Website Blog TensorPlay documentation

Automatic differentiation package - tensorplay.autograd Automatic Mixed Precision package - tensorplay.amp Distributed communication package - tensorplay.distributed Index Multiprocessing package - tensorplay.multiprocessing Python Module Index Quantization Search tensorplay tensorplay._stax tensorplay.audio tensorplay.cuda tensorplay.fft tensorplay.futures tensorplay.hub tensorplay.library tensorplay.linalg tensorplay.nn tensorplay.nn.functional tensorplay.nn.init tensorplay.optim tensorplay.random tensorplay.sparse tensorplay.special tensorplay.stax tensorplay.utils.checkpoint tensorplay.utils.data tensorplay.vision

tensorplay.special._elementwise.log_softmax tensorplay.special._elementwise.logsumexp tensorplay.special._elementwise.round tensorplay.special._elementwise.softmax tensorplay.special._error.expit tensorplay.special._gamma.gammaln tensorplay.special._gamma.multigammaln tensorplay.special._gamma.polygamma tensorplay.special._gamma.psi

API symbolsspecial

latest (dev)

latest (dev)2026-09-08 v1.0.02026-09-06

Copy

tensorplay.special._elementwise.round

tensorplay.special._elementwise.round(input)[source]: Rounds to nearest even integer (native Tensor.round).

Help improve this page

Found an error, an unclear step, or a missing example?

Was this page helpful?

Suggest an edit Report an issue

tensorplay.special._elementwise.logsumexp

Log-sum-exp along dim , computed with the max-shift trick.

tensorplay.special._elementwise.softmax

Normalized exponential along dim (default: the last dim).

On this page