{"id":16971258,"url":"https://github.com/phineas-pta/nvidia-win","last_synced_at":"2025-04-12T00:42:14.567Z","repository":{"id":200132136,"uuid":"704885767","full_name":"phineas-pta/NVIDIA-win","owner":"phineas-pta","description":"NVIDIA’s deep learning stack on Windows: CUDA toolkit + cuDNN + TensorRT","archived":false,"fork":false,"pushed_at":"2025-03-19T22:35:16.000Z","size":88,"stargazers_count":6,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-12T00:42:10.061Z","etag":null,"topics":["cuda","cudnn","guide","tensorrt","tutorial","windows"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc-by-4.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/phineas-pta.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-10-14T11:59:34.000Z","updated_at":"2025-03-19T22:35:20.000Z","dependencies_parsed_at":"2023-10-21T00:38:08.771Z","dependency_job_id":"35ed5ed9-afcd-452e-abf4-875e44877ce6","html_url":"https://github.com/phineas-pta/NVIDIA-win","commit_stats":{"total_commits":3,"total_committers":1,"mean_commits":3.0,"dds":0.0,"last_synced_commit":"f102a691f853938dd9866dd4d2f9e18bdbd86c4c"},"previous_names":["phineas-pta/nvidia-win"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phineas-pta%2FNVIDIA-win","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phineas-pta%2FNVIDIA-win/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phineas-pta%2FNVIDIA-win/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phineas-pta%2FNVIDIA-win/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/phineas-pta","download_url":"https://codeload.github.com/phineas-pta/NVIDIA-win/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248501958,"owners_count":21114681,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cuda","cudnn","guide","tensorrt","tutorial","windows"],"created_at":"2024-10-14T00:49:48.878Z","updated_at":"2025-04-12T00:42:14.559Z","avatar_url":"https://github.com/phineas-pta.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"![License](https://img.shields.io/github/license/phineas-pta/NVIDIA-win?logo=creativecommons)\n![Platform](https://img.shields.io/badge/Platform-win_64-0078D4?logo=windows)\n![Cuda](https://img.shields.io/badge/CUDA-v12.8-76B900?logo=nvidia)\n![Cudnn](https://img.shields.io/badge/cuDNN-v9.8-76B900?logo=nvidia)\n![Tensorrt](https://img.shields.io/badge/TensorRT-v10.9-76B900?logo=nvidia)\n![Python](https://img.shields.io/badge/python-v3.1x-3776AB?logo=python)\n![VS](https://img.shields.io/badge/Visual_Studio-v17_2022-5C2D91?logo=visualstudio)\n![Cmake](https://img.shields.io/badge/CMake-v3.2x-064F8C?logo=cmake)\n\n# NVIDIA-win\n\nhow to install the NVIDIA’s deep learning stack on Windows: CUDA toolkit + cuDNN + TensorRT,\u003cbr /\u003ealso various attempts to compile deep learning libraries with cuda\n\nonly for Windows 10/11 + recent RTX cards recommended\n\nall comands here are for cmd, if u prefer pwsh must change to adapt\n\nsome values are censored with black box ███ so u have to fill in with your use case\n\n**1st of all:** 👉👉👉 [install CUDA toolkit + cuDNN + TensorRT](NVIDIA-win.md) 👈👈👈\n\nmy attempts to build various deep learning libraries:\n1. [build onnxruntime](test01-onnxruntime.md) ✅\n2. [build whisper.cpp with cuBLAS](test02-whisper.cpp-cublas.md) ✅\n3. [build CTranslate2 to use faster-whisper](test03-ctranslate2.md) ❌\n4. [build triton to use xformers](test04-triton.md) ❌\n5. [try out TensorRT-LLM](test05-trt-llm.md) ❌\n6. [build OpenCV with CUDA](test06-opencv.md) ✅\n7. [build Torch-TensorRT](test07-torch-tensorrt.md) ❌\n8. [build llama.cpp with cuBLAS](test08-llama.cpp-cublas.md) ✅\n9. [build Stan with OpenCL](test09-stan-opencl.md) ✅\n\nall above guides are under CC-BY-4.0\n\nmore complicated tweaking with TensorRT (under GPLv3)\n- build Real-ESRGAN with TensorRT on Windows: https://github.com/phineas-pta/RealESRGAN-trt-win ✅\n- run Stable Diffusion XL with TensorRT natively on Windows: https://github.com/phineas-pta/SDXL-trt-win ✅\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphineas-pta%2Fnvidia-win","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fphineas-pta%2Fnvidia-win","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphineas-pta%2Fnvidia-win/lists"}