marcusguhao/Qwen3-4B-gate-IndexMem-rvkl16k-local128-b256-decay
Updated
guhao
marcusguhao
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression upvoted a paper about 8 hours ago
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation upvoted a paper about 8 hours ago
Block Sparse Attention with Log-Linear ComplexityOrganizations
None yet
marcusguhao/Qwen-3-8B-gqa_indexer_scalar-rvkl_16k_local128_b256_decay
Updated
marcusguhao/Qwen3-8B-gate-IndexMem
Updated
marcusguhao/Qwen-3-8B-gqa_indexer_scalar-stage1
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
marcusguhao/SVD-MoE-merge
Updated
marcusguhao/SVD-MoE-merge-code
Updated
marcusguhao/baichuan-moe-hf-3B-vllm
Updated
marcusguhao/Qwen2-1.5B-int3-128g_q3f16_1
Updated
marcusguhao/Qwen2-1.5B-Instruct-q4f16_1
Updated
marcusguhao/Qwen2-1.5B-Instruct-q0f16-no-quantized
Updated
marcusguhao/Qwen2-1.5B-Instruct-baichuan-distill_q3f16_0
Updated
marcusguhao/Qwen2-1.5B-Instruct-baichuan-distill_q3f16_1
Updated
marcusguhao/Llama-3.2-1B_q3f16_1_MLC
Updated
marcusguhao/Llama-3.2-3B_q3f16_1_MLC
Updated