llama.cpp releasesTools
b12146: metal : fuse DeepSeek-V4/V4.1 and GLM MoE routing (#31615)
metal : support scale-bias routing norm in the TOPK_MOE fusion The DeepSeek-V4.1 graph normalizes the routing weights with a scale+bias (sum + 1e-20) instead of the lower clamp used by the other…
Read at llama.cpp releases ↗Related

AsiaPowered by GPT-6, Unitree humanoid robots master painting, chess without training, says CEO SCMP Tech

SiliconAnthropic loosens Claude's game cloning ban Tom's Hardware
JapanGPT-6モデルはAstra、Sol、それともLuna? OpenAIが教える、Codex爆速開発の鉄則 ITmedia AI+

AsiaMoonshot AI releases Kimi K3.1 Pro model weights TechNode

AsiaChina Merchants' LionRock AI Lab Open-Sources Lion-ER-35B-A3B Embodied Reasoning Model Pandaily
