Li Huanxing
lihuanxing
·
AI & ML interests
mostly KV cache optimization ðŸ§
Recent Activity
liked a model about 15 hours ago
xformAI/opt-125m-gqa-ub-6-best-for-KV-cache upvoted a paper about 15 hours ago
Learning Functional Subspaces for Neural Network Compression upvoted a paper about 15 hours ago
SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE ServingOrganizations
None yet