llama.cpp/ggml
Nikodem Eluszkiewicz 1cee8b9dc1
Merge 0aae7d78c7 into 6b949d1078
2026-04-01 18:54:19 +08:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include ggml : limit the first TurboQuant CPU PR to TBQ 2026-03-27 23:57:43 +01:00
src Merge 0aae7d78c7 into 6b949d1078 2026-04-01 18:54:19 +08:00
.gitignore
CMakeLists.txt ggml-cpu: fix fallback for RVV kernels without zvfh (#21157) 2026-04-01 11:10:03 +03:00