Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
Paper • 2605.20104 • Published • 7
Jun Zhang
junzhang98
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 6 days ago
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding upvoted a collection over 1 year ago
Skynet upvoted a paper over 1 year ago
Train Small, Infer Large: Memory-Efficient LoRA Training for Large
Language ModelsOrganizations
