
DeepSpeed-MII
by deepspeedai (organization)
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed. (description from the project’s GitHub page)
Repository facts
- Stars
- 2,115
- Forks
- 192
- Open issues and pull requests
- 210
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- deepspeedai · Organization
- Created
- Mar 23, 2022
- Last push
- Jun 30, 2025
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 96: ultralytics/yolov5
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
58,181 starsPythonAGPL-3.0Last push Oct 18, 2026
Rank 141: deepspeedai/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
43,242 starsPythonApache-2.0Last push Oct 18, 2026
Rank 769: ultralytics/yolov3
PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.
10,622 starsPythonAGPL-3.0Last push Oct 17, 2026
Rank 8,662: Ki6an/fastT5
⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
586 starsPythonApache-2.0Last push Apr 24, 2023
Rank 8,809: open-nudge/torchlayers
Shape and dimension inference (Keras-like) for PyTorch layers and neural networks
572 starsPythonMITLast push Jun 13, 2022