake --build build --config Release
cmake --build build --config Release -j$(nproc)
```

</NewCodeBlock>
Expand All @@ -60,7 +63,7 @@ Llama.cpp 已集成 Arm KleidiAI 库，该库针对 SME、I8MM 及点积加速

```bash
cmake -B build -DGGML_CPU_KLEIDIAI=ON
cmake --build build --config Release
cmake --build build --config Release -j$(nproc)
```

</NewCodeBlock>
Expand Down
11 changes: 7 additions & 4 deletions i18n/en/docusaurus-plugin-content-docs/current/common/ai/_llama_cpp.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ git clone https://github.com/ggml-org/llama.cpp.git
<NewCodeBlock tip="Device" type="device">

```bash
sudo apt install cmake gcc g++
sudo apt install cmake gcc g++ libcurl4-openssl-dev
```

</NewCodeBlock>
Expand All @@ -39,15 +39,18 @@ cmake --build build --config Release -j$(nproc)

</NewCodeBlock>

:::info[KleidiAI]
:::info[ARMv9]
On devices using the ARMv9 architecture, such as [Radxa Orion O6 / O6N](/orion/o6), you can enable the `armv9-a` and KleidiAI build options for hardware-level optimization.

**Please use `4aced7a` commit**.
:::

<NewCodeBlock tip="Device" type="device">

```bash
git checkout 4aced7a
cmake -B build -DGGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv9-a+i8mm+dotprod -DGGML_CPU_KLEIDIAI=ON
cmake --build build --config Release
cmake --build build --config Release -j$(nproc)
```

</NewCodeBlock>
Expand All @@ -60,7 +63,7 @@ llama.cpp integrates the Arm KleidiAI library, which provides highly optimized m

```bash
cmake -B build -DGGML_CPU_KLEIDIAI=ON
cmake --build build --config Release
cmake --build build --config Release -j$(nproc)
```

</NewCodeBlock>
Expand Down
Loading