Skip to main content

v1.1.0

· One min read
  • llama.cpp updated to b2717
  • Phi3, Mamba(CPU only), gemma, StarCoder2, GritLM, Command-R, MobileVLM_V2, qwen2moe models
  • IQ1_S, IQ2_S, IQ2_M, IQ3_S, IQ4_NL, IQ4_XS quntization support
  • Performance improvements
  • Fixed crash when EOS option is on
  • Fixed image orientation