NVIDIA Container Toolkit: NVIDIA GPU access for containers
NVIDIA/nvidia-container-toolkit
Configures NVIDIA GPU access for container runtimes such as Docker, supporting containerized inference, training and CUDA workloads.
ToolAI.io · Chaîne GitHub
Découvrez les nouveaux projets AI open source ajoutés sur GitHub, avec les informations du dépôt, les instructions de configuration, les licences et les ressources associées.
Données du dépôt public
NVIDIA/nvidia-container-toolkit
Configures NVIDIA GPU access for container runtimes such as Docker, supporting containerized inference, training and CUDA workloads.
microsoft/TRELLIS.2
Microsoft’s 3D generation project with image-to-3D inference, PBR texturing and GLB export for GPU-equipped asset workflows.
hpcaitech/ColossalAI
Distributed training and inference tools for parallelism and memory management in large-model workloads.
2noise/ChatTTS
Conversational Chinese and English speech generation with speaker and prosody controls; released model weights are noncommercial.
google-ai-edge/mediapipe
On-device ML libraries, models, and tools for vision, text, and audio across supported platforms.
janhq/jan
A local AI chat application for running models on a personal computer.
ray-project/ray
A distributed computing runtime for machine learning training, tuning and model serving.
mudler/LocalAI
A local inference engine for self-hosting models and AI services.
ultralytics/yolov5
A PyTorch-based object detection project with training, inference and export workflows.
ultralytics/ultralytics
Training and inference tools for object detection, segmentation and pose estimation models.
ollama/ollama
A tool for running and managing large language models locally.
MoonshotAI/checkpoint-engine
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
Page 1 / 4 · 46 projets