FBGEMM_GPU¶
FBGEMM_GPU (FBGEMM GPU Kernels Library) is a collection of high-performance PyTorch GPU operator libraries built on top of FBGEMM for training and inference, with a focus on recommendation systems applications. This library is built on top of FBGEMM and provides efficient table batched embedding bag, data layout transformation, and quantization support.
FBGEMM_GPU Development
FBGEMM_GPU Overview
FBGEMM Stable API
FBGEMM_GPU C++ API
- Sparse Data Operators
- Quantization Operators
- Pooled Embeddings Operators
- Table Batched Embedding Operators
- Jagged Tensor Operators
- CUDA Memory Operators
- Combine Input Operators
- Layout Transformation Operators
- Embedding Operators
- SSD Embedding Operators
- Experimental Operators
- Feature Gates (C++)
- Faster Hash Operators