Georgi Gerganov @ggerganov
2 of this account's posts made the board, 1 reached the top 3.
72.8K followersOpen Source 2 Follow on X
Stories from this source
-
llama.cpp Heterogeneous Distributed Inference
Georgi Gerganov says llama.cpp appeared on the Windows event stage, showing software and hardware stacks finally coming together for local AI.
-
llama.cpp Adds DFlash Acceleration
llama.cpp's author advises Qwen3.8-27B+MTP users to upgrade to DFlash for extra speed, requiring the latest llama.cpp v0.6.0.