mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-02 09:12:03 +00:00
* suport multiple cards: split-mode - layer|row * rm warning * rebase with master, support tow new OPs, close feature for -sm=row, fix for unit test * update news * fix merge error * update according to review comments
41 KiB
41 KiB