conftrace_

token processing

5 papers

Explore in graph

Co-occurring keywords

large language model (13587) mixture of expert (640) language model (4599) neural network architecture (362) layer skipping (19) parameter efficiency (417) context window (73) expert activation (5) dynamic computation (16) nested expert (1)

Papers

D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models NIPS 2024
Mixture of Nested Experts: Adaptive Processing of Visual Tokens NIPS 2024
Multi-Head Mixture-of-Experts NIPS 2024
Fairness in Serving Large Language Models OSDI 2024
∞Bench: Extending Long Context Evaluation Beyond 100K Tokens ACL 2024