fix: blackwell-series GPU CUDA capability sm_120 fix

docker/dockerfile

@@ -41,3 +41,4 @@ RUN cd / && wget https://developer.download.nvidia.com/compute/tensorrt/10.11.0/
     rm -f /nv-tensorrt-local-repo-ubuntu2204-10.11.0-cuda-12.9_1.0-1_amd64.deb
 
 SHELL ["/bin/bash", "-c", "source ~/.bashrc && conda activate my"]
+WORKDIR /workspace

docker/dockerfile-cu128

@@ -0,0 +1,40 @@
+FROM nvidia/cuda:12.8.0-cudnn-devel-ubuntu22.04
+
+ENV TZ=US/Pacific
+RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
+
+RUN apt-get update --fix-missing && \
+    apt-get install -y apt-utils build-essential ca-certificates cmake curl ffmpeg git libturbojpeg-dev pkg-config wget libnvinfer10 libnvinfer-plugin10 libnvonnxparsers10 libnvinfer-dispatch10 libnvinfer-bin zstd libx11-xcb1 libxcb-xinerama0 libxcb-icccm4 libxcb-render-util0 libxcb-shape0 libxcb-keysyms1 libxcb-image0 libxkbcommon-x11-0 libxcb-cursor0 libxcb-xkb1 libxcb-render0 libxcb-shm0 libxcb-sync1 libxcb-xfixes0 libxcb-randr0 libxcb-xtest0 libsm6 libxext6 libxkbcommon0 && \
+    rm -rf /var/lib/apt/lists/*
+
+SHELL ["/bin/bash", "--login", "-c"]
+
+RUN cd / && wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O /miniconda.sh && \
+    /bin/bash /miniconda.sh -b -p /opt/conda &&\
+    ln -s /opt/conda/etc/profile.d/conda.sh /etc/profile.d/conda.sh &&\
+    echo ". /opt/conda/etc/profile.d/conda.sh" >> ~/.bashrc &&\
+    /bin/bash -c "source ~/.bashrc" && \
+    /opt/conda/bin/conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/main &&\
+    /opt/conda/bin/conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/r &&\
+    /opt/conda/bin/conda update -n base -c defaults conda -y
+
+COPY environment.yml /tmp/environment.yml
+
+RUN /opt/conda/bin/conda env create --name my -f /tmp/environment.yml
+
+ENV PATH=$PATH:/opt/conda/envs/my/bin
+ENV OPENCV_IO_ENABLE_OPENEXR=1
+
+RUN conda init bash &&\
+    echo "conda activate my" >> ~/.bashrc
+
+RUN pip install torch==2.8 torchvision xformers torchaudio --index-url https://download.pytorch.org/whl/cu128
+RUN pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu12torch2.8cxx11abiFALSE-cp311-cp311-linux_x86_64.whl
+
+RUN cd / && wget https://developer.download.nvidia.com/compute/tensorrt/10.11.0/local_installers/nv-tensorrt-local-repo-ubuntu2204-10.11.0-cuda-12.9_1.0-1_amd64.deb &&\
+    apt install -y ./nv-tensorrt-local-repo-ubuntu2204-10.11.0-cuda-12.9_1.0-1_amd64.deb &&\
+    echo 'alias trtexec="/usr/src/tensorrt/bin/trtexec"' >> ~/.bashrc &&\
+    rm -f /nv-tensorrt-local-repo-ubuntu2204-10.11.0-cuda-12.9_1.0-1_amd64.deb
+
+SHELL ["/bin/bash", "-c", "source ~/.bashrc && conda activate my"]
+WORKDIR /workspace

docker/run_container.sh

@@ -1,4 +1,21 @@
 docker rm -f ffs || true
 xhost +local:root || true
-DIR=$(pwd)/../
-docker run --gpus all --runtime nvidia --env NVIDIA_DISABLE_REQUIRE=1 -it --network=host --name ffs --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v $DIR:/workspace --ipc=host -e DISPLAY=${DISPLAY} -v /tmp/.X11-unix:/tmp/.X11-unix -v /tmp:/tmp -v /home:/home -v /mnt:/mnt ffs bash
+
+DIR=$(pwd) 
+
+docker run --gpus all \
+  --runtime nvidia \
+  --env NVIDIA_DISABLE_REQUIRE=1 \
+  -it \
+  --network=host \
+  --name ffs \
+  --cap-add=SYS_PTRACE \
+  --security-opt seccomp=unconfined \
+  -v "$DIR":/workspace \
+  --ipc=host \
+  -e DISPLAY=${DISPLAY} \
+  -v /tmp/.X11-unix:/tmp/.X11-unix \
+  -v /tmp:/tmp \
+  -v /home:/home \
+  -v /mnt:/mnt \
+  ffs bash

environment.yml

@@ -0,0 +1,252 @@
+name: foundation_stereo
+channels:
+  - defaults
+  - nvidia
+dependencies:
+  - _libgcc_mutex=0.1
+  - _openmp_mutex=5.1
+  - binutils_impl_linux-64=2.44
+  - binutils_linux-64=2.44
+  - bzip2=1.0.8
+  - ca-certificates=2025.12.2
+  - cuda-cccl_linux-64=12.8.90
+  - cuda-crt-dev_linux-64=12.8.93
+  - cuda-crt-tools=12.8.93
+  - cuda-cudart=12.8.90
+  - cuda-cudart-dev=12.8.90
+  - cuda-cudart-dev_linux-64=12.8.90
+  - cuda-cudart-static=12.8.90
+  - cuda-cudart-static_linux-64=12.8.90
+  - cuda-cudart_linux-64=12.8.90
+  - cuda-driver-dev_linux-64=12.8.90
+  - cuda-nvcc=12.8.93
+  - cuda-nvcc-dev_linux-64=12.8.93
+  - cuda-nvcc-impl=12.8.93
+  - cuda-nvcc-tools=12.8.93
+  - cuda-nvcc_linux-64=12.8.93
+  - cuda-nvvm-dev_linux-64=12.8.93
+  - cuda-nvvm-impl=12.8.93
+  - cuda-nvvm-tools=12.8.93
+  - cuda-version=12.8
+  - gcc_impl_linux-64=14.3.0
+  - gcc_linux-64=14.3.0
+  - gxx_impl_linux-64=14.3.0
+  - gxx_linux-64=14.3.0
+  - kernel-headers_linux-64=4.18.0
+  - ld_impl_linux-64=2.44
+  - libexpat=2.7.4
+  - libffi=3.4.4
+  - libgcc=15.2.0
+  - libgcc-devel_linux-64=14.3.0
+  - libgcc-ng=15.2.0
+  - libgomp=15.2.0
+  - libnsl=2.0.0
+  - libsanitizer=14.3.0
+  - libstdcxx=15.2.0
+  - libstdcxx-devel_linux-64=14.3.0
+  - libstdcxx-ng=15.2.0
+  - libuuid=1.41.5
+  - libxcb=1.17.0
+  - libzlib=1.3.1
+  - ncurses=6.5
+  - openssl=3.5.5
+  - packaging=25.0
+  - pip=26.0.1
+  - pthread-stubs=0.3
+  - python=3.11.15
+  - readline=8.3
+  - setuptools=80.10.2
+  - sqlite=3.51.2
+  - sysroot_linux-64=2.28
+  - tk=8.6.15
+  - wheel=0.46.3
+  - xorg-libx11=1.8.12
+  - xorg-libxau=1.0.12
+  - xorg-libxdmcp=1.1.5
+  - xorg-xorgproto=2024.1
+  - xz=5.8.2
+  - zlib=1.3.1
+  - pip:
+      - addict==2.4.0
+      - albucore==0.0.24
+      - albumentations==2.0.8
+      - annotated-doc==0.0.4
+      - annotated-types==0.7.0
+      - antlr4-python3-runtime==4.9.3
+      - anyio==4.12.1
+      - argon2-cffi==25.1.0
+      - argon2-cffi-bindings==25.1.0
+      - arrow==1.4.0
+      - asttokens==3.0.1
+      - async-lru==2.2.0
+      - attrs==25.4.0
+      - babel==2.18.0
+      - beautifulsoup4==4.14.3
+      - bleach==6.3.0
+      - blinker==1.9.0
+      - certifi==2026.2.25
+      - cffi==2.0.0
+      - charset-normalizer==3.4.6
+      - click==8.3.1
+      - comm==0.2.3
+      - configargparse==1.7.5
+      - contourpy==1.3.3
+      - cuda-bindings==12.9.4
+      - cuda-pathfinder==1.4.2
+      - cycler==0.12.1
+      - dash==4.0.0
+      - debugpy==1.8.20
+      - decorator==5.2.1
+      - defusedxml==0.7.1
+      - einops==0.8.2
+      - executing==2.2.1
+      - fastjsonschema==2.21.2
+      - filelock==3.25.2
+      - flask==3.1.3
+      - fonttools==4.62.1
+      - fqdn==1.5.1
+      - fsspec==2026.2.0
+      - gdown==5.2.1
+      - h11==0.16.0
+      - hf-xet==1.4.2
+      - httpcore==1.0.9
+      - httpx==0.28.1
+      - huggingface-hub==1.7.1
+      - idna==3.11
+      - imageio==2.37.3
+      - imgaug==0.4.0
+      - importlib-metadata==8.7.1
+      - ipykernel==7.2.0
+      - ipython==9.10.0
+      - ipython-pygments-lexers==1.1.1
+      - ipywidgets==8.1.8
+      - isoduration==20.11.0
+      - itsdangerous==2.2.0
+      - jedi==0.19.2
+      - jinja2==3.1.6
+      - joblib==1.5.3
+      - json5==0.13.0
+      - jsonpointer==3.0.0
+      - jsonschema==4.26.0
+      - jsonschema-specifications==2025.9.1
+      - jupyter-client==8.8.0
+      - jupyter-core==5.9.1
+      - jupyter-events==0.12.0
+      - jupyter-lsp==2.3.0
+      - jupyter-server==2.17.0
+      - jupyter-server-terminals==0.5.4
+      - jupyterlab==4.5.6
+      - jupyterlab-pygments==0.3.0
+      - jupyterlab-server==2.28.0
+      - jupyterlab-widgets==3.0.16
+      - kiwisolver==1.5.0
+      - lark==1.3.1
+      - lazy-loader==0.5
+      - markdown-it-py==4.0.0
+      - markupsafe==3.0.3
+      - matplotlib==3.10.8
+      - matplotlib-inline==0.2.1
+      - mdurl==0.1.2
+      - mistune==3.2.0
+      - mpmath==1.3.0
+      - narwhals==2.18.0
+      - nbclient==0.10.4
+      - nbconvert==7.17.0
+      - nbformat==5.10.4
+      - nest-asyncio==1.6.0
+      - networkx==3.6.1
+      - ninja==1.13.0
+      - nodejs==0.1.1
+      - notebook-shim==0.2.4
+      - numpy==2.4.3
+      - nvidia-cublas-cu12==12.8.4.1
+      - nvidia-cuda-cupti-cu12==12.8.90
+      - nvidia-cuda-nvrtc-cu12==12.8.93
+      - nvidia-cuda-runtime-cu12==12.8.90
+      - nvidia-cudnn-cu12==9.10.2.21
+      - nvidia-cufft-cu12==11.3.3.83
+      - nvidia-cufile-cu12==1.13.1.3
+      - nvidia-curand-cu12==10.3.9.90
+      - nvidia-cusolver-cu12==11.7.3.90
+      - nvidia-cusparse-cu12==12.5.8.93
+      - nvidia-cusparselt-cu12==0.7.1
+      - nvidia-nccl-cu12==2.27.5
+      - nvidia-nvjitlink-cu12==12.8.93
+      - nvidia-nvshmem-cu12==3.4.5
+      - nvidia-nvtx-cu12==12.8.90
+      - omegaconf==2.3.0
+      - open3d==0.19.0
+      - opencv-contrib-python==4.13.0.92
+      - opencv-python==4.13.0.92
+      - opencv-python-headless==4.13.0.92
+      - optional-django==0.1.0
+      - overrides==7.7.0
+      - pandas==3.0.1
+      - pandocfilters==1.5.1
+      - parso==0.8.6
+      - pexpect==4.9.0
+      - pillow==12.1.1
+      - platformdirs==4.9.4
+      - plotly==6.6.0
+      - prometheus-client==0.24.1
+      - prompt-toolkit==3.0.52
+      - psutil==7.2.2
+      - ptyprocess==0.7.0
+      - pure-eval==0.2.3
+      - pycparser==3.0
+      - pydantic==2.12.5
+      - pydantic-core==2.41.5
+      - pygments==2.19.2
+      - pyparsing==3.3.2
+      - pyquaternion==0.9.9
+      - pysocks==1.7.1
+      - python-dateutil==2.9.0.post0
+      - python-json-logger==4.0.0
+      - pyyaml==6.0.3
+      - pyzmq==27.1.0
+      - referencing==0.37.0
+      - requests==2.32.5
+      - retrying==1.4.2
+      - rfc3339-validator==0.1.4
+      - rfc3986-validator==0.1.1
+      - rfc3987-syntax==1.1.0
+      - rich==14.3.3
+      - rpds-py==0.30.0
+      - ruamel-yaml==0.19.1
+      - safetensors==0.7.0
+      - scikit-image==0.26.0
+      - scikit-learn==1.8.0
+      - scipy==1.17.1
+      - send2trash==2.1.0
+      - shapely==2.1.2
+      - shellingham==1.5.4
+      - simsimd==6.5.16
+      - six==1.17.0
+      - soupsieve==2.8.3
+      - stack-data==0.6.3
+      - stringzilla==4.6.0
+      - sympy==1.14.0
+      - terminado==0.18.1
+      - threadpoolctl==3.6.0
+      - tifffile==2026.3.3
+      - timm==1.0.25
+      - tinycss2==1.4.0
+      - tornado==6.5.5
+      - tqdm==4.67.3
+      - traitlets==5.14.3
+      - transformations==2026.1.18
+      - trimesh==4.11.3
+      - triton==3.6.0
+      - typer==0.24.1
+      - typing-extensions==4.15.0
+      - typing-inspection==0.4.2
+      - tzdata==2025.3
+      - uri-template==1.3.0
+      - urllib3==2.6.3
+      - wcwidth==0.6.0
+      - webcolors==25.10.0
+      - webencodings==0.5.1
+      - websocket-client==1.9.0
+      - werkzeug==3.1.6
+      - widgetsnbextension==4.0.15
+      - zipp==3.23.0

readme.md

@@ -32,6 +32,14 @@ Stereo foundation models achieve strong zero-shot generalization but remain comp
 docker build --network host -t ffs -f docker/dockerfile .
 bash docker/run_container.sh
 ```
+> [!NOTE]  
+> If using blackwell-series GPU, run 
+> 
+> ```
+> docker build --network host -t ffs -f docker/dockerfile-cu128 .
+> ``` 
+> 
+> instead. 
 
 - Option 2: pip
 ```bash