llama : mark LLM_ARCH_STARCODER as full offload supported (#3945)
as done in https://github.com/ggerganov/llama.cpp/pull/3827
M
Meng Zhang committed
3d48f42efcd05381221654376e9f6f69d76af739
Parent: c41ea36
Committed by GitHub <noreply@github.com>
on 11/5/2023, 12:40:08 PM