Linear algebra ops
Generated from the binaries by scripts/gen-ops-reference.ts — do not edit by
hand. Every op also documents itself: torch <op> --help.
mm
matrix multiply of two 2-D tensors
torch mm <t1> <t2>torch mm <t1> <t2>matmul
general matrix product (batched, PyTorch broadcasting)
torch matmul <t1> <t2>torch matmul <t1> <t2>bmm
batched matrix multiply of two 3-D tensors
torch bmm <t1> <t2>torch bmm <t1> <t2>dot
dot product of two 1-D tensors
torch dot <t1> <t2>torch dot <t1> <t2>outer
outer product of two 1-D tensors
torch outer <t1> <t2>torch outer <t1> <t2>einsum
Einstein summation over —equation
torch einsum <t1>... (at least 1) [--equation <Str>]torch einsum <t1>... (at least 1) [--equation <Str>]tril
lower triangle (—diagonal offset)
torch tril <t1> [--diagonal <Int>]torch tril <t1> [--diagonal <Int>]triu
upper triangle (—diagonal offset)
torch triu <t1> [--diagonal <Int>]torch triu <t1> [--diagonal <Int>]diag
diagonal of a matrix, or diagonal matrix from a vector
torch diag <t1> [--diagonal <Int>]torch diag <t1> [--diagonal <Int>]trace
sum of the main diagonal of a 2-D tensor
torch trace <t1>torch trace <t1>det
determinant of a square matrix
torch det <t1>torch det <t1>inverse
inverse of a square matrix
torch inverse <t1>torch inverse <t1>svd
singular value decomposition (U, S, V)
torch svd <t1>torch svd <t1>solve
solve AX = B for X
torch solve <t1> <t2>torch solve <t1> <t2>cross
vector cross product along —dim
torch cross <t1> <t2> [--dim <Int>]torch cross <t1> <t2> [--dim <Int>]kron
Kronecker product
torch kron <t1> <t2>torch kron <t1> <t2>tensordot
tensor contraction over the last/first —dims dims (default 2)
torch tensordot <t1> <t2> [--dims <Int>]torch tensordot <t1> <t2> [--dims <Int>]