Instructions to use replicate/trimul-gpumode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/trimul-gpumode with Kernels:
# !pip install kernels from kernels import get_kernel # a version (or an explicit revision) is required; see the "Files and versions" tab for the available ones kernel = get_kernel("replicate/trimul-gpumode", version=1) - Notebooks
- Google Colab
- Kaggle
Download build/torch-cuda/__init__.py from replicate/trimul-gpumode: direct link, hf CLI and curl.
- Browser
- Download file 280 Bytes
-
https://huggingface.co/replicate/trimul-gpumode/resolve/main/build/torch-cuda/__init__.py
- Command line
-
hf download hf://replicate/trimul-gpumode/build/torch-cuda/__init__.py
-
curl -L -o __init__.py https://huggingface.co/replicate/trimul-gpumode/resolve/main/build/torch-cuda/__init__.py
280 Bytes
| from .triton_a100 import kernel_a100 | |
| from .triton_h100 import kernel_h100 | |
| from .triton_b200 import kernel_b200 | |
| from .trimul_mi300 import kernel_mi300 | |
| from .trimul_global import kernel_global | |
| __all__ = ["kernel_a100", "kernel_h100", "kernel_b200", "kernel_mi300", "kernel_global"] |