S-LoRA: Serving Thousands of Concurrent LoRA Adapters
Paper • 2311.03285 • Published • 30
Nicholas Lee
nicholaslee
AI & ML interests
NLP, Speech, Efficient ML, Generative
Recent Activity
upvoted a paper 5 days ago
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution upvoted a paper 2 months ago
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts upvoted a paper 9 months ago
Arbitrage: Efficient Reasoning via Advantage-Aware SpeculationOrganizations
authored 2
papers about 2 years ago
authored a
paper over 2 years ago