Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility
Paper • 2605.06105 • Published • 3
jeongseokoh
jeongseokoh
·
AI & ML interests
Large Language Models, Efficient LLM, Trustworthy AI
Recent Activity
updated a model 14 minutes ago
jeongseokoh/Llama-3.1-8B-Instruct_SFT updated a model about 6 hours ago
jeongseokoh/Qwen3-8B_SPEED-24-BoS_PrefixBoS published a model about 6 hours ago
jeongseokoh/Qwen3-8B_SPEED-24-BoS_PrefixBoSOrganizations
authored a
paper 7 days ago
submitted a
paper to Daily Papers 14 days ago