Add Qwen3.5-MoE architecture support and fix Qwen3-VL-MoE linear attention weights - #696

Add Qwen3.5-MoE architecture support and fix Qwen3-VL-MoE linear attention weights#696

alchernysh wants to merge 2 commits into

arcee-ai:mainarcee-ai/mergekit:mainfrom

alchernysh:add-qwen3-5-moe-architecturealchernysh/mergekit:add-qwen3-5-moe-architectureCopy head branch name to clipboard