Fast and memory-efficient exact attention
Repository Index
47,133 repositories indexed
1–13 of 13 · Most stars
Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
- pytorch
- protein-structure
- alphafold2
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
Thin, unified, C++-flavored wrappers for the CUDA APIs
- api-wrapper
- cuda
- cuda-runtime-api
- modern-cpp
C++ implementation of a fast and memory efficient HAT-trie
- cpp
- trie
- hat-trie
- data-structures
Code for PaperRobot: Incremental Draft Generation of Scientific Ideas
- pytorch
- memory-networks
- generation
- end-to-end-learning
End-To-End Memory Network using Tensorflow
- memory-networks
- tensorflow
- nlp
BatchFlow helps you conveniently work with random or sequential batches of your data and define data processing and machine learning workflows even for datasets that do not fit into memory.
- python3
- data-science
- machine-learning
- python
MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting
TranslatedOpenMinutes · Voice recorder workbench: import · transcription · AI categorization · search and review of MemoTalk S1 recordings (open-source implementation of Floatboat Workbench)
- ai-classification
- floatboat
- react
- speech-to-text
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory, RAG and observability. Plug-and-play from chat UI to full agents.