Awesome work, I'm really looking forward to demoing this.

However I am currently running into build errors that I have not been able to troubleshoot myself, I have followed the instructions on your README.md. I am running Ubuntu 20 on a laptop with an NVIDIA GeForce RTX 2070 card and cuda 11.3.

Here are the logs of the build commands

`user@computer:~/software/instant-ngp$ cmake . -B build -DCMAKE_CUDA_COMPILER=/usr/local/cuda-11.3/bin/nvcc
-- The CUDA compiler identification is NVIDIA 11.3.109
-- Check for working CUDA compiler: /usr/local/cuda-11.3/bin/nvcc
-- Check for working CUDA compiler: /usr/local/cuda-11.3/bin/nvcc - works
-- Detecting CUDA compile features
-- Detecting CUDA compile features - done
-- No release type specified. Setting to 'Release'.
-- Looking for pthread.h
-- Looking for pthread.h - found
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Failed
-- Looking for pthread_create in pthreads
-- Looking for pthread_create in pthreads - not found
-- Looking for pthread_create in pthread
-- Looking for pthread_create in pthread - found
-- Found Threads: TRUE
-- Using X11 for window creation
-- Found X11: /usr/include
-- Looking for XOpenDisplay in /usr/lib/x86_64-linux-gnu/libX11.so;/usr/lib/x86_64-linux-gnu/libXext.so
-- Looking for XOpenDisplay in /usr/lib/x86_64-linux-gnu/libX11.so;/usr/lib/x86_64-linux-gnu/libXext.so - found
-- Looking for gethostbyname
-- Looking for gethostbyname - found
-- Looking for connect
-- Looking for connect - found
-- Looking for remove
-- Looking for remove - found
-- Looking for shmat
-- Looking for shmat - found
-- Looking for IceConnectionNumber in ICE
-- Looking for IceConnectionNumber in ICE - found
-- Found GLEW: /usr/include (found version "2.1.0")
-- Found OpenMP_C: -fopenmp (found version "4.5")
-- Found OpenMP_CXX: -fopenmp (found version "4.5")
-- Found OpenMP: TRUE (found version "4.5")
-- !!! Warning OptiX_INSTALL_DIR not set in environment. using default
-- OptiX_INSTALL_DIR value: /usr/local/NVIDIA-OptiX-SDK-7.3.0-linux64-x86_64
-- OptiX headers (optix.h and friends) not found.
CMake Warning at CMakeLists.txt:169 (message):
OptiX was not found. Neural graphics primitives will still compile and run
correctly. However, SDF training in 'raystab' and 'pathescape' modes will
be significantly slower.

-- Found Python: /usr/bin/python3.8 (found suitable version "3.8.10", minimum required is "3.7") found components: Interpreter Development Development.Module Development.Embed
-- pybind11 v2.7.1
CMake Warning (dev) at /home/user/software/cmake-3.22.1-linux-x86_64/share/cmake-3.22/Modules/CMakeDependentOption.cmake:84 (message):
Policy CMP0127 is not set: cmake_dependent_option() supports full Condition
Syntax. Run "cmake --help-policy CMP0127" for policy details. Use the
cmake_policy command to set the policy and suppress this warning.
Call Stack (most recent call first):
dependencies/pybind11/CMakeLists.txt:98 (cmake_dependent_option)
This warning is for project developers. Use -Wno-dev to suppress it.

-- Performing Test HAS_FLTO
-- Performing Test HAS_FLTO - Success
-- Targeting GPU architectures: 75
-- Configuring done
-- Generating done
-- Build files have been written to: /home/user/software/instant-ngp/build
user@computer:~/software/instant-ngp$ cmake --build build --config RelWithDebInfo -j 16
[ 1%] Building CUDA object dependencies/tiny-cuda-nn/src/CMakeFiles/tiny-cuda-nn.dir/common.cu.o
[ 3%] Building CUDA object dependencies/tiny-cuda-nn/src/CMakeFiles/tiny-cuda-nn.dir/common_device.cu.o
[ 5%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/context.c.o
[ 9%] Building CUDA object dependencies/tiny-cuda-nn/src/CMakeFiles/tiny-cuda-nn.dir/cutlass_resnet.cu.o
[ 9%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/init.c.o
[ 12%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/monitor.c.o
[ 12%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/input.c.o
[ 14%] Building CUDA object dependencies/tiny-cuda-nn/src/CMakeFiles/tiny-cuda-nn.dir/cutlass_mlp.cu.o
[ 16%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/vulkan.c.o
[ 18%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/window.c.o
[ 20%] Building CUDA object dependencies/tiny-cuda-nn/src/CMakeFiles/tiny-cuda-nn.dir/encoding.cu.o
[ 21%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/x11_init.c.o
[ 23%] Building CUDA object dependencies/tiny-cuda-nn/src/CMakeFiles/tiny-cuda-nn.dir/loss.cu.o
[ 25%] Building CUDA object dependencies/tiny-cuda-nn/src/CMakeFiles/tiny-cuda-nn.dir/network.cu.o
[ 27%] Building CUDA object dependencies/tiny-cuda-nn/src/CMakeFiles/tiny-cuda-nn.dir/object.cu.o
[ 29%] Building CUDA object dependencies/tiny-cuda-nn/src/CMakeFiles/tiny-cuda-nn.dir/optimizer.cu.o
[ 30%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/x11_monitor.c.o
[ 32%] Building CUDA object dependencies/tiny-cuda-nn/src/CMakeFiles/tiny-cuda-nn.dir/reduce_sum.cu.o
[ 34%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/x11_window.c.o
[ 36%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/xkb_unicode.c.o
[ 38%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/posix_time.c.o
[ 40%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/posix_thread.c.o
[ 41%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/glx_context.c.o
[ 43%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/egl_context.c.o
[ 45%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/osmesa_context.c.o
[ 47%] Building C object dependencies/glfw/src/CMakeFiles/glfw_objects.dir/linux_joystick.c.o
[ 49%] Building CUDA object dependencies/tiny-cuda-nn/src/CMakeFiles/tiny-cuda-nn.dir/fully_fused_mlp.cu.o
[ 49%] Built target glfw_objects
[ 50%] Linking CUDA static library libtiny-cuda-nn.a
[ 50%] Built target tiny-cuda-nn
[ 52%] Building CXX object CMakeFiles/ngp.dir/dependencies/imgui/ImGuizmo.cpp.o
[ 54%] Building CXX object CMakeFiles/ngp.dir/dependencies/imgui/imgui.cpp.o
[ 56%] Building CXX object CMakeFiles/ngp.dir/dependencies/imgui/imgui_impl_glfw.cpp.o
[ 58%] Building CXX object CMakeFiles/ngp.dir/dependencies/imgui/imgui_impl_opengl3.cpp.o
[ 60%] Building CXX object CMakeFiles/ngp.dir/dependencies/imgui/imgui_draw.cpp.o
[ 61%] Building CXX object CMakeFiles/ngp.dir/dependencies/imgui/imgui_tables.cpp.o
[ 63%] Building CXX object CMakeFiles/ngp.dir/dependencies/imgui/imgui_widgets.cpp.o
[ 65%] Building CUDA object CMakeFiles/ngp.dir/src/camera_path.cu.o
[ 67%] Building CUDA object CMakeFiles/ngp.dir/src/common_device.cu.o
[ 69%] Building CUDA object CMakeFiles/ngp.dir/src/marching_cubes.cu.o
[ 70%] Building CUDA object CMakeFiles/ngp.dir/src/nerf_loader.cu.o
[ 72%] Building CUDA object CMakeFiles/ngp.dir/src/render_buffer.cu.o
[ 74%] Building CUDA object CMakeFiles/ngp.dir/src/testbed.cu.o
[ 76%] Building CUDA object CMakeFiles/ngp.dir/src/testbed_image.cu.o
[ 78%] Building CUDA object CMakeFiles/ngp.dir/src/testbed_nerf.cu.o
[ 80%] Building CUDA object CMakeFiles/ngp.dir/src/testbed_sdf.cu.o
[ 81%] Building CUDA object CMakeFiles/ngp.dir/src/testbed_volume.cu.o
[ 83%] Building CXX object CMakeFiles/ngp.dir/src/thread_pool.cpp.o
[ 85%] Building CUDA object CMakeFiles/ngp.dir/src/tinyexr_wrapper.cu.o
[ 87%] Building CXX object CMakeFiles/ngp.dir/src/tinyobj_loader_wrapper.cpp.o
[ 89%] Building CUDA object CMakeFiles/ngp.dir/src/triangle_bvh.cu.o
[ 90%] Linking CUDA device code CMakeFiles/ngp.dir/cmake_device_link.o
[ 92%] Linking CXX static library libngp.a
[ 92%] Built target ngp
[ 96%] Building CUDA object CMakeFiles/pyngp.dir/src/python_api.cu.o
[ 96%] Building CUDA object CMakeFiles/testbed.dir/src/main.cu.o
[ 98%] Linking CXX executable testbed
/usr/bin/ld: libngp.a(testbed_image.cu.o): in function void tcnn::CudaGraph::capture_and_execute<tcnn::Trainer<float, __half, __half>::training_step(CUstream_st*, tcnn::GPUMatrix<float, (tcnn::MatrixLayout)1> const&, tcnn::GPUMatrix<float, (tcnn::MatrixLayout)1> const&, float*, tcnn::GPUMatrix<float, (tcnn::MatrixLayout)1> const*)::{lambda()#1}>(CUstream_st*, bool, tcnn::Trainer<float, __half, __half>::training_step(CUstream_st*, tcnn::GPUMatrix<float, (tcnn::MatrixLayout)1> const&, tcnn::GPUMatrix<float, (tcnn::MatrixLayout)1> const&, float*, tcnn::GPUMatrix<float, (tcnn::MatrixLayout)1> const*)::{lambda()#1})': tmpxft_00005ad8_00000000-6_testbed_image.cudafe1.cpp:(.text._ZN4tcnn9CudaGraph19capture_and_executeIZNS_7TrainerIf6__halfS3_E13training_stepEP11CUstream_stRKNS_9GPUMatrixIfLNS_12MatrixLayoutE1EEESB_PfPSA_EUlvE_EEvS6_bT_[_ZN4tcnn9CudaGraph19capture_and_executeIZNS_7TrainerIf6__halfS3_E13training_stepEP11CUstream_stRKNS_9GPUMatrixIfLNS_12MatrixLayoutE1EEESB_PfPSA_EUlvE_EEvS6_bT_]+0x406): undefined reference to cudaGraphExecUpdate'
/usr/bin/ld: dependencies/tiny-cuda-nn/src/libtiny-cuda-nn.a(optimizer.cu.o): in function tcnn::ShampooOptimizer<float>::step(CUstream_st*, float, float*, float*, float const*)::{lambda()#1}::operator()() const': tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text._ZZN4tcnn16ShampooOptimizerIfE4stepEP11CUstream_stfPfS4_PKfENKUlvE_clEv[_ZZN4tcnn16ShampooOptimizerIfE4stepEP11CUstream_stfPfS4_PKfENKUlvE_clEv]+0xacf): undefined reference to cublasSetWorkspace_v2'
/usr/bin/ld: tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text._ZZN4tcnn16ShampooOptimizerIfE4stepEP11CUstream_stfPfS4_PKfENKUlvE_clEv[_ZZN4tcnn16ShampooOptimizerIfE4stepEP11CUstream_stfPfS4_PKfENKUlvE_clEv]+0xebb): undefined reference to cublasSetWorkspace_v2' /usr/bin/ld: tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text._ZZN4tcnn16ShampooOptimizerIfE4stepEP11CUstream_stfPfS4_PKfENKUlvE_clEv[_ZZN4tcnn16ShampooOptimizerIfE4stepEP11CUstream_stfPfS4_PKfENKUlvE_clEv]+0x12c1): undefined reference to cublasSetWorkspace_v2'
/usr/bin/ld: dependencies/tiny-cuda-nn/src/libtiny-cuda-nn.a(optimizer.cu.o): in function tcnn::ShampooOptimizer<__half>::step(CUstream_st*, float, float*, __half*, __half const*)::{lambda()#1}::operator()() const': tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text._ZZN4tcnn16ShampooOptimizerI6__halfE4stepEP11CUstream_stfPfPS1_PKS1_ENKUlvE_clEv[_ZZN4tcnn16ShampooOptimizerI6__halfE4stepEP11CUstream_stfPfPS1_PKS1_ENKUlvE_clEv]+0xaec): undefined reference to cublasSetWorkspace_v2'
/usr/bin/ld: tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text._ZZN4tcnn16ShampooOptimizerI6__halfE4stepEP11CUstream_stfPfPS1_PKS1_ENKUlvE_clEv[_ZZN4tcnn16ShampooOptimizerI6__halfE4stepEP11CUstream_stfPfPS1_PKS1_ENKUlvE_clEv]+0xed8): undefined reference to cublasSetWorkspace_v2' /usr/bin/ld: dependencies/tiny-cuda-nn/src/libtiny-cuda-nn.a(optimizer.cu.o):tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text._ZZN4tcnn16ShampooOptimizerI6__halfE4stepEP11CUstream_stfPfPS1_PKS1_ENKUlvE_clEv[_ZZN4tcnn16ShampooOptimizerI6__halfE4stepEP11CUstream_stfPfPS1_PKS1_ENKUlvE_clEv]+0x12de): more undefined references to cublasSetWorkspace_v2' follow
/usr/bin/ld: dependencies/tiny-cuda-nn/src/libtiny-cuda-nn.a(optimizer.cu.o): in function void tcnn::CudaGraph::capture_and_execute<tcnn::ShampooOptimizer<float>::step(CUstream_st*, float, float*, float*, float const*)::{lambda()#1}>(CUstream_st*, bool, tcnn::ShampooOptimizer<float>::step(CUstream_st*, float, float*, float*, float const*)::{lambda()#1})': tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text._ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerIfE4stepEP11CUstream_stfPfS6_PKfEUlvE_EEvS5_bT_[_ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerIfE4stepEP11CUstream_stfPfS6_PKfEUlvE_EEvS5_bT_]+0x406): undefined reference to cudaGraphExecUpdate'
/usr/bin/ld: dependencies/tiny-cuda-nn/src/libtiny-cuda-nn.a(optimizer.cu.o): in function void tcnn::CudaGraph::capture_and_execute<tcnn::ShampooOptimizer<float>::inverse_pth_root_batched<float>(CUstream_st*, unsigned int, float*, tcnn::GPUMemory<float>&, unsigned int, unsigned int)::{lambda()#1}>(CUstream_st*, bool, tcnn::ShampooOptimizer<float>::inverse_pth_root_batched<float>(CUstream_st*, unsigned int, float*, tcnn::GPUMemory<float>&, unsigned int, unsigned int)::{lambda()#1})': tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text._ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerIfE24inverse_pth_root_batchedIfEEvP11CUstream_stjPfRNS_9GPUMemoryIT_EEjjEUlvE_EEvS6_bS9_[_ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerIfE24inverse_pth_root_batchedIfEEvP11CUstream_stjPfRNS_9GPUMemoryIT_EEjjEUlvE_EEvS6_bS9_]+0x406): undefined reference to cudaGraphExecUpdate'
/usr/bin/ld: dependencies/tiny-cuda-nn/src/libtiny-cuda-nn.a(optimizer.cu.o): in function void tcnn::CudaGraph::capture_and_execute<tcnn::ShampooOptimizer<float>::inverse_pth_root_batched<float>(CUstream_st*, unsigned int, float*, tcnn::GPUMemory<float>&, unsigned int, unsigned int)::{lambda()#2}>(CUstream_st*, bool, tcnn::ShampooOptimizer<float>::inverse_pth_root_batched<float>(CUstream_st*, unsigned int, float*, tcnn::GPUMemory<float>&, unsigned int, unsigned int)::{lambda()#2})': tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text._ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerIfE24inverse_pth_root_batchedIfEEvP11CUstream_stjPfRNS_9GPUMemoryIT_EEjjEUlvE0_EEvS6_bS9_[_ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerIfE24inverse_pth_root_batchedIfEEvP11CUstream_stjPfRNS_9GPUMemoryIT_EEjjEUlvE0_EEvS6_bS9_]+0x406): undefined reference to cudaGraphExecUpdate'
/usr/bin/ld: dependencies/tiny-cuda-nn/src/libtiny-cuda-nn.a(optimizer.cu.o): in function void tcnn::CudaGraph::capture_and_execute<tcnn::ShampooOptimizer<__half>::step(CUstream_st*, float, float*, __half*, __half const*)::{lambda()#1}>(CUstream_st*, bool, tcnn::ShampooOptimizer<__half>::step(CUstream_st*, float, float*, __half*, __half const*)::{lambda()#1})': tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text._ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerI6__halfE4stepEP11CUstream_stfPfPS3_PKS3_EUlvE_EEvS6_bT_[_ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerI6__halfE4stepEP11CUstream_stfPfPS3_PKS3_EUlvE_EEvS6_bT_]+0x406): undefined reference to cudaGraphExecUpdate'
/usr/bin/ld: dependencies/tiny-cuda-nn/src/libtiny-cuda-nn.a(optimizer.cu.o): in function void tcnn::CudaGraph::capture_and_execute<tcnn::ShampooOptimizer<__half>::inverse_pth_root_batched<float>(CUstream_st*, unsigned int, float*, tcnn::GPUMemory<float>&, unsigned int, unsigned int)::{lambda()#1}>(CUstream_st*, bool, tcnn::ShampooOptimizer<__half>::inverse_pth_root_batched<float>(CUstream_st*, unsigned int, float*, tcnn::GPUMemory<float>&, unsigned int, unsigned int)::{lambda()#1})': tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text._ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerI6__halfE24inverse_pth_root_batchedIfEEvP11CUstream_stjPfRNS_9GPUMemoryIT_EEjjEUlvE_EEvS7_bSA_[_ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerI6__halfE24inverse_pth_root_batchedIfEEvP11CUstream_stjPfRNS_9GPUMemoryIT_EEjjEUlvE_EEvS7_bSA_]+0x406): undefined reference to cudaGraphExecUpdate'
/usr/bin/ld: dependencies/tiny-cuda-nn/src/libtiny-cuda-nn.a(optimizer.cu.o):tmpxft_00005870_00000000-6_optimizer.cudafe1.cpp:(.text.ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerI6__halfE24inverse_pth_root_batchedIfEEvP11CUstream_stjPfRNS_9GPUMemoryIT_EEjjEUlvE0_EEvS7_bSA[ZN4tcnn9CudaGraph19capture_and_executeIZNS_16ShampooOptimizerI6__halfE24inverse_pth_root_batchedIfEEvP11CUstream_stjPfRNS_9GPUMemoryIT_EEjjEUlvE0_EEvS7_bSA]+0x406): more undefined references to cudaGraphExecUpdate' follow collect2: error: ld returned 1 exit status make[2]: *** [CMakeFiles/testbed.dir/build.make:116: testbed] Error 1 make[1]: *** [CMakeFiles/Makefile2:200: CMakeFiles/testbed.dir/all] Error 2 make[1]: *** Waiting for unfinished jobs.... [100%] Linking CXX shared library pyngp.cpython-38-x86_64-linux-gnu.so [100%] Built target pyngp make: *** [Makefile:91: all] Error 2