git/ik_llama.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
ik/format_name
ik_llama.cpp/ggml
History
Iwan Kawrakow 1f96fc97c6 Faster tensor name formatting 
We gain ~1% for Ling-mini-2.0 when running on CUDA.
2025-10-24 07:42:04 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Fused mul + multi_add op (#858) 2025-10-24 07:40:35 +03:00
src Faster tensor name formatting 2025-10-24 07:42:04 +03:00
.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