Learned KV-cache eviction gates for Qwen3, from "The Gating Mechanism of KV Cache Eviction".
guhao
marcusguhao
·
AI & ML interests
None yet
Recent Activity
updated a model 9 days ago
marcusguhao/IndexMem-Qwen3-4B updated a model 9 days ago
marcusguhao/IndexMem-Qwen3-8B upvoted a paper about 1 month ago
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language ModelsOrganizations
None yet
models 20
marcusguhao/IndexMem-Qwen3-4B
Updated
marcusguhao/IndexMem-Qwen3-8B
Updated
marcusguhao/llama-2-13b-hessian
Updated
marcusguhao/llama-30b-hessian
Updated
marcusguhao/llama-30b-inv_hessian
Updated
marcusguhao/llama-3-8b-inv_hessian
Updated
marcusguhao/llama-3-8b-hessian
Updated
marcusguhao/llama-2-13b-inv_hessian
Updated
marcusguhao/llama-2-7b-inv_hessian
Updated
marcusguhao/llama-2-7b_hessian
Updated
datasets 0
None public yet