SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention Paper • 2610.02953 • Published 15 days ago
zjiayu064/Qwen3-235B-A22B-Instruct-2507-BitsMoE-1.6bit Text Generation • 22B • Updated 13 days ago • 588
zjiayu064/Qwen3-235B-A22B-Instruct-2507-BitsMoE-1.6bit Text Generation • 22B • Updated 13 days ago • 588
zjiayu064/Qwen3-Next-80B-A3B-Instruct-BitsMoE-2bit Text Generation • 8B • Updated 18 days ago • 554 • 1
BitsMoE: Cost-Aware Bit Allocation in Spectral Space for MoE LLM Quantization Paper • 2606.00079 • Published 20 days ago • 1
zjiayu064/Qwen3-Next-80B-A3B-Instruct-BitsMoE-2bit Text Generation • 8B • Updated 18 days ago • 554 • 1