| Name | Version | Summary | date |
| ant-ray-cpp-nightly |
3.0.0.dev20251101 |
A subpackage of Ray which provides the Ray C++ API. |
2025-11-01 08:04:20 |
| ray-cpp |
2.51.1 |
A subpackage of Ray which provides the Ray C++ API. |
2025-11-01 03:25:23 |
| ray |
2.51.1 |
Ray provides a simple, universal API for building distributed applications. |
2025-11-01 03:23:30 |
| ve-ray |
2.46.0.2 |
Ray provides a simple, universal API for building distributed applications. |
2025-10-21 13:22:22 |
| ant-ray-nightly |
3.0.0.dev20251019 |
Ray provides a simple, universal API for building distributed applications. |
2025-10-19 08:26:49 |
| tensorflow-serving-api-gpu |
2.19.1 |
TensorFlow Serving Python API. |
2025-08-19 04:54:03 |
| tensorflow-serving-api |
2.19.1 |
TensorFlow Serving Python API. |
2025-08-19 04:54:01 |
| ant-ray-cpp |
3.0.0.dev0 |
A subpackage of Ray which provides the Ray C++ API. |
2025-08-03 03:53:46 |
| ant-ray |
2.42.2 |
Ray provides a simple, universal API for building distributed applications. |
2025-02-15 06:42:26 |
| torch-workflow-archiver-nightly |
2025.2.7 |
Torch Workflow Archiver is used for creating archives of workflow designed using trained neural net models that can be consumed by TorchServe inference |
2025-02-07 11:27:25 |
| torch-model-archiver-nightly |
2025.2.7 |
Torch Model Archiver is used for creating archives of trained neural net models that can be consumed by TorchServe inference |
2025-02-07 11:27:23 |
| torchserve-nightly |
2025.2.7 |
TorchServe is a tool for serving neural net models for inference |
2025-02-07 11:27:17 |
| jina |
3.33.0 |
Multimodal AI services & pipelines with cloud-native stack: gRPC, Kubernetes, Docker, OpenTelemetry, Prometheus, Jaeger, etc. |
2024-12-20 12:13:56 |
| ray-nightly |
3.0.0.dev20241219 |
Ray provides a simple, universal API for building distributed applications. |
2024-12-19 14:00:26 |
| torch-workflow-archiver |
0.2.15 |
Torch Workflow Archiver is used for creating archives of workflow designed using trained neural net models that can be consumed by TorchServe inference |
2024-09-30 18:57:48 |
| torch-model-archiver |
0.12.0 |
Torch Model Archiver is used for creating archives of trained neural net models that can be consumed by TorchServe inference |
2024-09-30 18:57:46 |
| torchserve |
0.12.0 |
TorchServe is a tool for serving neural net models for inference |
2024-09-30 18:57:42 |
| multi-model-server-gpu |
0.0.2 |
(Altered for multiprocessing GPU Inference) Multi Model Server is a tool for serving neural net models for inference |
2024-09-09 19:18:04 |
| mlModelSaver |
1.0.33 |
Make life easier for saving and serving ML models |
2024-06-20 07:30:14 |
| iog-sdk |
0.0.1 |
IOG SDK - Internet of GPUs - IO.net |
2024-04-29 22:27:48 |