diff --git a/Project.toml b/Project.toml
index 78120df1..7673c672 100644
--- a/Project.toml
+++ b/Project.toml
@@ -1,6 +1,6 @@
 name = "StaticArrays"
 uuid = "90137ffa-7385-5640-81b9-e52037218182"
-version = "1.0.0"
+version = "1.0.1"
 
 [deps]
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
diff --git a/src/matrix_multiply_add.jl b/src/matrix_multiply_add.jl
index 5d25483b..d04af8a1 100644
--- a/src/matrix_multiply_add.jl
+++ b/src/matrix_multiply_add.jl
@@ -218,13 +218,33 @@ const StaticVecOrMatLikeForFiveArgMulDest{T} = Union{
     α::Number, β::Number) = _mul!(TSize(dest), mul_parent(dest), Size(A), Size(B), A, B,
     AlphaBeta(α,β))
 
-@inline function LinearAlgebra.mul!(dest::StaticVecOrMatLike{TDest}, A::StaticVecOrMatLike{TA},
-        B::StaticVecOrMatLike{TB}) where {TDest,TA,TB}
+# See https://github.com/JuliaArrays/StaticArrays.jl/issues/857.
+# `StaticVecOrMatLike` is a very large union, and this caused Julia 1.0.x to
+# use a large amount of memory when compiling StaticArrays in the presence
+# of other packages that also extend `LinearAlgebra.mul!` in a similar
+# fashion. As an example, this led to JuMP using more than 4 GB of RAM when
+# running `using JuMP`, causing its CI to crash.
+#
+# Computing the eltypes within the function, rather than specifying them in
+# the type arguments greatly improves the issue, with `using JuMP` going
+# from:
+#     julia> @time using JuMP
+#     [ Info: Precompiling JuMP [4076af6c-e467-56ae-b986-b466b2749572]
+#     Killed
+# to:
+#     julia> @time using JuMP
+#     [ Info: Precompiling JuMP [4076af6c-e467-56ae-b986-b466b2749572]
+#     101.723598 seconds (12.85 M allocations: 812.902 MiB, 0.31% gc time)
+@inline function LinearAlgebra.mul!(
+    dest::StaticVecOrMatLike,
+    A::StaticVecOrMatLike,
+    B::StaticVecOrMatLike,
+)
+    TDest, TA, TB = eltype(dest), eltype(A), eltype(B)
     TMul = promote_op(matprod, TA, TB)
     return _mul!(TSize(dest), mul_parent(dest), Size(A), Size(B), A, B, NoMulAdd{TMul, TDest}())
 end
 
-
 "Calculate the product of the dimensions being multiplied. Useful as a heuristic for unrolling."
 @inline multiplied_dimension(A::Type{<:StaticVecOrMatLike}, B::Type{<:StaticVecOrMatLike}) =
     prod(size(A)) * size(B,2)
@@ -310,7 +330,7 @@ function uplo_access(sa, asym, k, j, uplo)
     elseif uplo == :unit_lower_triangular
         if k > j
             return :($asym[$(LinearIndices(sa)[k, j])])
-        elseif k == j 
+        elseif k == j
             return :(oneunit($TAsym))
         else
             return :(zero($TAsym))
@@ -439,7 +459,7 @@ end
     else
         ab = [:(a[$i] * transpose(b[$j])) for i = 1:sa[1], j = 1:sb[2]]
     end
-    
+
     exprs = _muladd_expr(lhs, ab, _add)
 
     return quote
@@ -558,7 +578,7 @@ end
             @inbounds $(Expr(:block, exprs...))
         end
     end
-    
+
     return quote
         @_inline_meta
         α = alpha(_add)