Savant
aphrodite-engine
Savant | aphrodite-engine | |
---|---|---|
54 | 2 | |
482 | 580 | |
3.3% | 25.9% | |
9.3 | 9.7 | |
8 days ago | 7 days ago | |
Python | Python | |
Apache License 2.0 | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Savant
-
🚀 Savant 0.2.6 is Out: Release Notes
Website: https://savant-ai.io/
-
Meet a new Savant Demo: Realtime (45 FPS) YOLOv8 instance segmentation
Link: https://github.com/insight-platform/Savant/tree/develop/samples/yolov8_seg
- Opt for a new innovative deep learning and computer vision framework on Nvidia platforms.
- Experience the benefits of a new Nvidia-optimized open-source framework in computer vision projects.
aphrodite-engine
-
Using vLLM for Home Assistant. I need help getting any model to work. Can't get anything over 7B to run on a 3090.
Try out https://github.com/PygmalionAI/aphrodite-engine
-
Mistral 7B,The complete Guide of the Best 7B model
If you want to host for the AI Horde, Aphrodite has the most GPU throughput, and Koboldcpp is the easiest and quite flexible:
https://github.com/PygmalionAI/aphrodite-engine
What are some alternatives?
pipeless - An open-source computer vision framework to build and deploy apps in minutes without worrying about multimedia pipelines [Moved to: https://github.com/pipeless-ai/pipeless]
koboldcpp - A simple one-file way to run various GGML and GGUF models with KoboldAI's UI
rpi-object-detection - Real-time object detection and tracking using Raspberry Pi and OpenCV!
dataset-viewer - Lightweight web API for visualizing and exploring any dataset - computer vision, speech, text, and tabular - stored on the Hugging Face Hub
caer - High-performance Vision library in Python. Scale your research, not boilerplate.
PhotoScavengerBackend - Backend for my Scangame react apps. It's a simple image recognition model that helps me understand API's, AI and native app development
nebuly - The user analytics platform for LLMs
astroid - A common base representation of python source code for pylint and other projects
jetson-inference - Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
petals - 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Pine - :evergreen_tree: Aimbot powered by real-time object detection with neural networks, GPU accelerated with Nvidia. Optimized for use with CS:GO.
FedML - FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on any GPU cloud or on-premise cluster. Built on this library, FEDML Nexus AI (https://fedml.ai) is your generative AI platform at scale.