diff --git a/src/CodeGen_Hexagon.cpp b/src/CodeGen_Hexagon.cpp
index c680fdb1a82e..fa194c6d2c91 100644
--- a/src/CodeGen_Hexagon.cpp
+++ b/src/CodeGen_Hexagon.cpp
@@ -1025,6 +1025,23 @@ Value *CodeGen_Hexagon::interleave_vectors(const vector<llvm::Value *> &v) {
     int native_elements =
         native_vector_bits() / element_ty->getScalarSizeInBits();
     int result_elements = get_vector_num_elements(v_ty) * v.size();
+    if (element_bits == 1) {
+        // If this is a vector of booleans, convert it to a vector of bytes,
+        // interleave that, and convert back. This avoids routing predicate
+        // (mask) vectors through the vdelta-based byte shuffle network
+        // below, which assumes native-vector-sized byte data: small,
+        // sub-native-width concatenations of predicates (as produced here
+        // when the number of lanes is much smaller than a native HVX
+        // vector) can trip up LLVM's Hexagon backend during DAG combining.
+        vector<llvm::Value *> i8_v(v.size());
+        for (size_t i = 0; i < v.size(); i++) {
+            llvm::Type *i8_ty = get_vector_type(i8_t, get_vector_num_elements(v[i]->getType()));
+            i8_v[i] = builder->CreateIntCast(v[i], i8_ty, true);
+        }
+        Value *result = interleave_vectors(i8_v);
+        llvm::Type *result_ty = get_vector_type(element_ty, result_elements);
+        return builder->CreateIntCast(result, result_ty, true);
+    }
     if (v.size() == 2) {
         // Interleaving two vectors.
         Value *a = v[0];
diff --git a/src/JITModule.cpp b/src/JITModule.cpp
index 4bdba15bdf25..1cf7ba1c141c 100644
--- a/src/JITModule.cpp
+++ b/src/JITModule.cpp
@@ -448,7 +448,21 @@ void compile_module_impl(
     dtorRunner->add(dtors);
 
     // Resolve system symbols (like pthread, dl and others)
+#if defined(__GNUC__) && !defined(__clang__)
+    // GCC's -Wuninitialized/-Wmaybe-uninitialized misfires on the move
+    // constructor of the default-constructed llvm::unique_function
+    // (AddAbsoluteSymbolsFn) that GetForCurrentProcess() takes by default
+    // argument, after LLVM's unique_function was refactored upstream
+    // (llvm/llvm-project#208251). Which of the two warnings fires depends
+    // on the GCC version, so both are silenced here.
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wuninitialized"
+#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
+#endif
     auto gen = llvm::orc::DynamicLibrarySearchGenerator::GetForCurrentProcess(target_data_layout.getGlobalPrefix());
+#if defined(__GNUC__) && !defined(__clang__)
+#pragma GCC diagnostic pop
+#endif
     internal_assert(gen) << llvm::toString(gen.takeError()) << "\n";
     JIT->getMainJITDylib().addGenerator(std::move(gen.get()));
 
diff --git a/test/fuzz/lossless_cast.cpp b/test/fuzz/lossless_cast.cpp
index 01ef1c38e8d7..cca4047ae5ed 100644
--- a/test/fuzz/lossless_cast.cpp
+++ b/test/fuzz/lossless_cast.cpp
@@ -267,27 +267,46 @@ FUZZ_TEST(lossless_cast, FuzzingContext &fuzz) {
     buf_u8.fill(fuzz);
     buf_i8.fill(fuzz);
 
-    Expr e1 = random_expr(fuzz);
-    Expr simplified = simplify(e1);
+    // random_expr() can produce deeply-nested expressions, and simplify(),
+    // lower_intrinsics(), and friends visit them recursively. Unlike the
+    // Pipeline lowering/codegen path (which already runs on a large stack
+    // via Internal::run_with_large_stack), these calls would otherwise run
+    // directly on the calling thread's stack, which can be too small on
+    // some CI configurations.
+    Expr e1, e2;
+    ConstantInterval bounds;
+    bool skip = false;
+    bool has_ub = false;
+    run_with_large_stack([&]() {
+        e1 = random_expr(fuzz);
+        Expr simplified = simplify(e1);
+
+        if (might_have_ub(e1) ||
+            might_have_ub(simplified) ||
+            might_have_ub(lower_intrinsics(simplified))) {
+            skip = true;
+            return;
+        }
 
-    if (might_have_ub(e1) ||
-        might_have_ub(simplified) ||
-        might_have_ub(lower_intrinsics(simplified))) {
-        return 0;
-    }
+        // We're also going to test constant_integer_bounds here.
+        bounds = constant_integer_bounds(e1);
 
-    // We're also going to test constant_integer_bounds here.
-    ConstantInterval bounds = constant_integer_bounds(e1);
+        std::vector<Type> target_types = {UInt(32), Int(32), UInt(16), Int(16)};
+        Type target = fuzz.PickValueInVector(target_types);
+        e2 = lossless_cast(target, e1);
+        if (!e2.defined()) {
+            skip = true;
+            return;
+        }
 
-    std::vector<Type> target_types = {UInt(32), Int(32), UInt(16), Int(16)};
-    Type target = fuzz.PickValueInVector(target_types);
-    Expr e2 = lossless_cast(target, e1);
+        has_ub = definitely_has_ub(e2);
+    });
 
-    if (!e2.defined()) {
+    if (skip) {
         return 0;
     }
 
-    if (definitely_has_ub(e2)) {
+    if (has_ub) {
         std::cerr << "lossless_cast introduced ub:\n"
                   << "e1 = " << e1 << "\n"
                   << "e2 = " << e2 << "\n"
diff --git a/uv.lock b/uv.lock
index 7cc651765b49..625f0f7800c9 100644
--- a/uv.lock
+++ b/uv.lock
@@ -178,7 +178,7 @@ ci-llvm-22 = [
 ]
 ci-llvm-main = [
     { name = "cmake" },
-    { name = "halide-llvm", version = "23.0.0.dev95984+gbaa69e92", source = { registry = "https://pypi.halide-lang.org/simple" } },
+    { name = "halide-llvm", version = "23.0.0.dev100667+g9bf20bdf", source = { registry = "https://pypi.halide-lang.org/simple" } },
     { name = "ninja" },
     { name = "onnx", marker = "platform_machine != 'armv7l' and platform_machine != 'armv8l'" },
     { name = "pre-commit" },
@@ -346,7 +346,7 @@ wheels = [
 
 [[package]]
 name = "halide-llvm"
-version = "23.0.0.dev95984+gbaa69e92"
+version = "23.0.0.dev100667+g9bf20bdf"
 source = { registry = "https://pypi.halide-lang.org/simple" }
 resolution-markers = [
     "(python_full_version >= '3.11' and platform_machine == 'armv7l' and sys_platform != 'armv7l' and sys_platform != 'armv8l') or (python_full_version >= '3.11' and platform_machine == 'armv8l' and sys_platform != 'armv7l' and sys_platform != 'armv8l')",
@@ -363,14 +363,14 @@ resolution-markers = [
     "(python_full_version < '3.11' and platform_machine != 'armv7l' and platform_machine != 'armv8l' and sys_platform == 'armv7l') or (python_full_version < '3.11' and platform_machine != 'armv7l' and platform_machine != 'armv8l' and sys_platform == 'armv8l')",
 ]
 wheels = [
-    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev95984+gbaa69e92-py3-none-macosx_11_0_arm64.whl", hash = "sha256:6e20a00865c98086bc132dc1f6963a882d6dfc858a435728835fb6396c220752" },
-    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev95984+gbaa69e92-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:431e97802719a2713fb07c7519e9c85d2ae3322087e46350284ae454b0b1cd4a" },
-    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev95984+gbaa69e92-py3-none-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:96a2bc0f893b643c9f4aa5324d305628101d7ef29e549ca974fccb1bd9ee1fbf" },
-    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev95984+gbaa69e92-py3-none-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:968aefab0d44587509029b1070d2ef84ff096faff42702cbac511a6fbfb7e08c" },
-    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev95984+gbaa69e92-py3-none-manylinux_2_28_i686.whl", hash = "sha256:00778ea8b791318a1b5d9225c6c39b429e4d6f37128414b74d073cf986144c87" },
-    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev95984+gbaa69e92-py3-none-manylinux_2_31_armv7l.whl", hash = "sha256:73c69bd047bf2be695e16f1564a2f6f723d43b27b0483ec2eb47879300716582" },
-    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev95984+gbaa69e92-py3-none-win32.whl", hash = "sha256:afafbaceb5f633e3c5efbf41a7b5cbf78cbcbe36d627b62eeca0fcbf9465f2e5" },
-    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev95984+gbaa69e92-py3-none-win_amd64.whl", hash = "sha256:9c87f8dc2f415b86de17c3873a6662174b59aa7bc14374d2fe1fb4f0112482b2" },
+    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev100667+g9bf20bdf-py3-none-macosx_11_0_arm64.whl", hash = "sha256:bc6ecef649b0eeb2d9b5827e8664652d6722ffe4ee98bac3febd3e223629d0d0" },
+    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev100667+g9bf20bdf-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:0fc4450b99b599300ff0088ed798082e1c7129e72a71a55a7ed29fd942d15886" },
+    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev100667+g9bf20bdf-py3-none-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0c00ff01a0c1b43e321cf0491d70d568868c65dc738d59ba054df550b36de6f1" },
+    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev100667+g9bf20bdf-py3-none-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9dfc5476b8647fb1eab8d6441303d34f065aabfea2d11d547afec94adb27b71b" },
+    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev100667+g9bf20bdf-py3-none-manylinux_2_28_i686.whl", hash = "sha256:182725f20d81737cd3d03ea384eaf9f05fbb6070fe57d22880d5efd90b6eae78" },
+    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev100667+g9bf20bdf-py3-none-manylinux_2_31_armv7l.whl", hash = "sha256:c14abaadf6781b2fbec4495c2d0558ae7fe25c17de05dde8e1b5e88f4de8fe33" },
+    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev100667+g9bf20bdf-py3-none-win32.whl", hash = "sha256:0bff9d935c76af54c0d656f76dd9f9c935784ccc549bf194eb4fedf9f26ce36e" },
+    { url = "https://pypi.halide-lang.org/packages/halide_llvm-23.0.0.dev100667+g9bf20bdf-py3-none-win_amd64.whl", hash = "sha256:0b32ab7ab02d63fb66664061da597dee70d5039c7be381a3f5ca73d30733b06f" },
 ]
 
 [[package]]