push sheeet

pkgs/development/cuda-modules/packages/cudnn-frontend/0001-cmake-float-out-common-python-bindings-option.patch

@@ -0,0 +1,30 @@
+From eeef96e91bd3453160315bf4618b7b91ae7240ba Mon Sep 17 00:00:00 2001
+From: Connor Baker <ConnorBaker01@gmail.com>
+Date: Sat, 18 Jan 2025 20:48:11 +0000
+Subject: [PATCH 1/4] cmake: float out common python bindings option
+
+---
+ CMakeLists.txt | 3 +--
+ 1 file changed, 1 insertion(+), 2 deletions(-)
+
+diff --git a/CMakeLists.txt b/CMakeLists.txt
+index 9739569..8944621 100644
+--- a/CMakeLists.txt
++++ b/CMakeLists.txt
+@@ -5,12 +5,11 @@ project(cudnn_frontend VERSION 1.9.0)
+ option(CUDNN_FRONTEND_SKIP_JSON_LIB "Defines whether FE should not include nlohmann/json.hpp." OFF)
+ option(CUDNN_FRONTEND_BUILD_SAMPLES "Defines if samples are built or not." ON)
+ option(CUDNN_FRONTEND_BUILD_TESTS "Defines if unittests are built or not." ON)
++option(CUDNN_FRONTEND_BUILD_PYTHON_BINDINGS "Defines if python bindings are built or not." OFF)
+ 
+ if(MSVC OR MSYS OR MINGW)
+-    option(CUDNN_FRONTEND_BUILD_PYTHON_BINDINGS "Defines if python bindings are built or not." OFF)
+     add_compile_options(/W4 /WX)
+ else()
+-    option(CUDNN_FRONTEND_BUILD_PYTHON_BINDINGS "Defines if python bindings are built or not." OFF)
+     add_compile_options(-Wall -Wextra -Wpedantic -Werror -Wno-error=attributes -Wno-attributes -Wno-error=unused-function -Wno-unused-function)
+ endif()
+ 
+-- 
+2.47.0
+

pkgs/development/cuda-modules/packages/cudnn-frontend/0002-cmake-add-config-so-headers-can-be-discovered-when-i.patch

@@ -0,0 +1,84 @@
+From da16ec51ea78f88f333ecf3df2a249fcc65ead24 Mon Sep 17 00:00:00 2001
+From: Connor Baker <ConnorBaker01@gmail.com>
+Date: Sat, 18 Jan 2025 22:01:03 +0000
+Subject: [PATCH 2/4] cmake: add config so headers can be discovered when
+ installed
+
+---
+ CMakeLists.txt                 | 39 +++++++++++++++++++++++++++++++---
+ cudnn_frontend-config.cmake.in |  3 +++
+ 2 files changed, 39 insertions(+), 3 deletions(-)
+ create mode 100644 cudnn_frontend-config.cmake.in
+
+diff --git a/CMakeLists.txt b/CMakeLists.txt
+index 8944621..9b1bfba 100644
+--- a/CMakeLists.txt
++++ b/CMakeLists.txt
+@@ -1,4 +1,4 @@
+-cmake_minimum_required(VERSION 3.17)
++cmake_minimum_required(VERSION 3.23)
+ 
+ project(cudnn_frontend VERSION 1.9.0)
+ 
+@@ -15,6 +15,15 @@ endif()
+ 
+ add_library(cudnn_frontend INTERFACE)
+ 
++# Add header files to library
++file(GLOB_RECURSE CUDNN_FRONTEND_INCLUDE_FILES "include/*")
++target_sources(
++    cudnn_frontend PUBLIC FILE_SET HEADERS
++    BASE_DIRS "$<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>"
++    FILES "${CUDNN_FRONTEND_INCLUDE_FILES}"
++)
++unset(CUDNN_FRONTEND_INCLUDE_FILES)
++
+ target_compile_definitions(
+     cudnn_frontend INTERFACE
+     $<$<BOOL:${CUDNN_FRONTEND_SKIP_JSON_LIB}>:CUDNN_FRONTEND_SKIP_JSON_LIB>
+@@ -58,7 +67,31 @@ endif()
+ # * CMAKE_INSTALL_INCLUDEDIR
+ include(GNUInstallDirs)
+ 
++# See https://cmake.org/cmake/help/latest/module/CMakePackageConfigHelpers.html#example-generating-package-files
++include(CMakePackageConfigHelpers)
++
++# Install and export the header files
++install(
++    TARGETS cudnn_frontend
++    EXPORT cudnn_frontend_targets FILE_SET HEADERS
++)
++export(
++    EXPORT cudnn_frontend_targets
++    FILE "${CMAKE_CURRENT_BINARY_DIR}/cudnn_frontend/cudnn_frontend-targets.cmake"
++)
++install(
++    EXPORT cudnn_frontend_targets
++    FILE cudnn_frontend-targets.cmake
++    DESTINATION "${CMAKE_INSTALL_LIBDIR}/cmake/cudnn_frontend"
++)
++
++# Install the CMake configuration file for header discovery
++configure_package_config_file(
++    cudnn_frontend-config.cmake.in
++    "${CMAKE_CURRENT_BINARY_DIR}/cudnn_frontend-config.cmake"
++    INSTALL_DESTINATION "${CMAKE_INSTALL_LIBDIR}/cmake/cudnn_frontend"
++)
+ install(
+-    DIRECTORY ${PROJECT_SOURCE_DIR}/include/
+-    DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
++    FILES "${CMAKE_CURRENT_BINARY_DIR}/cudnn_frontend-config.cmake"
++    DESTINATION "${CMAKE_INSTALL_LIBDIR}/cmake/cudnn_frontend"
+ )
+diff --git a/cudnn_frontend-config.cmake.in b/cudnn_frontend-config.cmake.in
+new file mode 100644
+index 0000000..8b2d843
+--- /dev/null
++++ b/cudnn_frontend-config.cmake.in
+@@ -0,0 +1,3 @@
++@PACKAGE_INIT@
++
++include(${CMAKE_CURRENT_LIST_DIR}/cudnn_frontend-targets.cmake)
+-- 
+2.47.0
+

pkgs/development/cuda-modules/packages/cudnn-frontend/0003-cmake-install-samples-and-tests-when-built.patch

@@ -0,0 +1,85 @@
+From 53d5aaaad09b479cd8c0e148c9428baa33204024 Mon Sep 17 00:00:00 2001
+From: Connor Baker <ConnorBaker01@gmail.com>
+Date: Sat, 18 Jan 2025 22:10:41 +0000
+Subject: [PATCH 3/4] cmake: install samples and tests when built
+
+---
+ CMakeLists.txt                        | 12 +++++++++++-
+ samples/cpp/CMakeLists.txt            |  2 ++
+ samples/legacy_samples/CMakeLists.txt |  2 ++
+ test/cpp/CMakeLists.txt               |  2 ++
+ 4 files changed, 17 insertions(+), 1 deletion(-)
+
+diff --git a/CMakeLists.txt b/CMakeLists.txt
+index 9b1bfba..f6af111 100644
+--- a/CMakeLists.txt
++++ b/CMakeLists.txt
+@@ -70,11 +70,21 @@ include(GNUInstallDirs)
+ # See https://cmake.org/cmake/help/latest/module/CMakePackageConfigHelpers.html#example-generating-package-files
+ include(CMakePackageConfigHelpers)
+ 
+-# Install and export the header files
++# Install the components
+ install(
+     TARGETS cudnn_frontend
+     EXPORT cudnn_frontend_targets FILE_SET HEADERS
+ )
++
++if (CUDNN_FRONTEND_BUILD_SAMPLES)
++    install(TARGETS legacy_samples samples RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
++endif()
++
++if (CUDNN_FRONTEND_BUILD_TESTS)
++    install(TARGETS tests RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
++endif()
++
++# Export the targets
+ export(
+     EXPORT cudnn_frontend_targets
+     FILE "${CMAKE_CURRENT_BINARY_DIR}/cudnn_frontend/cudnn_frontend-targets.cmake"
+diff --git a/samples/cpp/CMakeLists.txt b/samples/cpp/CMakeLists.txt
+index 9b8a5eb..01b09bb 100644
+--- a/samples/cpp/CMakeLists.txt
++++ b/samples/cpp/CMakeLists.txt
+@@ -69,8 +69,10 @@ target_link_libraries(
+     _cudnn_frontend_pch
+     CUDNN::cudnn
+ 
++    CUDA::cublasLt
+     CUDA::cudart
+     CUDA::cuda_driver # Needed as calls all CUDA calls will eventually move to driver
++    CUDA::nvrtc
+ )
+ 
+ # target cmake properties
+diff --git a/samples/legacy_samples/CMakeLists.txt b/samples/legacy_samples/CMakeLists.txt
+index 019f17c..3b56329 100644
+--- a/samples/legacy_samples/CMakeLists.txt
++++ b/samples/legacy_samples/CMakeLists.txt
+@@ -44,7 +44,9 @@ target_link_libraries(
+     _cudnn_frontend_pch
+     CUDNN::cudnn
+ 
++    CUDA::cublasLt
+     CUDA::cudart
++    CUDA::nvrtc
+ )
+ 
+ # target cmake properties
+diff --git a/test/cpp/CMakeLists.txt b/test/cpp/CMakeLists.txt
+index e244cd0..2750294 100644
+--- a/test/cpp/CMakeLists.txt
++++ b/test/cpp/CMakeLists.txt
+@@ -55,7 +55,9 @@ target_link_libraries(
+ 
+     CUDNN::cudnn
+ 
++    CUDA::cublasLt
+     CUDA::cudart
++    CUDA::nvrtc
+ )
+ 
+ # cuDNN dlopen's its libraries
+-- 
+2.47.0
+

pkgs/development/cuda-modules/packages/cudnn-frontend/0004-samples-fix-instances-of-maybe-uninitialized.patch

@@ -0,0 +1,591 @@
+From 4ce40a0c3de0e8a7065caf1cf59a90493e084682 Mon Sep 17 00:00:00 2001
+From: Connor Baker <ConnorBaker01@gmail.com>
+Date: Sat, 18 Jan 2025 22:22:21 +0000
+Subject: [PATCH 4/4] samples: fix instances of maybe-uninitialized
+
+---
+ samples/cpp/convolution/dgrads.cpp                 |  6 +++---
+ samples/cpp/convolution/fp8_fprop.cpp              |  2 +-
+ samples/cpp/convolution/fprop.cpp                  | 10 +++++-----
+ samples/cpp/convolution/int8_fprop.cpp             |  2 +-
+ samples/cpp/convolution/wgrads.cpp                 |  4 ++--
+ samples/cpp/matmul/fp8_matmul.cpp                  |  2 +-
+ samples/cpp/matmul/int8_matmul.cpp                 |  2 +-
+ samples/cpp/matmul/matmuls.cpp                     |  8 ++++----
+ samples/cpp/matmul/mixed_matmul.cpp                |  2 +-
+ samples/cpp/misc/pointwise.cpp                     |  6 +++---
+ samples/cpp/misc/resample.cpp                      |  6 +++---
+ samples/cpp/misc/serialization.cpp                 |  4 ++--
+ samples/cpp/misc/slice.cpp                         |  2 +-
+ samples/cpp/misc/sm_carveout.cpp                   |  2 +-
+ samples/cpp/norm/batchnorm.cpp                     |  8 ++++----
+ samples/cpp/norm/layernorm.cpp                     |  8 ++++----
+ samples/cpp/norm/rmsnorm.cpp                       |  6 +++---
+ samples/cpp/sdpa/fp16_bwd.cpp                      |  2 +-
+ samples/cpp/sdpa/fp16_bwd_with_flexible_graphs.cpp |  2 +-
+ samples/cpp/sdpa/fp16_cached.cpp                   |  2 +-
+ samples/cpp/sdpa/fp16_fwd.cpp                      |  2 +-
+ samples/cpp/sdpa/fp16_fwd_with_custom_dropout.cpp  |  2 +-
+ samples/cpp/sdpa/fp16_fwd_with_flexible_graphs.cpp |  2 +-
+ samples/cpp/sdpa/fp16_fwd_with_paged_caches.cpp    |  2 +-
+ samples/cpp/sdpa/fp8_bwd.cpp                       |  4 ++--
+ samples/cpp/sdpa/fp8_fwd.cpp                       |  2 +-
+ 26 files changed, 50 insertions(+), 50 deletions(-)
+
+diff --git a/samples/cpp/convolution/dgrads.cpp b/samples/cpp/convolution/dgrads.cpp
+index 589cb5f..f66abf4 100644
+--- a/samples/cpp/convolution/dgrads.cpp
++++ b/samples/cpp/convolution/dgrads.cpp
+@@ -65,7 +65,7 @@ TEST_CASE("Convolution Dgrad", "[dgrad][graph]") {
+     Surface<half> w_tensor(64 * 32 * 3 * 3, false);
+     Surface<half> dx_tensor(4 * 32 * 16 * 16, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+ 
+     Surface<int8_t> workspace(workspace_size, false);
+@@ -122,7 +122,7 @@ TEST_CASE("Dgrad Drelu Graph", "[dgrad][graph]") {
+     Surface<half> x_tensor(4 * 32 * 16 * 16, false);
+     Surface<half> dx_tensor(4 * 32 * 16 * 16, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -234,7 +234,7 @@ TEST_CASE("Dgrad Drelu DBNweight Graph", "[dgrad][graph]") {
+     Surface<float> eq_scale_x_tensor(1 * 32 * 1 * 1, false);
+     Surface<float> eq_bias_tensor(1 * 32 * 1 * 1, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/convolution/fp8_fprop.cpp b/samples/cpp/convolution/fp8_fprop.cpp
+index dfcb7e2..8246ce4 100644
+--- a/samples/cpp/convolution/fp8_fprop.cpp
++++ b/samples/cpp/convolution/fp8_fprop.cpp
+@@ -116,7 +116,7 @@ TEST_CASE("Convolution fp8 precision", "[conv][graph]") {
+     Surface<float> Y_scale_gpu(1, false);
+     Surface<float> amax_gpu(1, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/convolution/fprop.cpp b/samples/cpp/convolution/fprop.cpp
+index bc1aaf0..d61fa4e 100644
+--- a/samples/cpp/convolution/fprop.cpp
++++ b/samples/cpp/convolution/fprop.cpp
+@@ -80,7 +80,7 @@ TEST_CASE("Convolution fprop", "[conv][graph][caching]") {
+     std::unordered_map<int64_t, void *> variant_pack = {
+         {X->get_uid(), x_tensor.devPtr}, {W->get_uid(), w_tensor.devPtr}, {Y->get_uid(), y_tensor.devPtr}};
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -303,7 +303,7 @@ TEST_CASE("CSBR Graph", "[conv][graph][caching]") {
+     Surface<half> b_tensor(k, false);
+     Surface<half> y_tensor(n * k * h * w, false);  // Should be p, q.
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -550,7 +550,7 @@ TEST_CASE("SBRCS", "[conv][genstats][graph]") {
+         {SUM, sum_tensor.devPtr},
+         {SQ_SUM, sq_sum_tensor.devPtr}};
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -651,7 +651,7 @@ TEST_CASE("CBR Graph NCHW", "[conv][graph][caching]") {
+     Surface<half> y_tensor(n * k * h * w, false);  // Should be p, q.
+     Surface<half> z_tensor(n * k * h * w, false);  // Should be p, q.
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -734,7 +734,7 @@ TEST_CASE("Convolution fprop large", "[conv][graph][caching]") {
+     std::unordered_map<int64_t, void *> variant_pack = {
+         {X->get_uid(), x_tensor.devPtr}, {W->get_uid(), w_tensor.devPtr}, {Y->get_uid(), y_tensor.devPtr}};
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/convolution/int8_fprop.cpp b/samples/cpp/convolution/int8_fprop.cpp
+index 3d5ac2f..e9248f5 100644
+--- a/samples/cpp/convolution/int8_fprop.cpp
++++ b/samples/cpp/convolution/int8_fprop.cpp
+@@ -94,7 +94,7 @@ TEST_CASE("Conv with Int8 datatypes", "[conv][graph][caching]") {
+     std::unordered_map<std::shared_ptr<fe::graph::Tensor_attributes>, void*> variant_pack = {
+         {X, x_tensor.devPtr}, {W, w_tensor.devPtr}, {Y, y_tensor.devPtr}};
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/convolution/wgrads.cpp b/samples/cpp/convolution/wgrads.cpp
+index 2c58b26..26887dc 100644
+--- a/samples/cpp/convolution/wgrads.cpp
++++ b/samples/cpp/convolution/wgrads.cpp
+@@ -64,7 +64,7 @@ TEST_CASE("Convolution Wgrad", "[wgrad][graph][wgrad][Conv_wgrad]") {
+     Surface<half> dy_tensor(4 * 64 * 16 * 16, false);
+     Surface<half> dw_tensor(64 * 64 * 3 * 3, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -137,7 +137,7 @@ TEST_CASE("scale-bias-relu-wgrad Graph", "[wgrad][graph][scale-bias-relu-wgrad][
+     Surface<half> dy_tensor(4 * 64 * 16 * 16, false);
+     Surface<half> dw_tensor(64 * 64 * 3 * 3, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/matmul/fp8_matmul.cpp b/samples/cpp/matmul/fp8_matmul.cpp
+index c6470cd..f32c627 100644
+--- a/samples/cpp/matmul/fp8_matmul.cpp
++++ b/samples/cpp/matmul/fp8_matmul.cpp
+@@ -115,7 +115,7 @@ TEST_CASE("Matmul fp8 precision", "[matmul][graph]") {
+     REQUIRE(graph.build_plans(handle, fe::BuildPlanPolicy_t::HEURISTICS_CHOICE).is_good());
+ 
+     Surface<float> C_gpu(b * m * n, false);
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/matmul/int8_matmul.cpp b/samples/cpp/matmul/int8_matmul.cpp
+index cf4353a..cb3ce34 100644
+--- a/samples/cpp/matmul/int8_matmul.cpp
++++ b/samples/cpp/matmul/int8_matmul.cpp
+@@ -104,7 +104,7 @@ TEST_CASE("Int8 Matmul", "[matmul][graph]") {
+     // note this is a bf16 tensor, but half is used just for memory allocation
+     Surface<float> C_gpu(b * m * n, false);
+     Surface<float> Bias_gpu(b * m * n, false);
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/matmul/matmuls.cpp b/samples/cpp/matmul/matmuls.cpp
+index ed0f10b..5c95713 100644
+--- a/samples/cpp/matmul/matmuls.cpp
++++ b/samples/cpp/matmul/matmuls.cpp
+@@ -250,7 +250,7 @@ TEST_CASE("Matmul", "[matmul][graph]") {
+ 
+     // Run cudnn graph
+     Surface<float> C_gpu(b * m * n, false);
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -319,7 +319,7 @@ TEST_CASE("Abs + Matmul", "[matmul][graph]") {
+ 
+     // Run cudnn graph
+     Surface<float> C_gpu(b * m * n, false);
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -539,7 +539,7 @@ TEST_CASE("Matmul SBR Graph", "[matmul][graph]") {
+     auto [graph, A, B, bias, scale, O] = lookup_cache_or_build_graph(
+         handle, x_tensor.devPtr, w_tensor.devPtr, s_tensor.devPtr, b_tensor.devPtr, y_tensor.devPtr);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -606,7 +606,7 @@ TEST_CASE("Matmul with restricted shared memory", "[matmul][graph]") {
+ 
+     // Run cudnn graph
+     Surface<float> C_gpu(b * m * n, false);
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/matmul/mixed_matmul.cpp b/samples/cpp/matmul/mixed_matmul.cpp
+index ab3e195..a2b05bd 100644
+--- a/samples/cpp/matmul/mixed_matmul.cpp
++++ b/samples/cpp/matmul/mixed_matmul.cpp
+@@ -96,7 +96,7 @@ TEST_CASE("Mixed Precision Matmul", "[matmul][graph]") {
+     //// Run cudnn graph
+     // note this is a bf16 tensor, but half is used just for memory allocation
+     Surface<half> C_gpu(b * m * n, false);
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/misc/pointwise.cpp b/samples/cpp/misc/pointwise.cpp
+index 8f8d699..e8f4cb1 100644
+--- a/samples/cpp/misc/pointwise.cpp
++++ b/samples/cpp/misc/pointwise.cpp
+@@ -51,7 +51,7 @@ TEST_CASE("Reduction", "[reduction]") {
+     Surface<float> C_gpu(n * n * n * n, false);
+     std::unordered_map<std::shared_ptr<fe::graph::Tensor_attributes>, void*> variant_pack = {{A, A_gpu.devPtr},
+                                                                                              {C, C_gpu.devPtr}};
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -88,7 +88,7 @@ TEST_CASE("Fused scalar", "[scalar][graph]") {
+ 
+     std::unordered_map<std::shared_ptr<fe::graph::Tensor_attributes>, void*> variant_pack = {{A, A_gpu.devPtr},
+                                                                                              {C, C_gpu.devPtr}};
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -148,7 +148,7 @@ TEST_CASE("Fused Amax Reduction and type conversion", "[reduction]") {
+ 
+     std::unordered_map<std::shared_ptr<fe::graph::Tensor_attributes>, void*> variant_pack = {
+         {A, A_gpu.devPtr}, {scale, scale_gpu.devPtr}, {amax, amax_gpu.devPtr}, {C, C_gpu.devPtr}};
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/misc/resample.cpp b/samples/cpp/misc/resample.cpp
+index 3f782e7..21998c3 100644
+--- a/samples/cpp/misc/resample.cpp
++++ b/samples/cpp/misc/resample.cpp
+@@ -69,7 +69,7 @@ TEST_CASE("Resample Max Pooling NHWC Inference", "[resample][pooling][max][graph
+     Surface<half> Y_gpu(N * H * W * C, false);
+     std::unordered_map<std::shared_ptr<fe::graph::Tensor_attributes>, void*> variant_pack = {{X, X_gpu.devPtr},
+                                                                                              {Y, Y_gpu.devPtr}};
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -132,7 +132,7 @@ TEST_CASE("Resample Max Pooling NHWC Training", "[resample][pooling][max][graph]
+     Surface<int8_t> Index_gpu(N * H * W * C / 8, false);
+     std::unordered_map<std::shared_ptr<fe::graph::Tensor_attributes>, void*> variant_pack = {
+         {X, X_gpu.devPtr}, {Y, Y_gpu.devPtr}, {Index, Index_gpu.devPtr}};
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -186,7 +186,7 @@ TEST_CASE("Resample Avg Pooling", "[resample][pooling][average][graph]") {
+     Surface<half> Y_gpu(N * H * W * C, false);
+     std::unordered_map<std::shared_ptr<fe::graph::Tensor_attributes>, void*> variant_pack = {{X, X_gpu.devPtr},
+                                                                                              {Y, Y_gpu.devPtr}};
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/misc/serialization.cpp b/samples/cpp/misc/serialization.cpp
+index a130406..278bad8 100644
+--- a/samples/cpp/misc/serialization.cpp
++++ b/samples/cpp/misc/serialization.cpp
+@@ -178,7 +178,7 @@ TEST_CASE("CSBR Graph with serialization", "[conv][graph][serialization]") {
+     Surface<half> b_device_memory(k, false);
+     Surface<half> y_device_memory(n * k * h * w, false);  // Should be p, q.
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -401,7 +401,7 @@ TEST_CASE("SDPA Graph with serialization", "[sdpa][graph][serialization]") {
+     Surface<int32_t> dropoutSeed(scaleSize, false, seed_value);
+     Surface<int32_t> dropoutOffset(scaleSize, false, (int32_t)1);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/misc/slice.cpp b/samples/cpp/misc/slice.cpp
+index 087ba36..78962c6 100644
+--- a/samples/cpp/misc/slice.cpp
++++ b/samples/cpp/misc/slice.cpp
+@@ -80,7 +80,7 @@ TEST_CASE("Slice gemm", "[slice][gemm][graph][fusion]") {
+     Surface<half> C_gpu(B * M * N, false);
+     std::unordered_map<int64_t, void *> variant_pack = {
+         {a_uid, A_gpu.devPtr}, {b_uid, B_gpu.devPtr}, {c_uid, C_gpu.devPtr}};
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/misc/sm_carveout.cpp b/samples/cpp/misc/sm_carveout.cpp
+index d6818c0..b0e0651 100644
+--- a/samples/cpp/misc/sm_carveout.cpp
++++ b/samples/cpp/misc/sm_carveout.cpp
+@@ -121,7 +121,7 @@ TEST_CASE("SGBN with SM carveout", "[batchnorm][graph][sm_carveout]") {
+     Surface<float> Peer_stats_0_tensor(2 * 4 * c, false, true);
+     Surface<float> Peer_stats_1_tensor(2 * 4 * c, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/norm/batchnorm.cpp b/samples/cpp/norm/batchnorm.cpp
+index 5949365..a91a9bd 100644
+--- a/samples/cpp/norm/batchnorm.cpp
++++ b/samples/cpp/norm/batchnorm.cpp
+@@ -96,7 +96,7 @@ TEST_CASE("BN Finalize Graph", "[batchnorm][graph]") {
+     Surface<float> eq_scale_tensor(32, false);
+     Surface<float> eq_bias_tensor(32, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -226,7 +226,7 @@ TEST_CASE("SGBN Add Relu Graph", "[batchnorm][graph]") {
+     Surface<float> Peer_stats_0_tensor(2 * 4 * 32, false, true);
+     Surface<float> Peer_stats_1_tensor(2 * 4 * 32, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -346,7 +346,7 @@ TEST_CASE("DBN Add Relu Graph", "[BN][graph][backward]") {
+     Surface<float> Peer_stats_0_tensor(2 * 4 * 32, false, true);
+     Surface<float> Peer_stats_1_tensor(2 * 4 * 32, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -454,7 +454,7 @@ TEST_CASE("BN_inference DRelu DBN Graph", "[Batchnorm][graph][backward]") {
+     Surface<float> Dbias_tensor(32, false);
+     Surface<half> DX_tensor(4 * 32 * 16 * 16, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/norm/layernorm.cpp b/samples/cpp/norm/layernorm.cpp
+index bac996f..7f69f34 100644
+--- a/samples/cpp/norm/layernorm.cpp
++++ b/samples/cpp/norm/layernorm.cpp
+@@ -133,7 +133,7 @@ layernorm_fwd_dynamic_shapes(bool train = true) {
+         Surface<float> Mean_tensor(max_stats_volume, false);
+         Surface<float> Var_tensor(max_stats_volume, false);
+ 
+-        int64_t workspace_size;
++        int64_t workspace_size = 0;
+         REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+         Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -232,7 +232,7 @@ TEST_CASE("LayerNorm Training", "[layernorm][graph]") {
+     Surface<float> Bias_tensor(hidden_size, false);
+     Surface<half> Y_tensor(batch_size * seq_length * hidden_size, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -310,7 +310,7 @@ TEST_CASE("LayerNorm Inference", "[layernorm][graph]") {
+     Surface<float> Bias_tensor(hidden_size, false);
+     Surface<half> Y_tensor(batch_size * seq_length * hidden_size, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -392,7 +392,7 @@ TEST_CASE("LayerNorm Backward", "[layernorm][graph]") {
+     Surface<float> Dbias_tensor(hidden_size, false);
+     Surface<half> DX_tensor(batch_size * seq_length * hidden_size, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/norm/rmsnorm.cpp b/samples/cpp/norm/rmsnorm.cpp
+index 878086c..d5c919b 100644
+--- a/samples/cpp/norm/rmsnorm.cpp
++++ b/samples/cpp/norm/rmsnorm.cpp
+@@ -78,7 +78,7 @@ TEST_CASE("RmsNorm Training", "[rmsnorm][graph]") {
+     Surface<float> Scale_tensor(hidden_size, false);
+     Surface<float> Y_tensor(batch_size * seq_length * hidden_size, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -150,7 +150,7 @@ TEST_CASE("RmsNorm Inference", "[rmsnorm][graph]") {
+     Surface<float> Bias_tensor(hidden_size, false);
+     Surface<float> Y_tensor(batch_size * seq_length * hidden_size, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -227,7 +227,7 @@ TEST_CASE("RmsNorm Backward", "[rmsnorm][graph]") {
+     Surface<float> Dbias_tensor(hidden_size, false);
+     Surface<float> DX_tensor(batch_size * seq_length * hidden_size, false);
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/sdpa/fp16_bwd.cpp b/samples/cpp/sdpa/fp16_bwd.cpp
+index 749cbed..1145008 100644
+--- a/samples/cpp/sdpa/fp16_bwd.cpp
++++ b/samples/cpp/sdpa/fp16_bwd.cpp
+@@ -275,7 +275,7 @@ TEST_CASE("Toy sdpa backward", "[graph][sdpa][flash][backward]") {
+     }
+ 
+     // Allocate workspace
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/sdpa/fp16_bwd_with_flexible_graphs.cpp b/samples/cpp/sdpa/fp16_bwd_with_flexible_graphs.cpp
+index 62d6bb3..50205c3 100644
+--- a/samples/cpp/sdpa/fp16_bwd_with_flexible_graphs.cpp
++++ b/samples/cpp/sdpa/fp16_bwd_with_flexible_graphs.cpp
+@@ -195,7 +195,7 @@ TEST_CASE("Toy sdpa backward with flexible graph", "[graph][sdpa][flash][backwar
+                                                                                    {DV_UID, dV_tensor.devPtr}};
+ 
+     // Allocate workspace
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/sdpa/fp16_cached.cpp b/samples/cpp/sdpa/fp16_cached.cpp
+index d046271..4f0d3f8 100644
+--- a/samples/cpp/sdpa/fp16_cached.cpp
++++ b/samples/cpp/sdpa/fp16_cached.cpp
+@@ -146,7 +146,7 @@ TEST_CASE("Cached sdpa", "[graph][sdpa][flash]") {
+                     {O_UID, o_tensor.devPtr},
+                     {STATS_UID, stats_tensor.devPtr}};
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(fwd_graph2->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> fwd_workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/sdpa/fp16_fwd.cpp b/samples/cpp/sdpa/fp16_fwd.cpp
+index b3acf5e..63697a1 100644
+--- a/samples/cpp/sdpa/fp16_fwd.cpp
++++ b/samples/cpp/sdpa/fp16_fwd.cpp
+@@ -210,7 +210,7 @@ TEST_CASE("Toy sdpa forward", "[graph][sdpa][flash][forward]") {
+         variant_pack[STATS_UID] = statsTensor.devPtr;
+     }
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/sdpa/fp16_fwd_with_custom_dropout.cpp b/samples/cpp/sdpa/fp16_fwd_with_custom_dropout.cpp
+index 36cfba4..0cb9d2f 100644
+--- a/samples/cpp/sdpa/fp16_fwd_with_custom_dropout.cpp
++++ b/samples/cpp/sdpa/fp16_fwd_with_custom_dropout.cpp
+@@ -178,7 +178,7 @@ TEST_CASE("Toy sdpa forward with dropout", "[graph][sdpa][flash][forward]") {
+         variant_pack[STATS_UID] = statsTensor.devPtr;
+     }
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/sdpa/fp16_fwd_with_flexible_graphs.cpp b/samples/cpp/sdpa/fp16_fwd_with_flexible_graphs.cpp
+index 810de63..7d81afe 100644
+--- a/samples/cpp/sdpa/fp16_fwd_with_flexible_graphs.cpp
++++ b/samples/cpp/sdpa/fp16_fwd_with_flexible_graphs.cpp
+@@ -186,7 +186,7 @@ TEST_CASE("Toy sdpa forward with flexible graph", "[graph][sdpa][flash][forward]
+         variant_pack[STATS_UID] = statsTensor.devPtr;
+     }
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/sdpa/fp16_fwd_with_paged_caches.cpp b/samples/cpp/sdpa/fp16_fwd_with_paged_caches.cpp
+index 18dd937..d195f6b 100644
+--- a/samples/cpp/sdpa/fp16_fwd_with_paged_caches.cpp
++++ b/samples/cpp/sdpa/fp16_fwd_with_paged_caches.cpp
+@@ -268,7 +268,7 @@ TEST_CASE("Toy sdpa forward with paged caches", "[graph][sdpa][flash][paged][for
+         variant_pack[STATS_UID] = statsTensor.devPtr;
+     }
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(graph->get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/sdpa/fp8_bwd.cpp b/samples/cpp/sdpa/fp8_bwd.cpp
+index 82e542b..296f2f9 100644
+--- a/samples/cpp/sdpa/fp8_bwd.cpp
++++ b/samples/cpp/sdpa/fp8_bwd.cpp
+@@ -214,7 +214,7 @@ TEST_CASE("sdpa_fp8_bprop", "[graph][sdpa][fp8][backward]") {
+         {Amax_dV, AMax_dV_Tensor.devPtr},
+         {Amax_dP, AMax_dP_Tensor.devPtr}};
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(mha_graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+@@ -385,7 +385,7 @@ TEST_CASE("sdpa_fp8_gqa_bprop", "[graph][sdpa][fp8][backward]") {
+         {amax_dV, amax_dV_gpu.devPtr},
+         {amax_dP, amax_dP_gpu.devPtr}};
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(mha_graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+diff --git a/samples/cpp/sdpa/fp8_fwd.cpp b/samples/cpp/sdpa/fp8_fwd.cpp
+index 6ede98d..23abc3f 100644
+--- a/samples/cpp/sdpa/fp8_fwd.cpp
++++ b/samples/cpp/sdpa/fp8_fwd.cpp
+@@ -146,7 +146,7 @@ TEST_CASE("sdpa_fp8_fprop", "[graph][sdpa][fp8][forward]") {
+         variant_pack[Stats] = stats_tensor.devPtr;
+     }
+ 
+-    int64_t workspace_size;
++    int64_t workspace_size = 0;
+     REQUIRE(mha_graph.get_workspace_size(workspace_size).is_good());
+     Surface<int8_t> workspace(workspace_size, false);
+ 
+-- 
+2.47.0
+

pkgs/development/cuda-modules/packages/cudnn-frontend/CMakeLists.txt

@@ -0,0 +1,133 @@
+cmake_minimum_required(VERSION 3.23)
+
+project(cudnn_frontend VERSION 1.8.0)
+
+option(CUDNN_FRONTEND_SKIP_JSON_LIB "Defines whether FE should not include nlohmann/json.hpp." OFF)
+option(CUDNN_FRONTEND_BUILD_SAMPLES "Defines if samples are built or not." ON)
+option(CUDNN_FRONTEND_BUILD_TESTS "Defines if unittests are built or not." ON)
+option(CUDNN_FRONTEND_BUILD_PYTHON_BINDINGS "Defines if python bindings are built or not." OFF)
+
+if(MSVC OR MSYS OR MINGW)
+    add_compile_options(/W4 /WX)
+else()
+    add_compile_options(-Wall -Wextra -Wpedantic -Werror -Wno-error=attributes -Wno-attributes -Wno-error=unused-function -Wno-unused-function)
+endif()
+
+add_library(cudnn_frontend INTERFACE)
+
+# Add header files to library
+file(GLOB_RECURSE CUDNN_FRONTEND_INCLUDE_FILES "include/*")
+target_sources(
+    cudnn_frontend
+    PUBLIC
+        FILE_SET
+            HEADERS
+            BASE_DIRS
+                "$<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>"
+            FILES
+                "${CUDNN_FRONTEND_INCLUDE_FILES}"
+)
+unset(CUDNN_FRONTEND_INCLUDE_FILES)
+
+target_compile_definitions(cudnn_frontend INTERFACE $<$<BOOL:${CUDNN_FRONTEND_SKIP_JSON_LIB}>:CUDNN_FRONTEND_SKIP_JSON_LIB>)
+
+target_include_directories(
+    cudnn_frontend
+    INTERFACE
+        "$<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>"
+        "$<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>"
+)
+
+# Find the cuda compiler
+find_package(CUDAToolkit REQUIRED)
+
+target_include_directories(cudnn_frontend INTERFACE ${CUDAToolkit_INCLUDE_DIRS})
+
+target_compile_features(cudnn_frontend INTERFACE cxx_std_17)
+
+# Make PCH for targets to link against
+add_library(_cudnn_frontend_pch INTERFACE)
+target_precompile_headers(_cudnn_frontend_pch INTERFACE ${PROJECT_SOURCE_DIR}/include/cudnn_frontend.h)
+
+if (CUDNN_FRONTEND_BUILD_SAMPLES)
+    add_subdirectory(samples)
+    target_link_libraries(
+        samples
+        PRIVATE
+            CUDA::cublasLt
+            CUDA::nvrtc
+    )
+    target_link_libraries(
+        legacy_samples
+        PRIVATE
+            CUDA::cublasLt
+            CUDA::nvrtc
+    )
+endif()
+
+if (CUDNN_FRONTEND_BUILD_TESTS)
+    add_subdirectory(test)
+    target_link_libraries(
+        tests
+        CUDA::cublasLt
+        CUDA::nvrtc
+    )
+endif()
+
+if (CUDNN_FRONTEND_BUILD_PYTHON_BINDINGS)
+    add_subdirectory(python)
+endif()
+
+# Introduce variables:
+# * CMAKE_INSTALL_LIBDIR
+# * CMAKE_INSTALL_BINDIR
+# * CMAKE_INSTALL_INCLUDEDIR
+include(GNUInstallDirs)
+
+# Install and export the header files
+install(
+    TARGETS
+        cudnn_frontend
+    EXPORT
+        cudnn_frontend_targets
+    FILE_SET HEADERS
+)
+
+if (CUDNN_FRONTEND_BUILD_SAMPLES)
+    install(TARGETS legacy_samples samples RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
+endif()
+
+if (CUDNN_FRONTEND_BUILD_TESTS)
+    install(TARGETS tests RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
+endif()
+
+# See https://cmake.org/cmake/help/latest/module/CMakePackageConfigHelpers.html#example-generating-package-files
+include(CMakePackageConfigHelpers)
+
+export(
+    EXPORT
+        cudnn_frontend_targets
+    FILE
+        "${CMAKE_CURRENT_BINARY_DIR}/cudnn_frontend/cudnn_frontend-targets.cmake"
+)
+install(
+    EXPORT
+        cudnn_frontend_targets
+    FILE
+        cudnn_frontend-targets.cmake
+    DESTINATION
+        "${CMAKE_INSTALL_LIBDIR}/cmake/cudnn_frontend"
+)
+
+configure_package_config_file(
+    cudnn_frontend-config.cmake.in
+    "${CMAKE_CURRENT_BINARY_DIR}/cudnn_frontend-config.cmake"
+    INSTALL_DESTINATION
+        "${CMAKE_INSTALL_LIBDIR}/cmake/cudnn_frontend"
+)
+install(
+    FILES
+        "${CMAKE_CURRENT_BINARY_DIR}/cudnn_frontend-config.cmake"
+    DESTINATION
+        "${CMAKE_INSTALL_LIBDIR}/cmake/cudnn_frontend"
+)

pkgs/development/cuda-modules/packages/cudnn-frontend/cudnn_frontend-config.cmake.in

@@ -0,0 +1,3 @@
+@PACKAGE_INIT@
+
+include(${CMAKE_CURRENT_LIST_DIR}/cudnn_frontend-targets.cmake)

pkgs/development/cuda-modules/packages/cudnn-frontend/package.nix

@@ -0,0 +1,132 @@
+{
+  autoAddDriverRunpath,
+  catch2_3,
+  cmake,
+  fetchFromGitHub,
+  gitUpdater,
+  lib,
+  ninja,
+  nlohmann_json,
+  stdenv,
+  cuda_cccl ? null,
+  cuda_cudart ? null,
+  cuda_nvcc ? null,
+  cuda_nvrtc ? null,
+  cudnn ? null,
+  libcublas ? null,
+}:
+let
+  inherit (lib.lists) optionals;
+  inherit (lib.strings)
+    cmakeBool
+    cmakeFeature
+    optionalString
+    ;
+in
+
+# TODO(@connorbaker): This should be a hybrid C++/Python package.
+stdenv.mkDerivation (finalAttrs: {
+  pname = "cudnn-frontend";
+  version = "1.9.0";
+
+  src = fetchFromGitHub {
+    owner = "NVIDIA";
+    repo = "cudnn-frontend";
+    tag = "v${finalAttrs.version}";
+    hash = "sha256-Vc5jqB1XHcJEdKG0nxbWLewW2fDezRVwjUSzPDubSGE=";
+  };
+
+  patches = [
+    # https://github.com/NVIDIA/cudnn-frontend/pull/125
+    ./0001-cmake-float-out-common-python-bindings-option.patch
+    ./0002-cmake-add-config-so-headers-can-be-discovered-when-i.patch
+    ./0003-cmake-install-samples-and-tests-when-built.patch
+    ./0004-samples-fix-instances-of-maybe-uninitialized.patch
+  ];
+
+  # nlohmann_json should be the only vendored dependency.
+  postPatch = ''
+    echo "patching source to use nlohmann_json from nixpkgs"
+    rm -rf include/cudnn_frontend/thirdparty/nlohmann
+    rmdir include/cudnn_frontend/thirdparty
+    substituteInPlace include/cudnn_frontend_utils.h \
+      --replace-fail \
+        '#include "cudnn_frontend/thirdparty/nlohmann/json.hpp"' \
+        '#include <nlohmann/json.hpp>'
+  '';
+
+  # TODO: As a header-only library, we should make sure we have an `include` directory or similar which is not a
+  # superset of the `out` (`bin`) or `dev` outputs (which is what the multiple-outputs setup hook does by default).
+  outputs = [
+    "out"
+  ]
+  ++ optionals finalAttrs.doCheck [
+    "legacy_samples"
+    "samples"
+    "tests"
+  ];
+
+  nativeBuildInputs = [
+    autoAddDriverRunpath # Needed for samples because it links against CUDA::cuda_driver
+    cmake
+    cuda_nvcc
+    ninja
+  ];
+
+  buildInputs = [
+    cuda_cccl
+    cuda_cudart
+  ];
+
+  cmakeFlags = [
+    (cmakeBool "FETCHCONTENT_FULLY_DISCONNECTED" true)
+    (cmakeFeature "FETCHCONTENT_TRY_FIND_PACKAGE_MODE" "ALWAYS")
+    (cmakeBool "CUDNN_FRONTEND_BUILD_SAMPLES" finalAttrs.doCheck)
+    (cmakeBool "CUDNN_FRONTEND_BUILD_TESTS" finalAttrs.doCheck)
+    (cmakeBool "CUDNN_FRONTEND_BUILD_PYTHON_BINDINGS" false)
+  ];
+
+  checkInputs = [
+    cudnn
+    cuda_nvrtc
+    catch2_3
+    libcublas
+  ];
+
+  enableParallelBuilding = true;
+
+  propagatedBuildInputs = [
+    nlohmann_json
+  ];
+
+  doCheck = true;
+
+  postInstall = optionalString finalAttrs.doCheck ''
+    moveToOutput "bin/legacy_samples" "$legacy_samples"
+    moveToOutput "bin/samples" "$samples"
+    moveToOutput "bin/tests" "$tests"
+    if [[ -e "$out/bin" ]]
+    then
+      nixErrorLog "The bin directory in \$out should no longer exist."
+      exit 1
+    fi
+  '';
+
+  passthru.updateScript = gitUpdater {
+    inherit (finalAttrs) pname version;
+    rev-prefix = "v";
+  };
+
+  meta = {
+    description = "A c++ wrapper for the cudnn backend API";
+    homepage = "https://github.com/NVIDIA/cudnn-frontend";
+    license = lib.licenses.mit;
+    badPlatforms = optionals (cudnn == null) finalAttrs.meta.platforms;
+    platforms = [
+      "aarch64-linux"
+      "x86_64-linux"
+    ];
+    maintainers = with lib.maintainers; [ connorbaker ];
+    teams = [ lib.teams.cuda ];
+  };
+})