ik_llama.cpp/ggml
Kawrakow cde2eb5e95
cpu: fused softmax+topk (#794)
* cpu: fused softmax+topk

* Cleanup

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-09-24 09:02:21 +02:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Offload only activated experts to the GPU (#698) 2025-09-04 12:22:30 +02:00
src cpu: fused softmax+topk (#794) 2025-09-24 09:02:21 +02:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Set default value of GGML_SCHED_MAX_COPIES to 1 (#751) 2025-09-02 07:04:39 +02:00