MPS: Large matrix multiplications using can contains NaNs

See updated MWE in https://github.com/JuliaGPU/Metal.jl/issues/381#issuecomment-2314653468:

---

Old MWE:

```julia-repl
julia> a = Metal.randn(10000, 10000);

julia> b = Metal.randn(10000, 10000);

julia> c = a * b';

julia> for i in 1:10
C = Metal.zeros(Float32, size(a))
mul!(C, a, b')
@assert C ≈ c "$i"
end
ERROR: AssertionError: 1
Stacktrace:
[1] top-level scope
@ ./REPL[58]:4

julia> for i in 1:10
C = Metal.zeros(Float32, size(a))
mul!(C, a, b')
@assert C ≈ c "$i"
end
ERROR: AssertionError: 8
Stacktrace:
[1] top-level scope
@ ./REPL[58]:4

julia> for i in 1:10
@assert a * b' ≈ c "$i"
end
ERROR: AssertionError: 3
Stacktrace:
[1] top-level scope
@ ./REPL[59]:2

julia> for i in 1:10
@assert a * b' ≈ c "$i"
end
ERROR: AssertionError: 8
Stacktrace:
[1] top-level scope
@ ./REPL[59]:2

```