Files
whisper.cpp/ggml
Aman Gupta 20209c25f7 Deepseek 4: -sm tensor (llama/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
2026-08-25 15:28:56 +03:00
..
2026-08-25 15:28:56 +03:00