diff --git a/Project.toml b/Project.toml
index 82a370ef0..6643f2eea 100644
--- a/Project.toml
+++ b/Project.toml
@@ -8,7 +8,6 @@ Adapt = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
 CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
 ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
 DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
-FastClosures = "9aa1b823-49e4-5ca5-8b0f-3971ec8bab6a"
 Flux = "587475ba-b771-5e3f-ad9e-33799f191a9c"
 Functors = "d9f16b24-f501-4c13-a1f2-28368ffc5196"
 Graphs = "86223c79-3864-5bf0-83f7-82e725a168b6"
diff --git a/src/GraphNeuralNetworks.jl b/src/GraphNeuralNetworks.jl
index c3a122538..db8e7be16 100644
--- a/src/GraphNeuralNetworks.jl
+++ b/src/GraphNeuralNetworks.jl
@@ -11,12 +11,6 @@ using NNlib, NNlibCUDA
 using NNlib: scatter, gather
 using ChainRulesCore
 using Reexport
-
-# use `@closure` in conv layers in ored to avoid issues
-# https://github.com/JuliaLang/julia/issues/15276
-# https://github.com/FluxML/Zygote.jl/issues/1317
-# using FastClosures: @closure 
-
 using SparseArrays, Graphs # not needed but if removed Documenter will complain
 
 include("GNNGraphs/GNNGraphs.jl")