Upload folder using huggingface_hub

.gitattributes

@@ -8,6 +8,8 @@
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.mds filter=lfs diff=lfs merge=lfs -text
 *.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +35,29 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text
+# Video files - compressed
+*.mp4 filter=lfs diff=lfs merge=lfs -text
+*.webm filter=lfs diff=lfs merge=lfs -text
+wheels/flash_attn-2.7.4+cu130torch2.9-cp312-cp312-linux_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+wheels/sageattention-2.2.0-cp312-cp312-linux_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+wheels/sageattn3-1.0.0-cp312-cp312-linux_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+wheels/torchaudio-2.9.1+a224ab2-cp312-cp312-linux_x86_64.whl filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,4 @@
+flash-attention
+sageattention
+torchaudio
+tmp

Dockerfile

@@ -0,0 +1,39 @@
+ARG CONTAINER_VERSION=25.10-py3
+FROM nvcr.io/nvidia/pytorch:${CONTAINER_VERSION}
+LABEL maintainer="Juan Treminio <jtreminio@gmail.com>"
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV DOTNET_INSTALL_DIR=/usr/share/dotnet
+ENV DOTNET_ROOT=${DOTNET_INSTALL_DIR}
+
+RUN apt update &&\
+    apt install -y libgl1-mesa-dev ffmpeg libglib2.0-0 libgl1 &&\
+    apt-get autoclean &&\
+    apt-get -y --purge autoremove &&\
+    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* /usr/share/{man,doc}
+
+RUN curl -fsSL https://dot.net/v1/dotnet-install.sh -o /tmp/dotnet-install.sh &&\
+    chmod +x /tmp/dotnet-install.sh &&\
+    /tmp/dotnet-install.sh --version latest --install-dir "${DOTNET_INSTALL_DIR}" &&\
+    rm -f /tmp/dotnet-install.sh
+
+ENV PATH="${DOTNET_INSTALL_DIR}:${PATH}"
+
+COPY wheels /tmp/wheels
+RUN python -m pip install --upgrade \
+    torchao>=0.15.0 \
+    safetensors>=0.7.0 \
+    torchsde>=0.2.6 \
+    rotary_embedding_torch>=0.8.9 \
+    tokenizers>=0.22.2 \
+    SQLAlchemy>=2.0.45 \
+    &&\
+    python -m pip install --no-cache-dir /tmp/wheels/*.whl \
+    && rm -rf /tmp/wheels
+
+ENV LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libcuda.so.1
+ENV SWARM_NO_VENV=true
+RUN git config --global --add safe.directory '*'
+EXPOSE 7801
+
+ENTRYPOINT ["bash", "/workspace/launch-linux-dev.sh", "--launch_mode", "none", "--host", "0.0.0.0"]

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Juan Treminio
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README

@@ -0,0 +1,60 @@
+# swarm-container
+
+This repo builds a [SwarmUI](https://github.com/mcmonkeyprojects/SwarmUI)-ready container with:
+
+* [flash_attn @ 2.7.4](https://github.com/Dao-AILab/flash-attention)
+* [sageattention @ 2.2.0](https://github.com/thu-ml/SageAttention)
+* [sageattn @ 3 (compiled)](https://github.com/thu-ml/SageAttention/tree/main/sageattention3_blackwell)
+* [torchaudio @ 2.9.1 (compiled)](https://github.com/pytorch/audio)
+
+It is built on top of the [nvidia PyTorch images nvcr.io/nvidia/pytorch](https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/index.html).
+
+# Requirements
+
+* A Blackwell GPU
+    * RTX 50-series
+    * RTX Pro 6000
+    * RTX Pro 5000
+* Docker or Podman
+
+# Getting Started
+
+The image is available on DockerHub, so all you need to do is have the [SwarmUI repo](https://github.com/mcmonkeyprojects/SwarmUI) cloned locally.
+Replace `/path/to/SwarmUI` with the path you've cloned SwarmUI at locally and run one of the following:
+
+## All model paths as default
+
+```bash
+docker run --gpus all --rm -it --shm-size=512m --name swarmui \
+    -p 7801:7801 \
+    -v /path/to/SwarmUI:/workspace \
+    jtreminio/swarmui:latest
+```
+
+Then navigate to [http://localhost:7801/](http://localhost:7801/).
+
+## Define different model and config paths
+
+```bash
+docker run --gpus all --rm -it --shm-size=512m --name swarmui \
+    -p 7801:7801 \
+    -v /path/to/SwarmUI:/workspace \
+    -v /path/to/local/output_directory:/workspace/Output \
+    -v /path/to/local/wildcard_directory:/workspace/Data/Wildcards \
+    jtreminio/swarmui:latest
+```
+
+Then navigate to [http://localhost:7801/](http://localhost:7801/).
+
+# Building
+
+If you would like to build the image for yourself, simply run:
+
+```bash
+# compiles flash_attn, sageattention, torchaudio, etc
+./step-1.sh
+# builds the Docker image for reuse
+./step-2.sh
+```
+
+There are two steps because `docker build` does not have a `--gpus all` option, so you cannot compile anything that requires a GPU.

VERSION

@@ -0,0 +1 @@
+25.10-py3

compile-sageattention.sh

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+set -e
+set -o pipefail
+
+python -m pip install -U wheel setuptools
+
+cd /workspace/sageattention
+python setup.py install
+python setup.py bdist_wheel
+cp -av /workspace/sageattention/dist/*.whl /workspace/wheels
+
+cd /workspace/sageattention/sageattention3_blackwell
+python setup.py install
+python setup.py bdist_wheel
+cp -av /workspace/sageattention/sageattention3_blackwell/dist/*.whl /workspace/wheels

compile-torchaudio.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+set -e
+set -o pipefail
+
+cd /workspace/torchaudio
+apt update
+apt update && apt install -y libsox-dev libavformat-dev libavcodec-dev libavutil-dev libavdevice-dev ffmpeg libavfilter-dev libswresample-dev libswscale-dev
+pip install -U pynvml>=12.0.0 sentencepiece soundfile cmake ninja cupy-cuda13x cuda-python nvidia-ml-py pybind11 torchcodec
+
+export PYTORCH_VERSION="$(python3 -c 'import torch; print(torch.__version__)')"
+export USE_CUDA=1
+export USE_FFMPEG=1
+export BUILD_SOX=1
+export TORIO_USE_FFMPEG_VERSION=6  
+export TORCH_CUDA_ARCH_LIST="8.7 9.0 10.0 11.0+PTX"
+export CUDA_ARCH_LIST="8.7 9.0 10.0 11.0"
+export USE_CUDNN=1
+export USE_CUSPARSELT=1
+PYBIND11_INC="$(python3 -c 'import pybind11, sys; print(pybind11.get_include())')"
+export CPATH="$PYBIND11_INC${CPATH:+:$CPATH}"
+export CXXFLAGS="-I$PYBIND11_INC ${CXXFLAGS:-}"
+export CPLUS_INCLUDE_PATH=/usr/local/cuda-13.0/targets/sbsa-linux/include/cccl:${CPLUS_INCLUDE_PATH}
+export CPATH=/usr/local/cuda-13.0/targets/sbsa-linux/include/cccl:${CPATH}
+export MAX_JOBS=8 
+
+BUILD_SOX=1 TORCH_CUDA_ARCH_LIST=11.0 USE_CUDA=1 python3 -m pip install -v . --no-use-pep517 --no-build-isolation --no-deps
+BUILD_SOX=1 TORCH_CUDA_ARCH_LIST=11.0 USE_CUDA=1 python3 -m pip wheel -v . --no-use-pep517 --no-build-isolation --no-deps -w /workspace/wheels

step-1.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+set -e
+set -o pipefail
+
+CONTAINER_VERSION="$(tr -d '[:space:]' < VERSION)"
+
+if [[ ! -d "sageattention" ]]; then
+    git clone https://github.com/thu-ml/SageAttention.git sageattention
+fi
+
+if [[ ! -d "torchaudio" ]]; then
+    git clone https://github.com/pytorch/audio.git torchaudio
+fi
+
+if [[ ! -d "torchaudio" ]]; then
+    git clone https://github.com/Dao-AILab/flash-attention.git flash-attention
+fi
+
+cd torchaudio && git checkout release/2.9 && cd ..
+mkdir -p wheels
+
+# flash-attn 2 from at https://github.com/mjun0812/flash-attention-prebuild-wheels/releases
+
+docker run --gpus all --rm -it --shm-size=512m \
+    -v "${PWD}:/workspace" \
+    "nvcr.io/nvidia/pytorch:${CONTAINER_VERSION}" \
+    /bin/bash -c "bash compile-sageattention.sh && bash compile-torchaudio.sh"

step-2.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+set -e
+set -o pipefail
+
+CONTAINER_VERSION="$(tr -d '[:space:]' < VERSION)"
+
+docker image build \
+    --build-arg CONTAINER_VERSION=${CONTAINER_VERSION} \
+    -f Dockerfile \
+    -t "jtreminio/swarmui:${CONTAINER_VERSION}" \
+    -t "jtreminio/swarmui:latest" \
+    .

wheels/flash_attn-2.7.4+cu130torch2.9-cp312-cp312-linux_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95717cc7f94b3f372c7470f2c8a5d59452e07c6f8b73fa769736a2f1cbfa243d
+size 371267188

wheels/sageattention-2.2.0-cp312-cp312-linux_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a930a569d7131c6faf1355763af1e609c381cd1449e8322b79ea22a71cc8127
+size 3208022

wheels/sageattn3-1.0.0-cp312-cp312-linux_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66b3e8c642b9fc55c0382e3dd7fc6a008509ee63cee76f1f1551a2079f32932
+size 1737447

wheels/torchaudio-2.9.1+a224ab2-cp312-cp312-linux_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec3c8a8c67ed8a349742a9d403ad5d68c5b462de5f35217737953b3e713c38c
+size 908812