| Name | Version | Summary | date |
| megatron-bridge |
0.1.0rc0 |
Megatron Bridge: Training Recipes for Megatron-based LLM and VLM models |
2025-08-16 00:22:29 |
| cutensor-cu12 |
2.3.0 |
NVIDIA cuTENSOR |
2025-08-15 16:50:57 |
| cutensor-cu13 |
2.3.0 |
NVIDIA cuTENSOR |
2025-08-15 15:26:06 |
| gpu-benchmark-linux |
0.1.0 |
GPU基准测试工具 - 用于评估NVIDIA GPU性能的综合工具包 |
2025-08-15 09:46:36 |
| cuda-switch |
1.0.0 |
A tool for managing multiple CUDA versions on macOS |
2025-08-15 02:41:21 |
| nvidia-cusparselt-cu12 |
0.8.0 |
NVIDIA cuSPARSELt |
2025-08-13 19:27:03 |
| nvidia-cusparselt-cu13 |
0.8.0 |
NVIDIA cuSPARSELt |
2025-08-13 19:22:40 |
| nvidia-cusolvermp-cu12 |
0.7.0.833 |
cuSOLVERMp - runtime libraries |
2025-08-13 17:26:11 |
| nvidia-cublasmp-cu12 |
0.5.1.65 |
cuBLASMp - runtime libraries |
2025-08-12 19:10:48 |
| aiconfigurator |
0.1.0 |
aiconfigurator: automatic disaggregated serving offline configuration |
2025-08-12 19:10:42 |
| ai-dynamo-runtime |
0.4.0 |
Dynamo Inference Framework Runtime |
2025-08-11 23:23:51 |
| ai-dynamo |
0.4.0 |
Distributed Inference Framework |
2025-08-11 23:22:20 |
| nv2a-pretty |
0.1.1 |
Visualizer for xemu/nv2a-trace XBOX GPU (nv2a) logs. |
2025-08-11 22:09:42 |
| trtruntime |
0.1.0 |
A lightweight TensorRT inference runtime for Python, inspired by onnxruntime |
2025-08-10 20:12:58 |
| gpu-benchmark-tool |
0.4.6 |
Multi-vendor GPU health monitoring supporting old GPUs for e-waste reduction |
2025-08-09 07:08:40 |
| nvidia-cudnn-cu13 |
9.12.0.46 |
cuDNN runtime libraries |
2025-08-07 20:45:35 |
| nvidia-cudnn-cu12 |
9.12.0.46 |
cuDNN runtime libraries |
2025-08-07 20:45:10 |
| nvidia-nvtiff-tegra-cu13 |
0.5.1.75 |
NVIDIA nvTIFF native runtime libraries |
2025-08-06 22:31:28 |
| nvidia-nvtiff-cu13 |
0.5.1.75 |
NVIDIA nvTIFF native runtime libraries |
2025-08-06 22:30:36 |
| nvidia-nvjpeg2k-tegra-cu13 |
0.9.0.43 |
NVIDIA nvJPEG2000 native runtime libraries |
2025-08-06 22:22:41 |