llama.cpp/ggml
Max Krasnyansky 26ec40967c profiler: output all tensor names 2025-12-17 17:11:21 -08:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653) 2025-12-15 09:24:59 +01:00
src profiler: output all tensor names 2025-12-17 17:11:21 -08:00
.gitignore
CMakeLists.txt profiler: initial support for profiling graph ops 2025-12-17 17:11:21 -08:00