LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
Paper
•
2407.14057
•
Published
•
46
AI & ML interests
We are building the next-gen AI inference platform
mahyar-najibi
authored
6
papers
over 1 year ago
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper
•
2404.15653
•
Published
•
29
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework
Paper
•
2404.14619
•
Published
•
126
GINA-3D: Learning to Generate Implicit Neural Assets in the Wild
Paper
•
2304.02163
•
Published
•
1
Speculative Streaming: Fast LLM Inference without Auxiliary Models
Paper
•
2402.11131
•
Published
•
42
Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation
Paper
•
2404.06910
•
Published
•
3