The llama.cpp project has released version b11439, which includes refactoring of selective expert copying to user code. This update also incorporates tests for enrolling two models into the selective expert copy test, specifically using DeepSeek2 as a test model. The release also features improved comments and whitespace fixes. AI
IMPACT This update to llama.cpp improves its infrastructure for handling selective expert copying and testing, potentially enhancing performance for models like DeepSeek2.
RANK_REASON This is a software update for a specific project, 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 →