Visual Studio build configurations
Project: _AugmentedIntelligence.vcxproj · toolset v145 · platform x64 (primary).
Configurations
| Configuration | GPU/CUDA | TensorRT | SIMD | Llama build dir | Preprocessor highlights | |
| **Debug \ | x64** | Toolkit present | no | default | default | Dev |
| **Release \ | x64** | CUDA linked | no | default | llama_build | USE_CUDA, AI_MATHNN_LEARN, AI_REALITY_CONSTRUCT |
| **Release-GPU-AVX512 \ | x64** | CUDA | no | AVX-512 | llama_build | USE_CUDA, AI_MATHNN_LEARN, AI_REALITY_CONSTRUCT, AI_MATHNN_LARGE |
| **Release-GPU-AVX2 \ | x64** | CUDA | no | AVX2 | llama_build_cuda_avx2 | same + AI_MATHNN_LARGE |
| **Release-GPU-AVX512-Tensor \ | x64** | CUDA | yes | AVX-512 | llama_build | above + `AI_USE_TENSORRT`, `AI_TENSOR_ACCEL` |
| **Release-GPU-AVX2-Tensor \ | x64** | CUDA | yes | AVX2 | llama_build_cuda_avx2 | above + `AI_USE_TENSORRT`, `AI_TENSOR_ACCEL` |
| **Release-CPU-AVX2 \ | x64** | No CUDA libs | no | AVX2 | llama_build_cpu_avx2 | AI_CPU_ONLY, AI_MATHNN_LEARN, AI_REALITY_CONSTRUCT |
| **Release-CPU-NoAVX \ | x64** | No CUDA | no | NoExtensions | llama_build_cpu_noavx | AI_CPU_ONLY, AI_MATHNN_LEARN, AI_REALITY_CONSTRUCT |
Tensor configs (AVX2 Tensor / AVX512 Tensor)
These ship NVIDIA TensorRT inference (TensorRT.cpp) on top of the matching GPU+SIMD baseline.
- Install TensorRT 8.x+ for your CUDA version.
- Either:
- Copy/extract under third_party/tensorrt/ with include/ and lib/, or
- Build with /p:TensorRtDir=C:\Path\To\TensorRT
- Select configuration in VS or:
[powershell]
.\scripts\build_v145.ps1 -Configuration Release-GPU-AVX2-Tensor -Platform x64
.\scripts\build_v145.ps1 -Configuration Release-GPU-AVX512-Tensor -Platform x64
Linked: nvinfer.lib, nvonnxparser.lib, nvinfer_plugin.lib.
Post-build copies nvinfer*.dll when present under $(TensorRtDir)\lib or \bin.
Without TensorRT installed, non-Tensor GPU configs still build; Tensor configs will fail at link until TensorRtDir is valid.
Compile-type notes
- `UseCuda` — GPU configs true; CPU false.
- `USE_CUDA` — RealityConstruct hybrid, MathNNDevice GPU, RemoteCuda.
- `AI_USE_TENSORRT` / `AI_TENSOR_ACCEL` — TensorRT OD path enabled at compile time.
- `AI_CPU_ONLY` — no NVIDIA driver required.
- `AI_MATHNN_LEARN`, `AI_REALITY_CONSTRUCT`, `AI_MATHNN_LARGE` — feature markers.
Build scripts
[powershell]
.\scripts\build_v145.ps1
.\scripts\build_v145.ps1 -Configuration Release-GPU-AVX2 -Platform x64
.\scripts\build_v145.ps1 -Configuration Release-GPU-AVX2-Tensor -Platform x64
.\scripts\build_v145.ps1 -Configuration Release-CPU-AVX2 -Platform x64
Recommended picks
| Machine | Configuration |
| NVIDIA + modern CPU + TensorRT | `Release-GPU-AVX2-Tensor` or `Release-GPU-AVX512-Tensor` |
| NVIDIA + modern CPU (no TRT) | Release-GPU-AVX2 or Release-GPU-AVX512 |
| No GPU laptop | Release-CPU-AVX2 |
| Max compatibility | Release-CPU-NoAVX |
| Day-to-day dev | Release x64 |
Filed under: Uncategorized - @ July 18, 2026 6:11 am