Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
11 changes: 11 additions & 0 deletions installation/system_requirements.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -66,4 +66,15 @@ Please refer to the manual installation section for detailed installation steps.

## FAQ

<Accordion title="Does ComfyUI support MLX (Apple's machine learning framework)?">
ComfyUI does not use MLX directly. On Apple Silicon (M1/M2/M3/M4) Macs, ComfyUI uses PyTorch with the **MPS (Metal Performance Shaders)** backend, which leverages Apple's Metal graphics framework for GPU acceleration.

MLX is a separate machine-learning array framework designed for Apple Silicon. ComfyUI's PyTorch-based architecture uses MPS instead.

To verify MPS is working on your Mac:
```bash
python -c "import torch; print(torch.backends.mps.is_available())"
```
</Accordion>

<DockerNotice />
13 changes: 12 additions & 1 deletion ja/installation/system_requirements.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ title: "システム要件"
description: "ComfyUIをインストールして実行するためのハードウェアとソフトウェアの要件"
sidebarTitle: "システム要件"
icon: "computer"
translationSourceHash: db65e98b
translationSourceHash: 9a71d8f9
translationFrom: installation/system_requirements.mdx
---

Expand Down Expand Up @@ -68,4 +68,15 @@ Windows ポータブル版には現在、Python 3.13 と PyTorch CUDA 13.0 が

## よくある質問

<Accordion title="ComfyUIはMLX(Appleの機械学習フレームワーク)をサポートしていますか?">
ComfyUIはMLXを直接使用しません。Apple Silicon(M1/M2/M3/M4)Macでは、PyTorchの **MPS(Metal Performance Shaders)** バックエンドを使用して、AppleのMetalグラフィックスフレームワークによるGPUアクセラレーションを活用します。

MLXはApple Silicon向けに設計された独立した機械学習配列フレームワークです。ComfyUIのPyTorchベースのアーキテクチャでは、代わりにMPSを使用しています。

お使いのMacでMPSが動作していることを確認するには:
```bash
python -c "import torch; print(torch.backends.mps.is_available())"
```
</Accordion>

<DockerNotice />
13 changes: 12 additions & 1 deletion ko/installation/system_requirements.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ title: "시스템 요구사항"
description: "ComfyUI 설치 및 실행을 위한 하드웨어 및 소프트웨어 요구 사항."
sidebarTitle: "시스템 요구사항"
icon: "computer"
translationSourceHash: db65e98b
translationSourceHash: 9a71d8f9
translationFrom: installation/system_requirements.mdx
---

Expand Down Expand Up @@ -68,4 +68,15 @@ PyTorch 2.4 이상도 지원되지만, 일부 기능과 최적화는 최신 버

## 자주 묻는 질문

<Accordion title="ComfyUI가 MLX(Apple의 머신러닝 프레임워크)를 지원하나요?">
ComfyUI는 MLX를 직접 사용하지 않습니다. Apple Silicon(M1/M2/M3/M4) Mac에서 ComfyUI는 PyTorch의 **MPS(Metal Performance Shaders)** 백엔드를 사용하여 Apple의 Metal 그래픽스 프레임워크로 GPU 가속을 활용합니다.

MLX는 Apple Silicon을 위해 설계된 별도의 머신러닝 배열 프레임워크입니다. ComfyUI의 PyTorch 기반 아키텍처는 MPS를 대신 사용합니다.

Mac에서 MPS가 정상 작동하는지 확인하려면:
```bash
python -c "import torch; print(torch.backends.mps.is_available())"
```
</Accordion>

<DockerNotice />
13 changes: 12 additions & 1 deletion zh/installation/system_requirements.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ title: "系统要求"
description: "安装和运行 ComfyUI 的硬件和软件要求"
sidebarTitle: "系统要求"
icon: "computer"
translationSourceHash: db65e98b
translationSourceHash: 9a71d8f9
translationFrom: installation/system_requirements.mdx
---

Expand Down Expand Up @@ -68,4 +68,15 @@ Windows 便携版目前附带 Python 3.13 和 PyTorch CUDA 13.0。如果无法

## 常见问题

<Accordion title="ComfyUI 是否支持 MLX(Apple 的机器学习框架)?">
ComfyUI 不直接使用 MLX。在 Apple Silicon(M1/M2/M3/M4)Mac 上,ComfyUI 使用 PyTorch 的 **MPS(Metal Performance Shaders)** 后端,利用 Apple 的 Metal 图形框架进行 GPU 加速。

MLX 是 Apple 为 Apple Silicon 设计的一个独立的机器学习数组框架。ComfyUI 基于 PyTorch 架构,所以使用 MPS 而非 MLX。

要验证 MPS 是否在你的 Mac 上正常工作:
```bash
python -c "import torch; print(torch.backends.mps.is_available())"
```
</Accordion>

<DockerNotice />
Loading