BeefAndPoultry@lemmus.orgEnglish · edit-22 days agollama.cpp in progress pull request for smart caching of MoE experts, 16% to 35% TPS boost for my RTX 2080plus-squaregithub.comexternal-linkmessage-square1fedilinkarrow-up13arrow-down10
arrow-up13arrow-down1external-linkllama.cpp in progress pull request for smart caching of MoE experts, 16% to 35% TPS boost for my RTX 2080plus-squaregithub.comBeefAndPoultry@lemmus.orgEnglish · edit-22 days agomessage-square1fedilink
BeefAndPoultry@lemmus.orgEnglish · edit-24 days agoQwen 3.8 Max (2.4T-a95b) and 27B open weights being released next weekplus-squarelemmus.orgimagemessage-square12fedilinkarrow-up13arrow-down10
arrow-up13arrow-down1imageQwen 3.8 Max (2.4T-a95b) and 27B open weights being released next weekplus-squarelemmus.orgBeefAndPoultry@lemmus.orgEnglish · edit-24 days agomessage-square12fedilink
SirDimples@programming.devEnglish · edit-24 days agoGLM-5.3 Imminent dropplus-squaregithub.comexternal-linkmessage-square7fedilinkarrow-up10arrow-down10
arrow-up10arrow-down1external-linkGLM-5.3 Imminent dropplus-squaregithub.comSirDimples@programming.devEnglish · edit-24 days agomessage-square7fedilink