The llama.cpp project has released version b11626, which addresses an issue where layers were not split evenly when no device reported free memory. Previously, a NaN split caused layers to be sent to an invalid device index, leading to loading aborts. This update normalizes the split points to prevent such errors. AI
IMPACT Improves the stability and performance of the llama.cpp inference engine for users running models on systems with limited memory.
RANK_REASON This is a software release for a specific tool, not a frontier model release or significant industry event.
Read on llama.cpp — Releases →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →