Kawrakow 996e77047a Avoid ggml_get_rows if not necessary (#1160) ...

* Copy reduce result to other GPUs if necessary

* Avoid ggml_get_rows for TG

* For the output ops use the result of the split that ran on the main GPU

* More models

2026-01-20 15:38:21 +02:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

server: improve speed of speculative decoding (#1119)

2026-01-10 08:01:22 +02:00

src

Avoid ggml_get_rows if not necessary (#1160)

2026-01-20 15:38:21 +02:00

.gitignore

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

CMakeLists.txt

CUDA: compress-mode size (#1110)

2026-01-07 18:33:17 +02:00