在 “小小容器” WasmEdge 里运行小小羊驼 llama 2

 昨天,特斯拉前 AI 总监、OpenAI 联合创始人 Andrej Karpathy 开源了 llama2.c 。 只用 500 行纯 C 语言就能训练和推理 llama 2 模型的框架,没有任何繁杂的 python 依赖。这个项目一推出就受到大家的追捧,24 小时内 GitHub 收获 4000 颗星!

可是,C 编译的原生机器码不能跨平台,不安全,也不可被调度。这些问题使得它的应用场景非常有限。这时,一个大胆的想法油然而生!把 llama2.c 编译成 Wasm 在 WasmEdge 里运行!

在 “小小容器” WasmEdge 里运行小小羊驼 llama 2_第1张图片

​图片来自 https://github.com/karpathy/llama2.c 



这么做的好处是:

  • 轻量级:一个 Wasm 文件只有几十 KB 大小,相比于 Python 镜像动辄几百上千 MB,差了一万倍。
  • 安全:沙箱机制,提供隔离性,适合多租户的云部署。
  • 可移植:Wasm 文件无需任何改变,可以在 x86, ARM, Apple, RISC-V 机器上运行
  • 性能:没有冷启动,且运行速度接近本机速度
  • 能够被 Docker 和 kuberbetes 等容器工具进行管理


下面,我们来具体看看是如何实现的。

 

先决条件

请参考 WasmEdge 的官方文档安装 WasmEdge runtime。

curl -sSf https://raw.githubusercontent.com/WasmEdge/WasmEdge/master/utils/install.sh | sudo bash -s — -p /usr/local

准备 wasi-sdk

export WASI_VERSION=20
export WASI_VERSION_FULL=${WASI_VERSION}.0
wget https://github.com/WebAssembly/wasi-sdk/releases/download/wasi-sdk-${WASI_VERSION}/wasi-sdk-${WASI_VERSION_FULL}-linux.tar.gz
tar xvf wasi-sdk-${WASI_VERSION_FULL}-linux.tar.gz
export WASI_SDK_PATH=`pwd`/wasi-sdk-${WASI_VERSION_FULL}
CC="${WASI_SDK_PATH}/bin/clang --sysroot=${WASI_SDK_PATH}/share/wasi-sysroot"

把 llama2.c 编译成 Wasm

git clone https://github.com/karpathy/llama2.c.git
cd llama2.c
$CC run.c -D_WASI_EMULATED_PROCESS_CLOCKS -lwasi-emulated-process-clocks -o run.wasm

优化 wasm file 并且运行


这里我们将使用 WasmEdge 的 AOT 编译器对编译好的 Wasm 文件进行优化,以提升 Wasm 的性能。

$ wget https://karpathy.ai/llama2c/model.bin -P out
$ wasmedgec run.wasm run-aot.wasm
[2023-07-24 16:39:52.851] [info] compile start
[2023-07-24 16:39:52.858] [info] verify start
[2023-07-24 16:39:52.862] [info] optimize start
[2023-07-24 16:39:53.251] [info] codegen start
[2023-07-24 16:39:53.608] [info] output start
[2023-07-24 16:39:53.611] [info] compile done
[2023-07-24 16:39:53.611] [info] output start


运行这个 wasm 文件

$ wasmedge --dir .:. run-aot.wasm out/model.bin


输出如下:

Once upon a time, there was a wealthy man. He lived in a big house with many things. The wealthy man liked to play in the fog.
One day, the wealthy man saw that the fog was increasing. The fog was getting stronger and the weight on the man's body made it hard to walk. The man said, "Oh no, I need to find a place to stop."
The wealthy man walked and walked, looking for a safe place. Soon, he found a small house. To his surprise, the house was full of toys and candy! The man said, "I found this house of good value. I can keep all the toys and candy in it." And from that day on, the wealthy man never played in the fog again.

 Once upon a time, there was a little girl named Lily. She loved to play with her toys and sing songs. One day, Lily's friend Timmy came over to play.
"Hi Lily, do you want to play with my new toy car?" asked Timmy.
"Yay, thank you!" replied Lily.
But after a while, Lily started to feel sleep
achieved tok/s: 30.738912

就是这样啦。 WasmEdge 也将逐步支持 Llama2 7B 及更大的 model。


最后。 如果你有兴趣使用 Wasm 作为 Python 的高性能替代品在生产环境中进行 AI 推理,请查看我们基于 Rust 的库 mediapipe-rs。 这是 Google 的 mediapipe 模型。同时支持 TF Lite 和 Pytorch!

https://github.com/WasmEdge/mediapipe-rsicon-default.png?t=N6B9https://github.com/WasmEdge/mediapipe-rs

你可能感兴趣的:(人工智能,开源,c语言)