Files
pytorch/docs/cpp/source/api/nn/embedding.md
T
Svetlana Karslioglu 19da3da3d3 Restructure C++ docs (#174096)
The fix-cpp-build branch is a major restructuring that:

- Drops Exhale (which auto-generated API docs but caused OOM in CI) in favor of hand-written RST pages using Breathe directives
- Reorganizes notes into a hierarchical API reference with proper categories
- Adds new content: XPU docs, stable ABI docs, DeviceGuard/Stream docs
- Always runs Doxygen instead of gating on an env var

Pull Request resolved: https://github.com/pytorch/pytorch/pull/174096
Approved by: https://github.com/janeyx99, https://github.com/seemethere, https://github.com/albanD
2026-04-07 17:24:38 +00:00

1.3 KiB

myst
myst
html_meta
description keywords
Embedding layers in PyTorch C++ — Embedding and EmbeddingBag for sparse and dense lookups. PyTorch, C++, Embedding, EmbeddingBag, lookup table, sparse, NLP

Embedding Layers

Embedding layers map discrete tokens (words, categories, IDs) to dense vector representations. They are the foundation of NLP models and recommendation systems.

  • Embedding: Standard lookup table that maps indices to dense vectors
  • EmbeddingBag: Computes sums or means of embeddings (efficient for sparse features)

Key parameters:

  • num_embeddings: Size of the vocabulary (number of unique tokens)
  • embedding_dim: Dimension of each embedding vector
  • padding_idx: Index that outputs zeros (useful for padding tokens)

Embedding

:members:
:undoc-members:
:members:
:undoc-members:

Example:

auto embedding = torch::nn::Embedding(
    torch::nn::EmbeddingOptions(10000, 256)  // num_embeddings, embedding_dim
        .padding_idx(0));

auto indices = torch::tensor({1, 2, 3, 4});
auto embedded = embedding->forward(indices);  // [4, 256]

EmbeddingBag

:members:
:undoc-members:
:members:
:undoc-members: