Current physics indicates that we can't increase computation indefinitely in this way.

This is not clear at all.

Current physics posits no ultimate minimal energy requirement for computation. With reversible computing, a couple of watts could perform any amount of computation. The upper theoretical limit is infinity. The limits are purely practical, not theoretical.

There is also quantum computation to consider:

A quantum computer with a given number of qubits is exponentially more complex than a classical computer with the same number of bits because describing the state of n qubits requires 2^n complex coefficients. . . .For example, a 300-qubit quantum computer has a state described by 2^300 (approximately 10^90) complex numbers, more than the number of atoms in the observable universe.

Why do you think that mass/energy is ultimately important? And finally, there are the more radical possibilities of space-time engineering.

When we consider new physics, they might increase the returns to colonization (e.g. more computation using bigger black holes) or have little effect, with only a portion of our probability mass going to the "vast inner expansion" scenarios.

I don't follow your logic.

When we consider new physics, they could do any number of things. The most likely is to increase utilization of current matter/energy. They could also allow the creation of matter/energy. Any of these would further increase the rate of return of acceleration over expansion. And acceleration already starts with a massive lead. The only new physics which would appear at first to favor colonization is speed of light circumvention. But depending on the details that could actually also favor acceleration over expansion.

As long as there are bottlenecks somewhere along the technology trajectory, civilizations should spend most of their time there, and would benefit from additional resources to advance through the bottlenecks

I don't see any benefit. A colony 10 light-years away would be more or less inaccessible for accelerated hyper-intelligences in terms of bandwidth and latency.

The possible benefit seems to be satisficing the idea that you have replicated, and or possibly travelling to new regions where you have better growth opportunities.