You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: lib/shape_inference.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -163,10 +163,10 @@ The constraints are solved by: unification of the equation constraints, unificat
163
163
* Stage 1 is online as tensors are composed, and conservatively performs unification and constraint propagation. Stages 2, 3, 4 are only performed once necessary: when projections or dimensions are requested.
164
164
* Stage 2, when solving the constraints, substitutes dim variables in terminal shapes that do not have a LUB or other constraints, by dimension-1. (This is generalized at stage 6 to all variables.) (FIXME: reconsider this, see the algo for row variables: a new LUB can still be inferred.) Forces coefficients coming from precision byte sizes.
165
165
* Stage 3, when solving the constraints, sets yet-unknown dimension and row variables in terminal shapes to their least upper bounds (if any). It substitutes row variables in terminal shapes that do not have a LUB by one axis if that's required to satisfy the variable's constraint.
166
-
* Stage 4 sets yet-unknown dimensions with >1 lower bounds from direct accesses, to their LUBs if they have any, otherwise to the lower bound. It substitutes row variables in terminal shapes that do not have a LUB by no-further-axes. (This is generalized at stage 6 to all variables.)
166
+
* Stage 4 sets yet-unknown dimensions with >1 lower bounds from direct accesses, to their LUBs if they have any. It substitutes row variables in terminal shapes that do not have a LUB by no-further-axes. (This is generalized at stage 6 to all variables.)
167
167
* Stage 5 addresses `Total_elems` and `Exact` constraints with yet-unknown row variables. For `Total_elems` and a single row variable: if the constraint can be satisfied by assuming the row variable is no-further-axes, it sets the row variable to `Broadcastable`, otherwise it sets it to one axis of the required dimension. For multiple row variables, if one is of the Output kind, sets the other variables to no-further-axes, and retries.
168
168
* Stage 6 sets row variables in the remaining inequalities to no-further-axes values. This can unlock further between-axis inequalities because of row variables sandwiched between leftmost axes from their side of the inequality and rightmost axes from the other side of the inequality.
169
-
* Stage 7 sets all dim resp. row variables remaining in updated shapes to dimension-1 resp. no-further-axes.
169
+
* Stage 7 sets all dim variables remaining in updated shapes to the lower bound if they have any, otherwise to dimension-1. It sets all row variables remaining in updated shapes to no-further-axes.
0 commit comments