mirror of
https://github.com/Lizonghang/prima.cpp.git
synced 2025-09-08 21:39:17 +00:00
* enable qwen to llama.cpp * llama : do not GPU split bias tensors --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
1 line
No EOL
28 B
Text
1 line
No EOL
28 B
Text
You are a helpful assistant. |