2026-10-07 · America/Los_Angeles · 社区动态 · #6

llama: add a GPU cache for MoE experts kept in host memory by am17an · Pull Request #29887 · ggml-org/llama.cpp

Potentially big speedup for MoE models that don’t fully fit in VRAM. Are you GPU Poor? Show your speedups;) update https://github.com/ggml-org/llama.cpp/pull/30112 MERGED

阅读原文查看评分、趋势与关联来源阅读整期日报

llama: add a GPU cache for MoE experts kept in host memory by am17an · Pull Request #29887 · ggml-org/llama.cpp

热度 52.4 / 100；排名与评分保留该期记录。