facebookarchive/fbcunn

Health v2 · maintenance only

Flags: no_releases archived no_license

Adoption not part of the score

1059 stars · 242 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Facebook AI Research's CUDA-accelerated deep learning extension modules for the Torch-7 framework, including fast FFT-based convolutions, multi-GPU parallel containers, and optimized lookup tables. It is an archived repository and no longer maintained.

Use cases

• accelerate convolutional neural network training on GPUs
• train deep learning models across multiple GPUs
• build fast neural language models with efficient lookup tables
• classify a very large number of classes with hierarchical softmax
• speed up temporal convolutions in Torch-7

When to choose

• you are already working in the legacy Torch-7 ecosystem and need faster GPU modules
• you need the original FFT-based convolution implementations from the FAIR paper

When to avoid

• you are starting a new project - use PyTorch or another maintained framework instead
• you need up-to-date GPU support or bug fixes
• you do not use Torch-7 or Lua

Facets

library · maturity abandoned

deep-learning machine-learning gpu-computing deep-learning machine-learning computer-vision lua torch7 cuda fft-convolution facebook-ai-research neural-networks multi-gpu archived natural-language-processing gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="facebookarchive/fbcunn")