comfyui-gfx1151/README.md

# ComfyUI for gfx1151 (Ryzen AI MAX / Strix Halo)

Dockerized ComfyUI with PyTorch & flash-attention for **gfx1151** (AMD Strix Halo,
e.g. Ryzen AI Max+ 395 — Minisforum MS-S1 Max, Framework Desktop), based on AMD's
pre-built and pre-configured `rocm/pytorch` image (no custom wheels needed).

This is my working setup, adapted from
[ignatberesnev/comfyui-gfx1151](https://hub.docker.com/r/ignatberesnev/comfyui-gfx1151)
(see [Acknowledgements](#acknowledgements)). The difference here: this repo is meant to
be **built locally** with `docker compose build` — no image pull required.

Reported working on:

* Minisforum MS-S1 Max (Ryzen AI Max+ 395, gfx1151) — daily driver
* AMD Radeon RX 9700 (gfx1201), 32 GB — works out of the box (thanks!)

Versions used:

* ROCm: 7.2.4
* PyTorch: 2.9.1
* Python: 3.12
* ComfyUI: whatever you clone (see below)

> [!NOTE]
> I got this working after a day of digging, and the final solution turned out to be
> much simpler than most of what's out there. I don't claim to understand every moving
> part — if you know better, PRs and comments welcome.

## Get started

### 1. Clone ComfyUI yourself

The container mounts ComfyUI from the host, so you can update it independently of the
image. Clone it into this directory (or anywhere — just adjust the volume path in
`docker-compose.yml`):

```bash
git clone https://github.com/comfyanonymous/ComfyUI
```

If the mounted directory is empty when the container starts, a pre-cloned (baked-in)
copy of ComfyUI is copied into it automatically — but bringing your own clone is the
recommended way.

### 2. Build and run

```bash
docker compose up -d --build
```

ComfyUI is available at http://localhost:8188. The starter templates should generate
images without any issues.

### 3. Verify the GPU works

While the container is running:

```bash
# PyTorch sees the GPU
docker exec -it comfyui /bin/bash /opt/comfyui-gfx1151-utils/test-pytorch.sh

# flash-attention (Triton backend) works
docker exec -it comfyui python3 /opt/comfyui-gfx1151-utils/test-pytorch-flashattention.py
```

Both should run without errors (sample output in the
[upstream README](https://github.com/ignatberesnev/comfyui-gfx1151)).

## What's configured

In [docker-compose.yml](docker-compose.yml):

* `build: .` — image is built from the [Dockerfile](Dockerfile) in this repo
* `shm_size: 8G` — shared memory for PyTorch/ComfyUI. Should NOT be larger than
  available RAM; this is **not** VRAM. Feel free to lower it.
* `./ComfyUI:/opt/ComfyUI` — your ComfyUI clone (models, custom nodes, output all live
  in here)
* Port `8188` exposed
* `/dev/kfd`, `/dev/dri` + `video`/`render` groups — GPU access. Works as-is on Arch;
  may need extra steps on Ubuntu, untested.
* `TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1` — enables the experimental AOTriton
  backend

No reverse proxy / external network is configured — it binds `8188` directly. Put it
behind whatever you like if you need auth/TLS.

## Updating

* **ComfyUI**: `cd ComfyUI && git pull`, then `docker compose restart`. Custom nodes:
  the ComfyUI Manager is enabled (`--enable-manager`), or install from inside the
  container:

  ```bash
  docker exec -it comfyui /bin/bash
  cd /opt/ComfyUI && pip install -r requirements.txt
  ```

* **ROCm / PyTorch**: bump the `FROM rocm/pytorch:...` line in the
  [Dockerfile](Dockerfile) and the `image:` tag in `docker-compose.yml`, then
  `docker compose up -d --build`.

## What's inside / how it works

The image is based on AMD's [rocm/pytorch](https://hub.docker.com/r/rocm/pytorch)
image (Ubuntu 24.04, ROCm, Python 3.12, PyTorch) where everything is configured to
work together — see
[AMD's docs](https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/docs/install/installryz/native_linux/install-pytorch.html#use-docker-image-with-pre-installed-pytorch).

Only two pieces are added: ComfyUI (nothing special — bring your own clone) and
**flash-attention**. The latter "doesn't work" out of the box on AMD's image: it lacks
the frontend APIs but ships the Triton backend. Setting
`FLASH_ATTENTION_TRITON_AMD_ENABLE=TRUE` makes flash-attention install fast and route
to Triton, which does the actual work. It's cloned from the `main_perf` branch of
[ROCm/flash-attention](https://github.com/ROCm/flash-attention/) — that's what others
(vLLM on Strix Halo, [kyuz0](https://github.com/kyuz0)'s setups) use, presumably for
Triton support not yet in `main` (see
[ROCm/flash-attention#27](https://github.com/ROCm/flash-attention/issues/27)).

The `scripts/` directory holds the test scripts above; they're baked into the image at
`/opt/comfyui-gfx1151-utils/`.

## What did NOT work (so you don't try it)

* Custom-built wheel setups (e.g.
  [pccr10001/comfyui-gfx1151-fa](https://github.com/pccr10001/comfyui-gfx1151-fa)) —
  never worked for me, presumably non-locked dependencies pulling newer ROCm under old
  wheels. Huge thanks to them for the pointers though.
* `ghcr.io/rocm/therock_pytorch_dev_ubuntu_24_04_gfx1151` — no longer published.
* Speed "tuning" env vars (`PYTORCH_TUNABLEOP_ENABLED`, `MIOPEN_FIND_MODE`,
  `ROCBLAS_USE_HIPBLASLT`) — made things slower and (probably) crashed my X11 display
  server during SD runs. Don't add them unless you enjoy that.

## Acknowledgements

* [ignatberesnev](https://github.com/ignatberesnev) — original repo this is based on
* [pccr10001](https://github.com/pccr10001), [lhl](https://github.com/lhl),
  [kyuz0](https://github.com/kyuz0) — for setting everyone on the right path