Distributed Inference and Fine-tuning of Large Language Models Over The Internet
Paper
•
2312.08361
•
Published
•
25
Serving
-
-
Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes
Paper • 2312.06353 • Published • 6 -
Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache
Paper • 2401.02669 • Published • 14 -
LLM in a flash: Efficient Large Language Model Inference with Limited Memory
Paper • 2312.11514 • Published • 257