In #11362 hip graph was disabled by default as, at the time, its performance impact was negative. Due to improvements in rocm and our usage and construction of graphs this is no longer true, so lets change the default.
set_property(CACHE GGML_CUDA_COMPRESSION_MODE PROPERTY STRINGS "none;speed;balance;size")
option(GGML_HIP "ggml: use HIP" OFF)
-option(GGML_HIP_GRAPHS "ggml: use HIP graph, experimental, slow" OFF)
+option(GGML_HIP_GRAPHS "ggml: use HIP graph" ON)
option(GGML_HIP_RCCL "ggml: use ROCm Collective Comm. Library" OFF)
option(GGML_HIP_NO_VMM "ggml: do not try to use HIP VMM" ON)
option(GGML_HIP_ROCWMMA_FATTN "ggml: enable rocWMMA for FlashAttention" OFF)