Distributed training & inference for multimodal perception: shared embeddings across text, images, video, audio, code & graphs from 64 to 1024 dimensions 🖼️
- huggingface-transformers
- language-vision
- multimodal
- pytorch
108,094 visible repositories in the index
1–3 of 3 · Most stars
Distributed training & inference for multimodal perception: shared embeddings across text, images, video, audio, code & graphs from 64 to 1024 dimensions 🖼️
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
cuVS - a library for vector search and clustering on the GPU