llama.cpp/ggml
uvos c7aa1364fd
HIP: Ignore unsupported unroll transformation in fattn-vec (#14931)
llvm with the amdgcn target dose not support unrolling loops with conditional break statements, when those statements can not be resolved at compile time. Similar to other places in GGML lets simply ignore this warning.
2025-07-29 17:43:43 +02:00
..
cmake cmake : Indent ggml-config.cmake (ggml/1310) 2025-07-28 08:15:01 +03:00
include ggml: Add initial WebGPU backend (#14521) 2025-07-16 18:18:51 +03:00
src HIP: Ignore unsupported unroll transformation in fattn-vec (#14931) 2025-07-29 17:43:43 +02:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml-cpu : disable GGML_NNPA by default due to instability (#14880) 2025-07-25 19:09:03 +02:00