llama.cpp
bf0a29cc - Deepseek 4: `-sm tensor` (#26490)

Commit
76 days ago
Deepseek 4: `-sm tensor` (#26490) * DSV4: sm tensor * set coarser granularity for head splits * fix dspark * add model saving for dsv4 + allow dflash to return on specific device * add comment about dsv4 seq_rm * simplify * add shared expert delayed allreduce * remove special test for dsv4
Author
Parents
Loading