llama.cpp
3d48f42e - llama : mark LLM_ARCH_STARCODER as full offload supported (#3945)

Commit

1 year ago

llama : mark LLM_ARCH_STARCODER as full offload supported (#3945) as done in https://github.com/ggerganov/llama.cpp/pull/3827

References

Author

wsxiaoys

Parents