github pytorch/FBGEMM v0.3.0

latest releases: v1.0.0, v1.0.0-rc3, v1.0.0-rc2...
2 years ago

New Features

Table Batched Embedding enhancements:

AMD Support (beta) (#1102, #1193)

  • FBGEMM previously supported only NVIDIA accelerators, but FBGEMM 0.3.0 started to support AMD GPUs in collaboration with AMD. Although its support is still beta (e.g., we don't have a stable release build for AMD GPUs yet), the AMD GPU implementation covers almost all the FBGEMM operators supported by NVIDIA GPUs. AMD GPU support is tested using CI with AMD MI250 GPUs.

Quantized Communication Primitives (#1219, #1337)

Sparse kernel enhancements

  • New kernel: invert_permute (#1403)
  • New kernel: truncate_jagged_1d (#1345)
  • New kernel: jagged_index_select (#1157)
  • Jagged Tensor optimization for inference use cases (#1236)

Improved documentation for Jagged Tensors and SplitTableBatchedEmbeddingBagsCodegen

Optimized 2x2 kernel for AVX2 (#1280)

Full Changelog: https://github.com/pytorch/FBGEMM/commits/v0.3.0

Don't miss a new FBGEMM release

NewReleases is sending notifications on new releases.