[Mlir-commits] [mlir] [mlir][tosa] Guard pooling shape inference on unranked inputs (PR #177999)

Luke Hutton llvmlistbot at llvm.org
Mon Jan 26 09:30:34 PST 2026


================
@@ -1743,3 +1743,16 @@ func.func @test_tconv2d_bias_broadcast(%input: tensor<2x6x7x3xf32>, %weight: ten
        : (tensor<2x6x7x3xf32>, tensor<?x3x3x3xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xf32>) -> tensor<?x?x?x?xf32>
     return
   }
+
+// -----
+
+// CHECK-LABEL: test_pool2d_unknown_rank
+func.func @test_pool2d_unknown_rank() {
----------------
lhutton1 wrote:

nit: please could we update this test such that it only uses `tosa.avg_pool2d`?

https://github.com/llvm/llvm-project/pull/177999


More information about the Mlir-commits mailing list